Skip to main content

AI Hub Rankings

Compare 361 paid AI models across quality, price, and value.

Value score

Live-recomputes the Value column from your workload.

#Model
1Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) anthropic100.0%100.0%1.5K$10.00 /M in$50.00 /M out1.0M ctx
2Claude Opus 4.8 (Adaptive Reasoning, Max Effort) anthropic93.0%97.1%2.6K$5.00 /M in$25.00 /M out1.0M ctx
3GPT-5.5 (xhigh) openai91.5%97.9%2.4K$5.00 /M in$30.00 /M out400K
4Claude Opus 4.7 (Adaptive Reasoning, Max Effort) anthropic89.3%96.2%2.4K$5.00 /M in$25.00 /M out1.0M ctx
5GPT-5.5 (high) openai88.6%93.6%2.3K$5.00 /M in$30.00 /M out400K
6GPT-5.4 (xhigh) openai85.8%92.9%4.3K$2.50 /M in$15.00 /M out400K
7GLM-5.2 (max) zai85.3%89.9%8.5K$1.40 /M in$4.40 /M out—
8Gemini 3.5 Flash (high) google83.8%91.6%6.8K$1.50 /M in$9.00 /M out131K
9Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) anthropic78.8%82.4%3.1K$3.00 /M in$15.00 /M out1.0M ctx
10GPT-5.5 (medium) openai78.6%—1.8K$5.00 /M in$30.00 /M out400K
11Gemini 3.1 Pro Preview google77.6%89.9%4.4K$2.00 /M in$12.00 /M out131K
12Qwen3.7 Max alibaba76.8%86.3%3.9K$2.50 /M in$7.50 /M out—
13Gemini 3.5 Flash (medium) google75.8%—5.5K$1.50 /M in$9.00 /M out131K
14MiniMax-M3 minimax74.1%76.6%28.8K$0.30 /M in$1.20 /M out1.0M ctx
15GPT-5.3 Codex (xhigh) openai74.0%—4.2K$1.75 /M in$14.00 /M out400K
16DeepSeek V4 Pro (Reasoning, Max Effort) deepseek74.0%77.6%21.7K$0.43 /M in$0.87 /M out1.0M ctx
17Claude Opus 4.6 (Adaptive Reasoning, Max Effort) anthropic73.0%—1.6K$5.00 /M in$25.00 /M out1.0M ctx
18Kimi K2.6 kimi71.5%73.2%8.4K$0.95 /M in$4.00 /M out—
19Claude Opus 4.7 (Non-reasoning, High Effort) anthropic71.3%—1.5K$5.00 /M in$25.00 /M out1.0M ctx
20MiMo-V2.5-Pro xiaomi70.5%78.7%19.7K$0.43 /M in$0.87 /M out1.0M ctx
21GPT-5.2 (xhigh) openai70.5%—3.8K$1.75 /M in$14.00 /M out400K
22Kimi K2.7 Code kimi69.9%79.5%8.0K$0.95 /M in$4.00 /M out—
23GPT-5.5 (low) openai69.6%—1.4K$5.00 /M in$30.00 /M out400K
24DeepSeek V4 Pro (Reasoning, High Effort) deepseek68.1%—18.4K$0.43 /M in$0.87 /M out1.0M ctx
25Claude Opus 4.5 (Reasoning) anthropic68.1%—1.4K$5.00 /M in$25.00 /M out1.0M ctx
26DeepSeek V4 Flash (Reasoning, Max Effort) deepseek67.3%73.5%55.7K$0.14 /M in$0.28 /M out1.0M ctx
27MiMo-V2-Pro xiaomi67.3%—7.4K$1.00 /M in$3.00 /M out1.0M ctx
28GLM-5.1 (Reasoning) zai67.1%72.9%5.3K$1.40 /M in$4.40 /M out—
29MiMo-V2.5 xiaomi66.9%—55.2K$0.14 /M in$0.28 /M out1.0M ctx
30GPT-5.2 Codex (xhigh) openai66.9%—3.4K$1.75 /M in$14.00 /M out400K
31GPT-5.4 mini (xhigh) openai66.8%73.3%8.6K$0.75 /M in$4.50 /M out400K
32Qwen3.6 Max Preview alibaba66.8%—5.0K$1.30 /M in$7.80 /M out—
33Qwen3.6 Plus alibaba66.1%71.2%12.6K$0.50 /M in$3.00 /M out—
34Gemini 3 Pro Preview (high) google66.1%—3.2K$2.00 /M in$12.00 /M out131K
35GLM-5 (Reasoning) zai65.9%—7.1K$1.00 /M in$3.20 /M out—
36GPT-5.4 (low) openai65.3%—2.3K$2.63 /M in$15.75 /M out400K
37Qwen3.7 Plus alibaba65.1%73.1%17.5K$0.40 /M in$1.16 /M out—
38GPT-5.1 (high) openai64.9%—4.5K$1.25 /M in$10.00 /M out400K
39GPT-5.4 nano (xhigh) openai63.8%73.3%29.1K$0.20 /M in$1.25 /M out400K
40MiniMax-M2.7 minimax63.6%68.8%21.2K$0.30 /M in$1.20 /M out1.0M ctx
41Kimi K2.5 (Reasoning) kimi63.6%—10.4K$0.58 /M in$3.00 /M out—
42GPT-5.2 (medium) openai63.4%—3.1K$1.75 /M in$14.00 /M out400K
43Nemotron 3 Ultra 550B A55B (Reasoning) nvidia63.1%64.4%9.3K$0.68 /M in$2.67 /M out128K
44Gemini 3 Flash Preview (Reasoning) google63.1%—11.5K$0.50 /M in$3.00 /M out131K
45Claude Opus 4.6 (Non-reasoning, High Effort) anthropic63.1%—1.2K$5.00 /M in$25.00 /M out1.0M ctx
46Grok 4.3 (high) xai62.8%55.2%5.4K$1.25 /M in$2.50 /M out—
47DeepSeek V4 Flash (Reasoning, High Effort) deepseek62.4%—48.0K$0.14 /M in$0.28 /M out1.0M ctx
48Qwen3.6 27B (Reasoning) alibaba61.9%70.2%9.2K$0.60 /M in$3.60 /M out—
49Grok 4.20 0309 v2 (Reasoning) xai61.8%—3.1K$2.00 /M in$6.00 /M out—
50Grok 4.20 0309 (Reasoning) xai60.9%—3.1K$2.00 /M in$6.00 /M out—
51MiMo-V2-Omni-0327 xiaomi60.8%—13.9K$0.40 /M in$2.00 /M out1.0M ctx
52GPT-5 (high) openai60.3%—3.9K$1.25 /M in$10.00 /M out400K
53GPT-5 Codex (high) openai60.3%—3.9K$1.25 /M in$10.00 /M out400K
54Grok 4.3 (medium) xai60.1%—5.0K$1.25 /M in$2.50 /M out—
55Claude Sonnet 4.6 (Non-reasoning, High Effort) anthropic59.9%—1.8K$3.00 /M in$15.00 /M out1.0M ctx
56Grok 4.3 (low) xai59.1%—4.8K$1.25 /M in$2.50 /M out—
57KAT Coder Pro V2 kwaikat59.1%—18.3K$0.30 /M in$1.20 /M out—
58GLM-5.1 (Non-reasoning) zai59.1%—4.1K$1.40 /M in$4.40 /M out—
59Gemini 3.5 Flash (minimal) google58.3%—3.3K$1.50 /M in$9.00 /M out131K
60GPT-5.1 Codex (high) openai57.9%—3.6K$1.25 /M in$10.00 /M out400K
61Claude Opus 4.5 (Non-reasoning) anthropic57.9%—1.0K$5.00 /M in$25.00 /M out1.0M ctx
62Claude 4.5 Sonnet (Reasoning) anthropic57.9%—1.7K$3.00 /M in$15.00 /M out1.0M ctx
63Kimi K2.6 (Non-reasoning) kimi57.8%—5.5K$0.95 /M in$4.00 /M out—
64Claude Sonnet 4.6 (Non-reasoning, Low Effort) anthropic57.3%—1.6K$3.00 /M in$15.00 /M out1.0M ctx
65GLM-4.7 (Reasoning) zai56.4%—8.5K$0.60 /M in$2.20 /M out—
66Qwen3.5 27B (Reasoning) alibaba56.4%—14.2K$0.30 /M in$2.40 /M out—
67Qwen3.5 397B A17B (Reasoning) alibaba56.3%63.0%7.6K$0.60 /M in$3.60 /M out—
68GPT-5 (medium) openai56.3%—3.4K$1.25 /M in$10.00 /M out400K
69Claude 4.1 Opus (Reasoning) anthropic56.3%—318$15.00 /M in$75.00 /M out1.0M ctx
70MiniMax-M2.5 minimax56.3%—16.6K$0.30 /M in$1.20 /M out1.0M ctx
71Hy3-preview (Reasoning) tencent56.1%—41.1K$0.12 /M in$0.43 /M out262K
72GPT-5.5 Instant (May 2026) openai55.9%—905$5.00 /M in$30.00 /M out400K
73DeepSeek V3.2 (Reasoning) deepseek55.8%—18.3K$0.30 /M in$0.45 /M out1.0M ctx
74Grok 4 xai55.6%—847$5.50 /M in$27.50 /M out—
75MiMo-V2-Flash (Feb 2026) xiaomi55.4%—50.5K$0.10 /M in$0.30 /M out1.0M ctx
76Gemini 3 Pro Preview (low) google55.3%—2.2K$2.00 /M in$12.00 /M out131K
77GPT-5 mini (high) openai55.1%—16.2K$0.25 /M in$2.00 /M out400K
78GPT-5.5 (Non-reasoning) openai54.6%—862$5.00 /M in$30.00 /M out400K
79Kimi K2 Thinking kimi54.6%—7.8K$0.60 /M in$2.50 /M out—
80o3-pro openai54.3%—232$20.00 /M in$80.00 /M out200K
81GLM-5 (Non-reasoning) zai54.1%—4.8K$1.00 /M in$3.20 /M out—
82Qwen3.5 122B A10B (Reasoning) alibaba53.9%59.7%9.7K$0.40 /M in$3.20 /M out—
83Qwen3.5 397B A17B (Non-reasoning) alibaba53.4%—6.9K$0.60 /M in$3.60 /M out—
84Qwen3 Max Thinking alibaba52.9%—3.5K$1.20 /M in$6.00 /M out—
85Qwen3.6 35B A3B (Reasoning) alibaba52.8%54.8%16.2K$0.25 /M in$1.49 /M out—
86MiniMax-M2.1 minimax52.4%—14.4K$0.30 /M in$1.20 /M out1.0M ctx
87DeepSeek V4 Pro (Non-reasoning) deepseek52.1%—10.8K$0.43 /M in$0.87 /M out1.0M ctx
88GPT-5 (low) openai52.1%—2.9K$1.25 /M in$10.00 /M out400K
89MiMo-V2-Flash (Reasoning) xiaomi52.1%—44.6K$0.10 /M in$0.30 /M out1.0M ctx
90Claude 4 Opus (Reasoning) anthropic51.8%—269$15.00 /M in$75.00 /M out1.0M ctx
91GPT-5 mini (medium) openai51.6%—14.2K$0.25 /M in$2.00 /M out400K
92Claude 4 Sonnet (Reasoning) anthropic51.3%—1.3K$3.00 /M in$15.00 /M out1.0M ctx
93Qwen3.5 Omni Plus alibaba51.1%—7.6K$0.40 /M in$4.80 /M out—
94Ring-2.6-1T inclusionai51.1%55.9%11.5K$0.30 /M in$2.50 /M out262K
95GPT-5.1 Codex mini (high) openai51.1%—14.0K$0.25 /M in$2.00 /M out400K
96o3 openai50.8%—2.0K$2.00 /M in$8.00 /M out200K
97GPT-5.4 nano (medium) openai50.4%—18.2K$0.20 /M in$1.25 /M out400K
98Mistral Medium 3.5 mistral49.9%61.3%2.5K$1.50 /M in$7.50 /M out—
99GPT-5.4 mini (medium) openai49.7%—4.8K$0.75 /M in$4.50 /M out400K
100Step 3.7 Flash stepfun49.6%48.8%18.0K$0.20 /M in$1.15 /M out256K
101Claude 4.5 Haiku (Reasoning) anthropic49.4%57.4%3.7K$1.00 /M in$5.00 /M out1.0M ctx
102Kimi K2.5 (Non-reasoning) kimi49.1%—6.1K$0.60 /M in$3.00 /M out—
103Qwen3.6 27B (Non-reasoning) alibaba48.9%—5.8K$0.60 /M in$3.60 /M out—
104Claude 4.5 Sonnet (Non-reasoning) anthropic48.9%—1.2K$3.00 /M in$15.00 /M out1.0M ctx
105Qwen3.5 35B A3B (Reasoning) alibaba48.9%—12.8K$0.25 /M in$2.00 /M out—
106Qwen3.5 27B (Non-reasoning) alibaba48.9%—10.4K$0.30 /M in$2.60 /M out—
107DeepSeek V4 Flash (Non-reasoning) deepseek47.9%—28.3K$0.14 /M in$0.28 /M out1.0M ctx
108KAT-Coder-Pro V1 kwaikat47.2%—11.7K$0.30 /M in$1.20 /M out—
109MiniMax-M2 minimax47.2%—11.7K$0.30 /M in$1.20 /M out205K
110Claude 4.1 Opus (Non-reasoning) anthropic47.1%—223$15.00 /M in$75.00 /M out1.0M ctx
111Qwen3.5 122B A10B (Non-reasoning) alibaba46.9%—7.4K$0.40 /M in$3.20 /M out—
112MiMo-V2.5-Pro (Non-reasoning) xiaomi46.6%—4.0K$0.90 /M in$2.70 /M out1.0M ctx
113GPT-5.4 (Non-reasoning) openai46.2%—1.2K$2.63 /M in$15.75 /M out400K
114Gemini 3 Flash Preview (Non-reasoning) google45.7%—6.1K$0.50 /M in$3.00 /M out131K
115Grok 4 Fast (Reasoning) xai45.7%—17.6K$0.20 /M in$0.50 /M out—
116Gemini 2.5 Pro google45.1%—2.2K$1.25 /M in$10.00 /M out131K
117GLM-4.7 (Non-reasoning) zai44.4%—5.2K$0.60 /M in$2.20 /M out—
118DeepSeek V3.1 Terminus (Reasoning) deepseek43.9%—2.1K$1.64 /M in$2.75 /M out1.0M ctx
119Hy3-preview (Non-reasoning) tencent43.6%—24.8K$0.12 /M in$0.43 /M out262K
120Ling-2.6-1T inclusionai43.6%—8.4K$0.30 /M in$2.50 /M out262K
121Step 3.5 Flash 2603 stepfun43.4%—31.0K$0.10 /M in$0.30 /M out256K
122GPT-5.2 (Non-reasoning) openai43.4%—1.4K$1.75 /M in$14.00 /M out400K
123Gemma 4 26B A4B (Reasoning) google42.9%51.4%23.2K$0.13 /M in$0.40 /M out262K
124o4-mini (high) openai42.7%—2.6K$1.10 /M in$4.40 /M out200K
125Claude 4 Opus (Non-reasoning) anthropic42.6%—182$15.00 /M in$75.00 /M out1.0M ctx
126Claude 4 Sonnet (Non-reasoning) anthropic42.6%—910$3.00 /M in$15.00 /M out1.0M ctx
127Step 3.5 Flash stepfun42.6%—29.8K$0.10 /M in$0.30 /M out256K
128NVIDIA Nemotron 3 Super 120B A12B (Reasoning) nvidia42.4%49.3%10.1K$0.30 /M in$0.75 /M out128K
129DeepSeek V3.2 Exp (Reasoning) deepseek42.4%—11.5K$0.28 /M in$0.41 /M out1.0M ctx
130Mercury 2 inception42.2%—11.7K$0.25 /M in$0.75 /M out128K
131GLM-4.6 (Reasoning) zai41.9%—5.0K$0.55 /M in$2.20 /M out—
132Gemini 3.1 Flash-Lite google41.7%45.4%10.1K$0.25 /M in$1.50 /M out131K
133Qwen3.5 9B (Reasoning) alibaba41.7%37.5%30.8K$0.10 /M in$0.15 /M out—
134Qwen3 Max Thinking (Preview) alibaba41.7%—2.2K$1.20 /M in$6.00 /M out—
135Gemma 4 31B (Non-reasoning) google41.4%—20.3K$0.14 /M in$0.40 /M out262K
136Grok 4.3 (Non-reasoning) xai41.4%46.0%2.4K$1.25 /M in$2.50 /M out—
137DeepSeek V3.2 (Non-reasoning) deepseek41.2%—5.5K$0.50 /M in$1.60 /M out1.0M ctx
138Trinity Large Thinking arcee40.9%—11.3K$0.23 /M in$0.88 /M out—
139Qwen3.6 35B A3B (Non-reasoning) alibaba40.4%—6.3K$0.38 /M in$2.25 /M out—
140Qwen3 Max alibaba40.1%—1.5K$1.66 /M in$7.22 /M out—
141gpt-oss-120b (high) openai39.7%39.7%16.6K$0.15 /M in$0.60 /M out131K
142Claude 4.5 Haiku (Non-reasoning) anthropic39.6%—2.4K$1.00 /M in$5.00 /M out1.0M ctx
143Claude 3.7 Sonnet (Non-reasoning) anthropic39.2%—773$3.00 /M in$15.00 /M out1.0M ctx
144Kimi K2 0905 kimi39.2%—4.0K$0.60 /M in$2.50 /M out—
145Qwen3.5 35B A3B (Non-reasoning) alibaba39.1%—8.2K$0.25 /M in$2.00 /M out—
146o1 openai39.1%51.9%160$15.00 /M in$60.00 /M out200K
147MiMo-V2-Flash (Non-reasoning) xiaomi38.6%—24.5K$0.10 /M in$0.30 /M out1.0M ctx
148GLM-4.6 (Non-reasoning) zai38.4%—3.9K$0.60 /M in$2.20 /M out—
149GLM-4.7-Flash (Reasoning) zai38.2%—30.5K$0.07 /M in$0.40 /M out—
150Grok 3 mini Reasoning (high) xai37.6%—8.2K$0.30 /M in$0.50 /M out—
151Grok 4.20 0309 (Non-reasoning) xai37.6%—1.2K$2.00 /M in$6.00 /M out—
152Gemini 2.5 Pro Preview (May' 25) google37.2%—1.5K$1.25 /M in$10.00 /M out131K
153Qwen3 235B A22B 2507 (Reasoning) alibaba37.2%—5.1K$0.40 /M in$2.15 /M out—
154HyperNova 60B 2605 multiversecomputing36.9%—54.7K$0.04 /M in$0.14 /M out—
155Gemma 4 12B (Reasoning) google36.7%—22.2K$0.10 /M in$0.30 /M out262K
156Nova 2.0 Pro Preview (medium) aws36.4%44.4%1.4K$1.25 /M in$10.00 /M out—
157Grok 4.20 0309 v2 (Non-reasoning) xai36.4%—1.1K$2.00 /M in$6.00 /M out—
158DeepSeek V3.1 Terminus (Non-reasoning) deepseek35.7%—7.5K$0.27 /M in$1.00 /M out1.0M ctx
159DeepSeek V3.2 Exp (Non-reasoning) deepseek35.6%—8.1K$0.28 /M in$0.41 /M out1.0M ctx
160Qwen3 Coder Next alibaba35.4%—5.8K$0.35 /M in$1.20 /M out—
161DeepSeek V3.1 (Non-reasoning) deepseek35.1%—3.6K$0.56 /M in$1.67 /M out1.0M ctx
162Nova 2.0 Omni (medium) aws34.9%—5.4K$0.30 /M in$2.50 /M out—
163Mistral Small 4 (Reasoning) mistral34.7%—12.6K$0.15 /M in$0.60 /M out—
164DeepSeek V3.1 (Reasoning) deepseek34.6%—3.4K$0.59 /M in$1.69 /M out1.0M ctx
165Qwen3 VL 235B A22B (Reasoning) alibaba34.4%—1.9K$0.84 /M in$6.17 /M out—
166Nova 2.0 Lite (high) aws34.2%—5.2K$0.30 /M in$2.50 /M out—
167GPT-5.1 (Non-reasoning) openai34.1%—1.2K$1.25 /M in$10.00 /M out400K
168Gemma 4 26B A4B (Non-reasoning) google33.6%—14.2K$0.13 /M in$0.40 /M out262K
169Magistral Medium 1.2 mistral33.6%—948$2.00 /M in$5.00 /M out—
170Qwen3.5 4B (Reasoning) alibaba33.6%29.5%56.6K$0.03 /M in$0.15 /M out—
171Gemini 2.5 Flash (Reasoning) google33.6%—5.0K$0.30 /M in$2.50 /M out131K
172DeepSeek R1 0528 (May '25) deepseek33.6%—1.4K$1.35 /M in$4.20 /M out164K
173GPT-5 nano (high) openai33.2%—29.5K$0.05 /M in$0.40 /M out400K
174Qwen3 Next 80B A3B (Reasoning) alibaba33.1%—2.5K$0.50 /M in$6.00 /M out—
175Nova 2.0 Pro Preview (low) aws32.6%—1.1K$1.25 /M in$10.00 /M out—
176GLM-4.5 (Reasoning) zai32.6%—2.8K$0.60 /M in$2.20 /M out—
177GPT-4.1 openai32.4%—825$2.00 /M in$8.00 /M out400K
178Kimi K2 kimi32.4%—2.8K$0.58 /M in$2.40 /M out—
179Ling 2.6 Flash inclusionai32.2%—17.1K$0.10 /M in$0.30 /M out262K
180Qwen3 Max (Preview) alibaba32.1%—1.3K$1.20 /M in$6.00 /M out—
181Nova 2.0 Lite (medium) aws31.7%—4.4K$0.30 /M in$2.50 /M out—
182Qwen3.5 Omni Flash alibaba31.7%—13.5K$0.10 /M in$0.80 /M out—
183o3-mini openai31.7%—1.4K$1.10 /M in$4.40 /M out200K
184GPT-5 nano (medium) openai31.7%—26.9K$0.05 /M in$0.40 /M out400K
185o1-pro openai31.6%—10.4$150.00 /M in$600.00 /M out200K
186o3-mini (high) openai30.7%55.0%1.3K$1.10 /M in$4.40 /M out200K
187Grok 3 xai30.7%—355$4.00 /M in$20.00 /M out—
188Seed-OSS-36B-Instruct bytedance_seed30.6%—7.4K$0.21 /M in$0.57 /M out—
189Qwen3 235B A22B 2507 Instruct alibaba30.4%—7.2K$0.20 /M in$0.82 /M out—
190Qwen3 Coder 480B A35B Instruct alibaba30.1%—4.4K$0.30 /M in$1.80 /M out—
191Qwen3 VL 32B (Reasoning) alibaba29.9%—1.5K$0.70 /M in$8.40 /M out—
192Nova 2.0 Lite (low) aws29.7%—3.9K$0.30 /M in$2.50 /M out—
193gpt-oss-120b (low) openai29.5%—9.2K$0.15 /M in$0.60 /M out400K
194MiniMax M1 80k minimax29.5%—2.5K$0.55 /M in$2.20 /M out1.0M ctx
195GPT-5.4 nano (Non-Reasoning) openai29.4%—6.2K$0.20 /M in$1.25 /M out400K
196NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) nvidia29.2%—24.4K$0.06 /M in$0.22 /M out128K
197GPT-5 (minimal) openai28.7%—883$1.25 /M in$10.00 /M out400K
198o1-preview openai28.4%44.4%76.8$16.50 /M in$66.00 /M out200K
199GLM-4.6V (Reasoning) zai28.0%—4.3K$0.30 /M in$0.90 /M out—
200GPT-5.4 mini (Non-Reasoning) openai27.7%—1.5K$0.75 /M in$4.50 /M out400K
201Nova 2.0 Omni (low) aws27.7%—3.4K$0.30 /M in$2.50 /M out—
202Grok 4 Fast (Non-reasoning) xai27.5%—6.4K$0.20 /M in$0.50 /M out—
203GLM-4.5-Air zai27.5%—6.5K$0.17 /M in$0.98 /M out—
204Nova 2.0 Pro Preview (Non-reasoning) aws27.4%—803$1.25 /M in$10.00 /M out—
205GPT-4.1 mini openai27.2%—2.9K$0.40 /M in$1.60 /M out400K
206Mistral Large 3 mistral27.0%—2.4K$0.50 /M in$1.50 /M out—
207Qwen3.5 4B (Non-reasoning) alibaba26.7%26.5%35.8K$0.03 /M in$0.15 /M out—
208Qwen3 30B A3B 2507 (Reasoning) alibaba26.4%—3.5K$0.28 /M in$1.85 /M out—
209DeepSeek V3 0324 deepseek26.2%—1.0K$1.20 /M in$1.25 /M out1.0M ctx
210GLM-4.7-Flash (Non-reasoning) zai25.9%—14.0K$0.07 /M in$0.40 /M out—
211GPT-5 (ChatGPT) openai25.5%—699$1.25 /M in$10.00 /M out400K
212Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) google25.2%—10.0K$0.10 /M in$0.40 /M out131K
213gpt-oss-20B (high) openai24.9%27.1%19.5K$0.05 /M in$0.20 /M out131K
214Nemotron 3 Nano Omni 30B A3B Reasoning nvidia24.9%—13.0K$0.07 /M in$0.30 /M out128K
215Mistral Medium 3.1 mistral24.7%—2.3K$0.40 /M in$2.00 /M out—
216gpt-oss-20B (low) openai23.9%—15.4K$0.06 /M in$0.20 /M out400K
217Llama 4 Maverick meta23.9%21.3%2.8K$0.35 /M in$0.85 /M out—
218GPT-5 mini (minimal) openai23.9%—3.1K$0.25 /M in$2.00 /M out400K
219Qwen3 VL 235B A22B Instruct alibaba23.9%—2.7K$0.30 /M in$1.90 /M out—
220Gemini 2.5 Flash (Non-reasoning) google23.5%—2.4K$0.30 /M in$2.50 /M out131K
221Qwen3 Next 80B A3B Instruct alibaba22.9%—1.6K$0.50 /M in$2.00 /M out—
222Qwen3 Coder 30B A3B Instruct alibaba22.7%—4.2K$0.19 /M in$0.84 /M out—
223QwQ 32B alibaba22.4%—1.3K$0.66 /M in$1.00 /M out—
224Qwen3 235B A22B (Reasoning) alibaba22.4%—833$0.70 /M in$8.40 /M out—
225Qwen3 VL 30B A3B (Reasoning) alibaba22.2%—3.9K$0.20 /M in$0.75 /M out—
226Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) google21.9%—7.5K$0.10 /M in$0.40 /M out131K
227Nova Premier aws21.2%—271$2.50 /M in$12.50 /M out—
228DeepSeek R1 (Jan '25) deepseek21.0%—438$1.68 /M in$4.70 /M out1.0M ctx
229Mistral Medium 3 mistral20.9%—1.6K$0.40 /M in$2.00 /M out—
230Mistral Small 4 (Non-reasoning) mistral20.7%—4.5K$0.15 /M in$0.60 /M out—
231Llama Nemotron Super 49B v1.5 (Reasoning) nvidia20.7%—6.7K$0.10 /M in$0.40 /M out131K
232Claude 3.5 Haiku anthropic20.7%—807$0.80 /M in$4.00 /M out1.0M ctx
233Devstral Medium mistral20.7%—1.6K$0.40 /M in$2.00 /M out—
234Gemini 2.0 Flash (Feb '25) google20.5%—4.4K$0.15 /M in$0.60 /M out131K
235Magistral Small 1.2 mistral19.9%—1.3K$0.50 /M in$1.50 /M out—
236Sarvam 105B (high) sarvam19.9%—14.8K$0.04 /M in$0.17 /M out—
237Nova 2.0 Lite (Non-reasoning) aws19.7%—1.7K$0.30 /M in$2.50 /M out—
238Claude 3 Opus anthropic19.7%25.5%39.0$15.00 /M in$75.00 /M out1.0M ctx
239Gemini 2.5 Flash-Lite (Reasoning) google19.0%—5.7K$0.10 /M in$0.40 /M out131K
240GPT-4o (Nov '24) openai18.7%—220$2.50 /M in$10.00 /M out128K
241Qwen3 VL 32B Instruct alibaba18.5%—772$0.70 /M in$2.80 /M out—
242GLM-4.6V (Non-reasoning) zai18.4%—1.8K$0.30 /M in$0.90 /M out—
243Qwen3 235B A22B (Non-reasoning) alibaba18.2%—1.2K$0.45 /M in$1.80 /M out—
244Qwen3 VL 8B (Reasoning) alibaba17.7%—2.0K$0.18 /M in$2.10 /M out—
245Nova 2.0 Omni (Non-reasoning) aws17.5%—1.4K$0.30 /M in$2.50 /M out—
246Qwen3 32B (Reasoning) alibaba17.5%—2.6K$0.20 /M in$0.52 /M out—
247DeepSeek V3 (Dec '24) deepseek17.4%—1.3K$0.40 /M in$0.89 /M out1.0M ctx
248Qwen3.5 2B (Reasoning) alibaba17.0%25.8%21.8K$0.02 /M in$0.10 /M out—
249Qwen2.5 Max alibaba17.0%—285$1.60 /M in$6.40 /M out—
250Qwen3 14B (Reasoning) alibaba16.9%—1.5K$0.23 /M in$2.22 /M out—
251Llama 4 Scout meta16.7%10.7%2.6K$0.17 /M in$0.66 /M out—
252Ministral 3 14B mistral16.7%19.1%2.5K$0.20 /M in$0.20 /M out—
253Hermes 4 - Llama-3.1 70B (Reasoning) nous-research16.7%—3.5K$0.13 /M in$0.40 /M out—
254Qwen3 VL 30B A3B Instruct alibaba16.7%—2.3K$0.20 /M in$0.60 /M out—
255Claude 3.5 Sonnet (Oct '24) anthropic16.5%39.5%137$3.00 /M in$15.00 /M out1.0M ctx
256DeepSeek R1 Distill Llama 70B deepseek16.5%—689$0.70 /M in$1.05 /M out128K
257Ling-flash-2.0 inclusionai16.2%—2.9K$0.14 /M in$0.57 /M out262K
258Qwen3 Omni 30B A3B (Reasoning) alibaba16.0%—1.6K$0.25 /M in$0.97 /M out—
259GPT-4o (Aug '24) openai16.0%—162$2.50 /M in$10.00 /M out128K
260Qwen2.5 Instruct 72B alibaba16.0%—1.3K$0.36 /M in$0.40 /M out—
261Devstral Small (Jul '25) mistral15.5%—4.0K$0.10 /M in$0.30 /M out—
262Qwen3 30B A3B (Reasoning) alibaba15.5%—4.0K$0.09 /M in$0.45 /M out—
263Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) nvidia15.2%—633$0.60 /M in$1.80 /M out131K
264Mistral Large 2 (Nov '24) mistral15.2%—190$2.00 /M in$6.00 /M out—
265Mistral Small 3.2 mistral15.2%—4.4K$0.09 /M in$0.25 /M out—
266GLM-4.5V (Reasoning) zai15.2%—633$0.60 /M in$1.80 /M out—
267Qwen3 30B A3B 2507 Instruct alibaba15.2%—2.6K$0.15 /M in$0.40 /M out—
268NVIDIA Nemotron Nano 12B v2 VL (Reasoning) nvidia15.0%—1.9K$0.20 /M in$0.60 /M out128K
269Hermes 4 - Llama-3.1 405B (Reasoning) nous-research15.0%—371$1.00 /M in$3.00 /M out—
270ERNIE 4.5 300B A47B baidu15.0%—1.3K$0.28 /M in$1.10 /M out131K
271Ministral 3 8B mistral14.9%14.9%2.7K$0.15 /M in$0.15 /M out—
272NVIDIA Nemotron Nano 9B V2 (Reasoning) nvidia14.7%—8.5K$0.04 /M in$0.16 /M out128K
273Hermes 4 - Llama-3.1 405B (Non-reasoning) nous-research14.7%—355$1.00 /M in$3.00 /M out—
274Qwen3.5 2B (Non-reasoning) alibaba14.7%22.7%16.3K$0.02 /M in$0.10 /M out—
275Llama Nemotron Super 49B v1.5 (Non-reasoning) nvidia14.5%—3.3K$0.10 /M in$0.40 /M out131K
276Llama 3.3 Instruct 70B meta14.4%—636$0.58 /M in$0.71 /M out—
277GPT-4o (May '24) openai14.4%31.6%67.8$5.00 /M in$15.00 /M out128K
278Mistral Small 3.1 mistral14.4%—3.3K$0.10 /M in$0.23 /M out—
279Qwen3 32B (Non-reasoning) alibaba14.4%—2.2K$0.15 /M in$0.59 /M out—
280Llama 3.1 Instruct 405B meta14.2%—124$2.75 /M in$6.50 /M out—
281Qwen3 4B (Reasoning) alibaba14.0%—2.1K$0.11 /M in$1.26 /M out—
282Qwen3 VL 8B Instruct alibaba14.0%—1.7K$0.18 /M in$0.70 /M out—
283Claude 3.5 Sonnet (June '24) anthropic13.9%34.0%96.4$3.00 /M in$15.00 /M out1.0M ctx
284Ring-flash-2.0 inclusionai13.7%—2.1K$0.14 /M in$0.57 /M out262K
285Pixtral Large mistral13.5%—150$2.00 /M in$6.00 /M out—
286GPT-5 nano (minimal) openai13.4%—4.8K$0.05 /M in$0.40 /M out400K
287GPT-4 Turbo openai13.2%28.1%28.6$10.00 /M in$30.00 /M out128K
288Command A cohere12.9%—104$2.50 /M in$10.00 /M out256K
289Nova Pro aws12.9%—325$0.80 /M in$3.20 /M out—
290Llama 3.1 Nemotron Instruct 70B nvidia12.7%—243$1.20 /M in$1.20 /M out131K
291NVIDIA Nemotron Nano 9B V2 (Non-reasoning) nvidia12.4%—4.8K$0.05 /M in$0.20 /M out128K
292NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) nvidia12.4%—4.8K$0.05 /M in$0.20 /M out128K
293Qwen3 8B (Reasoning) alibaba12.4%—1.7K$0.11 /M in$1.15 /M out—
294GPT-4.1 nano openai12.2%—2.3K$0.10 /M in$0.40 /M out400K
295Mistral Large 2 (Jul '24) mistral12.2%—122$2.00 /M in$6.00 /M out—
296GPT-4 openai11.7%17.1%7.8$30.00 /M in$60.00 /M out8K
297GLM-4.5V (Non-reasoning) zai11.7%—374$0.60 /M in$1.80 /M out—
298Qwen3 14B (Non-reasoning) alibaba11.7%—935$0.23 /M in$0.82 /M out—
299Hermes 4 - Llama-3.1 70B (Non-reasoning) nous-research11.5%—1.7K$0.13 /M in$0.40 /M out—
300GPT-4o mini openai11.5%—1.4K$0.15 /M in$0.60 /M out128K
301Gemini 2.5 Flash-Lite (Non-reasoning) google11.5%—2.1K$0.10 /M in$0.40 /M out131K
302Mistral Small 3 mistral11.5%—3.0K$0.07 /M in$0.19 /M out—
303Nova Lite aws11.5%—3.5K$0.06 /M in$0.24 /M out—
304Llama 3.1 Instruct 70B meta11.4%—417$0.56 /M in$0.56 /M out—
305Qwen3 4B (Non-reasoning) alibaba11.4%—1.9K$0.11 /M in$0.42 /M out—
306Qwen3 30B A3B (Non-reasoning) alibaba11.4%—2.6K$0.08 /M in$0.29 /M out—
307Granite 4.1 8B ibm11.2%12.4%4.3K$0.05 /M in$0.10 /M out—
308Sarvam 30B (high) sarvam11.0%—7.3K$0.03 /M in$0.11 /M out—
309Reka Flash (Sep '24) reka-ai10.5%—870$0.20 /M in$0.80 /M out—
310Qwen2.5 Turbo alibaba10.5%—3.5K$0.05 /M in$0.20 /M out—
311Llama 3.2 Instruct 90B (Vision) meta10.4%—141$1.38 /M in$1.38 /M out—
312Solar Mini upstage10.4%—1.3K$0.15 /M in$0.15 /M out128K
313Llama 3.1 Instruct 8B meta10.2%—1.9K$0.10 /M in$0.10 /M out—
314Ministral 3 3B mistral9.3%6.3%1.6K$0.10 /M in$0.10 /M out—
315Jamba 1.7 Large ai21-labs8.8%—61.6$2.00 /M in$8.00 /M out—
316Granite 4.0 H Small ibm8.7%—2.0K$0.06 /M in$0.25 /M out—
317Qwen3 Omni 30B A3B Instruct alibaba8.5%—459$0.25 /M in$0.97 /M out—
318Hermes 3 - Llama-3.1 70B nous-research8.5%—438$0.30 /M in$0.30 /M out—
319Jamba 1.5 Large ai21-labs8.5%—57.0$2.00 /M in$8.00 /M out—
320Qwen3 8B (Non-reasoning) alibaba8.5%—725$0.18 /M in$0.20 /M out—
321Qwen3.5 0.8B (Reasoning) alibaba8.3%19.6%10.5K$0.01 /M in$0.05 /M out—
322Jamba 1.6 Large ai21-labs8.3%—54.8$2.00 /M in$8.00 /M out—
323Phi-4 azure8.2%—842$0.13 /M in$0.50 /M out—
324LFM2 24B A2B liquidai8.2%—3.5K$0.03 /M in$0.12 /M out—
325Gemma 3 27B Instruct google8.0%—993$0.11 /M in$0.25 /M out262K
326Nova Micro aws7.8%—2.8K$0.04 /M in$0.14 /M out—
327Claude 3 Sonnet anthropic7.8%—30.9$3.00 /M in$15.00 /M out1.0M ctx
328Mistral Small (Sep '24) mistral7.8%—506$0.20 /M in$0.60 /M out—
329NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) nvidia7.7%—485$0.20 /M in$0.60 /M out128K
330Qwen3.5 0.8B (Non-reasoning) alibaba7.3%28.6%8.1K$0.01 /M in$0.05 /M out—
331Mistral Large (Feb '24) mistral7.3%—22.2$4.00 /M in$12.00 /M out—
332Llama 2 Chat 7B meta7.2%—1.6K$0.05 /M in$0.25 /M out—
333Llama 3.2 Instruct 3B meta7.0%—594$0.15 /M in$0.15 /M out—
334Reka Flash 3 reka-ai6.8%—368$0.20 /M in$0.80 /M out—
335Claude 3 Haiku anthropic6.5%—256$0.25 /M in$1.25 /M out200K
336GPT-3.5 Turbo openai6.0%14.0%119$0.50 /M in$1.50 /M out400K
337Mistral Small (Feb '24) mistral6.0%—59.4$1.00 /M in$3.00 /M out—
338Mistral Medium mistral6.0%—21.7$2.75 /M in$8.10 /M out—
339Llama 3 Instruct 70B meta5.8%—81.8$0.65 /M in$2.75 /M out—
340Gemma 3 12B Instruct google5.7%—583$0.09 /M in$0.29 /M out262K
341Llama 3.2 Instruct 11B (Vision) meta5.5%—224$0.24 /M in$0.24 /M out—
342Command-R+ (Apr '24) cohere5.0%—12.6$3.00 /M in$15.00 /M out256K
343Olmo 3 7B Instruct ai24.7%—377$0.10 /M in$0.20 /M out—
344Jamba 1.5 Mini ai21-labs4.5%—175$0.20 /M in$0.40 /M out—
345Jamba 1.6 Mini ai21-labs4.3%—162$0.20 /M in$0.40 /M out—
346Qwen3 1.7B (Reasoning) alibaba4.3%—203$0.11 /M in$1.26 /M out—
347Apertus 70B Instruct swiss-ai-initiative4.0%—31.4$0.82 /M in$2.92 /M out—
348Mixtral 8x7B Instruct mistral4.0%—62.9$0.45 /M in$0.70 /M out—
349Mistral 7B Instruct mistral3.5%—111$0.20 /M in$0.23 /M out—
350Command-R (Mar '24) cohere3.5%—40.4$0.50 /M in$1.50 /M out256K
351Granite 3.3 8B (Non-reasoning) ibm3.0%—398$0.03 /M in$0.25 /M out—
352Qwen3 1.7B (Non-reasoning) alibaba2.5%—90.4$0.11 /M in$0.42 /M out—
353Qwen3 0.6B (Reasoning) alibaba2.2%—50.8$0.11 /M in$1.26 /M out—
354Llama 3 Instruct 8B meta2.0%—145$0.04 /M in$0.14 /M out—
355Gemma 3n E4B Instruct google2.0%—346$0.02 /M in$0.04 /M out262K
356Llama 3.2 Instruct 1B meta1.8%—122$0.05 /M in$0.05 /M out—
357Gemma 3 4B Instruct google1.8%—145$0.04 /M in$0.08 /M out262K
358Apertus 8B Instruct swiss-ai-initiative1.7%—48.1$0.10 /M in$0.20 /M out—
359Qwen3 0.6B (Non-reasoning) alibaba1.7%—40.2$0.11 /M in$0.42 /M out—
360Cogito v2.1 (Reasoning) deepcogito———$1.25 /M in$1.25 /M out128K
361GPT-5.4 Pro (xhigh) openai———$30.00 /M in$180.00 /M out400K
  1. 1
    Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) anthropic
    Intelligence
    100.0%
    Coding
    100.0%
    Value
    1.5K
    Input
    $10.00/M
    Output
    $50.00/M
    Context
    1.0M
  2. 2
    Claude Opus 4.8 (Adaptive Reasoning, Max Effort) anthropic
    Intelligence
    93.0%
    Coding
    97.1%
    Value
    2.6K
    Input
    $5.00/M
    Output
    $25.00/M
    Context
    1.0M
  3. 3
    GPT-5.5 (xhigh) openai
    Intelligence
    91.5%
    Coding
    97.9%
    Value
    2.4K
    Input
    $5.00/M
    Output
    $30.00/M
    Context
    400K
  4. 4
    Claude Opus 4.7 (Adaptive Reasoning, Max Effort) anthropic
    Intelligence
    89.3%
    Coding
    96.2%
    Value
    2.4K
    Input
    $5.00/M
    Output
    $25.00/M
    Context
    1.0M
  5. 5
    GPT-5.5 (high) openai
    Intelligence
    88.6%
    Coding
    93.6%
    Value
    2.3K
    Input
    $5.00/M
    Output
    $30.00/M
    Context
    400K
  6. 6
    GPT-5.4 (xhigh) openai
    Intelligence
    85.8%
    Coding
    92.9%
    Value
    4.3K
    Input
    $2.50/M
    Output
    $15.00/M
    Context
    400K
  7. 7
    GLM-5.2 (max) zai
    Intelligence
    85.3%
    Coding
    89.9%
    Value
    8.5K
    Input
    $1.40/M
    Output
    $4.40/M
    Context
    —
  8. 8
    Gemini 3.5 Flash (high) google
    Intelligence
    83.8%
    Coding
    91.6%
    Value
    6.8K
    Input
    $1.50/M
    Output
    $9.00/M
    Context
    131K
  9. 9
    Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) anthropic
    Intelligence
    78.8%
    Coding
    82.4%
    Value
    3.1K
    Input
    $3.00/M
    Output
    $15.00/M
    Context
    1.0M
  10. 10
    GPT-5.5 (medium) openai
    Intelligence
    78.6%
    Coding
    —
    Value
    1.8K
    Input
    $5.00/M
    Output
    $30.00/M
    Context
    400K
  11. 11
    Gemini 3.1 Pro Preview google
    Intelligence
    77.6%
    Coding
    89.9%
    Value
    4.4K
    Input
    $2.00/M
    Output
    $12.00/M
    Context
    131K
  12. 12
    Qwen3.7 Max alibaba
    Intelligence
    76.8%
    Coding
    86.3%
    Value
    3.9K
    Input
    $2.50/M
    Output
    $7.50/M
    Context
    —
  13. 13
    Gemini 3.5 Flash (medium) google
    Intelligence
    75.8%
    Coding
    —
    Value
    5.5K
    Input
    $1.50/M
    Output
    $9.00/M
    Context
    131K
  14. 14
    MiniMax-M3 minimax
    Intelligence
    74.1%
    Coding
    76.6%
    Value
    28.8K
    Input
    $0.30/M
    Output
    $1.20/M
    Context
    1.0M
  15. 15
    GPT-5.3 Codex (xhigh) openai
    Intelligence
    74.0%
    Coding
    —
    Value
    4.2K
    Input
    $1.75/M
    Output
    $14.00/M
    Context
    400K
  16. 16
    DeepSeek V4 Pro (Reasoning, Max Effort) deepseek
    Intelligence
    74.0%
    Coding
    77.6%
    Value
    21.7K
    Input
    $0.43/M
    Output
    $0.87/M
    Context
    1.0M
  17. 17
    Claude Opus 4.6 (Adaptive Reasoning, Max Effort) anthropic
    Intelligence
    73.0%
    Coding
    —
    Value
    1.6K
    Input
    $5.00/M
    Output
    $25.00/M
    Context
    1.0M
  18. 18
    Kimi K2.6 kimi
    Intelligence
    71.5%
    Coding
    73.2%
    Value
    8.4K
    Input
    $0.95/M
    Output
    $4.00/M
    Context
    —
  19. 19
    Claude Opus 4.7 (Non-reasoning, High Effort) anthropic
    Intelligence
    71.3%
    Coding
    —
    Value
    1.5K
    Input
    $5.00/M
    Output
    $25.00/M
    Context
    1.0M
  20. 20
    MiMo-V2.5-Pro xiaomi
    Intelligence
    70.5%
    Coding
    78.7%
    Value
    19.7K
    Input
    $0.43/M
    Output
    $0.87/M
    Context
    1.0M
  21. 21
    GPT-5.2 (xhigh) openai
    Intelligence
    70.5%
    Coding
    —
    Value
    3.8K
    Input
    $1.75/M
    Output
    $14.00/M
    Context
    400K
  22. 22
    Kimi K2.7 Code kimi
    Intelligence
    69.9%
    Coding
    79.5%
    Value
    8.0K
    Input
    $0.95/M
    Output
    $4.00/M
    Context
    —
  23. 23
    GPT-5.5 (low) openai
    Intelligence
    69.6%
    Coding
    —
    Value
    1.4K
    Input
    $5.00/M
    Output
    $30.00/M
    Context
    400K
  24. 24
    DeepSeek V4 Pro (Reasoning, High Effort) deepseek
    Intelligence
    68.1%
    Coding
    —
    Value
    18.4K
    Input
    $0.43/M
    Output
    $0.87/M
    Context
    1.0M
  25. 25
    Claude Opus 4.5 (Reasoning) anthropic
    Intelligence
    68.1%
    Coding
    —
    Value
    1.4K
    Input
    $5.00/M
    Output
    $25.00/M
    Context
    1.0M
  26. 26
    DeepSeek V4 Flash (Reasoning, Max Effort) deepseek
    Intelligence
    67.3%
    Coding
    73.5%
    Value
    55.7K
    Input
    $0.14/M
    Output
    $0.28/M
    Context
    1.0M
  27. 27
    MiMo-V2-Pro xiaomi
    Intelligence
    67.3%
    Coding
    —
    Value
    7.4K
    Input
    $1.00/M
    Output
    $3.00/M
    Context
    1.0M
  28. 28
    GLM-5.1 (Reasoning) zai
    Intelligence
    67.1%
    Coding
    72.9%
    Value
    5.3K
    Input
    $1.40/M
    Output
    $4.40/M
    Context
    —
  29. 29
    MiMo-V2.5 xiaomi
    Intelligence
    66.9%
    Coding
    —
    Value
    55.2K
    Input
    $0.14/M
    Output
    $0.28/M
    Context
    1.0M
  30. 30
    GPT-5.2 Codex (xhigh) openai
    Intelligence
    66.9%
    Coding
    —
    Value
    3.4K
    Input
    $1.75/M
    Output
    $14.00/M
    Context
    400K
  31. 31
    GPT-5.4 mini (xhigh) openai
    Intelligence
    66.8%
    Coding
    73.3%
    Value
    8.6K
    Input
    $0.75/M
    Output
    $4.50/M
    Context
    400K
  32. 32
    Qwen3.6 Max Preview alibaba
    Intelligence
    66.8%
    Coding
    —
    Value
    5.0K
    Input
    $1.30/M
    Output
    $7.80/M
    Context
    —
  33. 33
    Qwen3.6 Plus alibaba
    Intelligence
    66.1%
    Coding
    71.2%
    Value
    12.6K
    Input
    $0.50/M
    Output
    $3.00/M
    Context
    —
  34. 34
    Gemini 3 Pro Preview (high) google
    Intelligence
    66.1%
    Coding
    —
    Value
    3.2K
    Input
    $2.00/M
    Output
    $12.00/M
    Context
    131K
  35. 35
    GLM-5 (Reasoning) zai
    Intelligence
    65.9%
    Coding
    —
    Value
    7.1K
    Input
    $1.00/M
    Output
    $3.20/M
    Context
    —
  36. 36
    GPT-5.4 (low) openai
    Intelligence
    65.3%
    Coding
    —
    Value
    2.3K
    Input
    $2.63/M
    Output
    $15.75/M
    Context
    400K
  37. 37
    Qwen3.7 Plus alibaba
    Intelligence
    65.1%
    Coding
    73.1%
    Value
    17.5K
    Input
    $0.40/M
    Output
    $1.16/M
    Context
    —
  38. 38
    GPT-5.1 (high) openai
    Intelligence
    64.9%
    Coding
    —
    Value
    4.5K
    Input
    $1.25/M
    Output
    $10.00/M
    Context
    400K
  39. 39
    GPT-5.4 nano (xhigh) openai
    Intelligence
    63.8%
    Coding
    73.3%
    Value
    29.1K
    Input
    $0.20/M
    Output
    $1.25/M
    Context
    400K
  40. 40
    MiniMax-M2.7 minimax
    Intelligence
    63.6%
    Coding
    68.8%
    Value
    21.2K
    Input
    $0.30/M
    Output
    $1.20/M
    Context
    1.0M
  41. 41
    Kimi K2.5 (Reasoning) kimi
    Intelligence
    63.6%
    Coding
    —
    Value
    10.4K
    Input
    $0.58/M
    Output
    $3.00/M
    Context
    —
  42. 42
    GPT-5.2 (medium) openai
    Intelligence
    63.4%
    Coding
    —
    Value
    3.1K
    Input
    $1.75/M
    Output
    $14.00/M
    Context
    400K
  43. 43
    Nemotron 3 Ultra 550B A55B (Reasoning) nvidia
    Intelligence
    63.1%
    Coding
    64.4%
    Value
    9.3K
    Input
    $0.68/M
    Output
    $2.67/M
    Context
    128K
  44. 44
    Gemini 3 Flash Preview (Reasoning) google
    Intelligence
    63.1%
    Coding
    —
    Value
    11.5K
    Input
    $0.50/M
    Output
    $3.00/M
    Context
    131K
  45. 45
    Claude Opus 4.6 (Non-reasoning, High Effort) anthropic
    Intelligence
    63.1%
    Coding
    —
    Value
    1.2K
    Input
    $5.00/M
    Output
    $25.00/M
    Context
    1.0M
  46. 46
    Grok 4.3 (high) xai
    Intelligence
    62.8%
    Coding
    55.2%
    Value
    5.4K
    Input
    $1.25/M
    Output
    $2.50/M
    Context
    —
  47. 47
    DeepSeek V4 Flash (Reasoning, High Effort) deepseek
    Intelligence
    62.4%
    Coding
    —
    Value
    48.0K
    Input
    $0.14/M
    Output
    $0.28/M
    Context
    1.0M
  48. 48
    Qwen3.6 27B (Reasoning) alibaba
    Intelligence
    61.9%
    Coding
    70.2%
    Value
    9.2K
    Input
    $0.60/M
    Output
    $3.60/M
    Context
    —
  49. 49
    Grok 4.20 0309 v2 (Reasoning) xai
    Intelligence
    61.8%
    Coding
    —
    Value
    3.1K
    Input
    $2.00/M
    Output
    $6.00/M
    Context
    —
  50. 50
    Grok 4.20 0309 (Reasoning) xai
    Intelligence
    60.9%
    Coding
    —
    Value
    3.1K
    Input
    $2.00/M
    Output
    $6.00/M
    Context
    —
  51. 51
    MiMo-V2-Omni-0327 xiaomi
    Intelligence
    60.8%
    Coding
    —
    Value
    13.9K
    Input
    $0.40/M
    Output
    $2.00/M
    Context
    1.0M
  52. 52
    GPT-5 (high) openai
    Intelligence
    60.3%
    Coding
    —
    Value
    3.9K
    Input
    $1.25/M
    Output
    $10.00/M
    Context
    400K
  53. 53
    GPT-5 Codex (high) openai
    Intelligence
    60.3%
    Coding
    —
    Value
    3.9K
    Input
    $1.25/M
    Output
    $10.00/M
    Context
    400K
  54. 54
    Grok 4.3 (medium) xai
    Intelligence
    60.1%
    Coding
    —
    Value
    5.0K
    Input
    $1.25/M
    Output
    $2.50/M
    Context
    —
  55. 55
    Claude Sonnet 4.6 (Non-reasoning, High Effort) anthropic
    Intelligence
    59.9%
    Coding
    —
    Value
    1.8K
    Input
    $3.00/M
    Output
    $15.00/M
    Context
    1.0M
  56. 56
    Grok 4.3 (low) xai
    Intelligence
    59.1%
    Coding
    —
    Value
    4.8K
    Input
    $1.25/M
    Output
    $2.50/M
    Context
    —
  57. 57
    KAT Coder Pro V2 kwaikat
    Intelligence
    59.1%
    Coding
    —
    Value
    18.3K
    Input
    $0.30/M
    Output
    $1.20/M
    Context
    —
  58. 58
    GLM-5.1 (Non-reasoning) zai
    Intelligence
    59.1%
    Coding
    —
    Value
    4.1K
    Input
    $1.40/M
    Output
    $4.40/M
    Context
    —
  59. 59
    Gemini 3.5 Flash (minimal) google
    Intelligence
    58.3%
    Coding
    —
    Value
    3.3K
    Input
    $1.50/M
    Output
    $9.00/M
    Context
    131K
  60. 60
    GPT-5.1 Codex (high) openai
    Intelligence
    57.9%
    Coding
    —
    Value
    3.6K
    Input
    $1.25/M
    Output
    $10.00/M
    Context
    400K
  61. 61
    Claude Opus 4.5 (Non-reasoning) anthropic
    Intelligence
    57.9%
    Coding
    —
    Value
    1.0K
    Input
    $5.00/M
    Output
    $25.00/M
    Context
    1.0M
  62. 62
    Claude 4.5 Sonnet (Reasoning) anthropic
    Intelligence
    57.9%
    Coding
    —
    Value
    1.7K
    Input
    $3.00/M
    Output
    $15.00/M
    Context
    1.0M
  63. 63
    Kimi K2.6 (Non-reasoning) kimi
    Intelligence
    57.8%
    Coding
    —
    Value
    5.5K
    Input
    $0.95/M
    Output
    $4.00/M
    Context
    —
  64. 64
    Claude Sonnet 4.6 (Non-reasoning, Low Effort) anthropic
    Intelligence
    57.3%
    Coding
    —
    Value
    1.6K
    Input
    $3.00/M
    Output
    $15.00/M
    Context
    1.0M
  65. 65
    GLM-4.7 (Reasoning) zai
    Intelligence
    56.4%
    Coding
    —
    Value
    8.5K
    Input
    $0.60/M
    Output
    $2.20/M
    Context
    —
  66. 66
    Qwen3.5 27B (Reasoning) alibaba
    Intelligence
    56.4%
    Coding
    —
    Value
    14.2K
    Input
    $0.30/M
    Output
    $2.40/M
    Context
    —
  67. 67
    Qwen3.5 397B A17B (Reasoning) alibaba
    Intelligence
    56.3%
    Coding
    63.0%
    Value
    7.6K
    Input
    $0.60/M
    Output
    $3.60/M
    Context
    —
  68. 68
    GPT-5 (medium) openai
    Intelligence
    56.3%
    Coding
    —
    Value
    3.4K
    Input
    $1.25/M
    Output
    $10.00/M
    Context
    400K
  69. 69
    Claude 4.1 Opus (Reasoning) anthropic
    Intelligence
    56.3%
    Coding
    —
    Value
    318
    Input
    $15.00/M
    Output
    $75.00/M
    Context
    1.0M
  70. 70
    MiniMax-M2.5 minimax
    Intelligence
    56.3%
    Coding
    —
    Value
    16.6K
    Input
    $0.30/M
    Output
    $1.20/M
    Context
    1.0M
  71. 71
    Hy3-preview (Reasoning) tencent
    Intelligence
    56.1%
    Coding
    —
    Value
    41.1K
    Input
    $0.12/M
    Output
    $0.43/M
    Context
    262K
  72. 72
    GPT-5.5 Instant (May 2026) openai
    Intelligence
    55.9%
    Coding
    —
    Value
    905
    Input
    $5.00/M
    Output
    $30.00/M
    Context
    400K
  73. 73
    DeepSeek V3.2 (Reasoning) deepseek
    Intelligence
    55.8%
    Coding
    —
    Value
    18.3K
    Input
    $0.30/M
    Output
    $0.45/M
    Context
    1.0M
  74. 74
    Grok 4 xai
    Intelligence
    55.6%
    Coding
    —
    Value
    847
    Input
    $5.50/M
    Output
    $27.50/M
    Context
    —
  75. 75
    MiMo-V2-Flash (Feb 2026) xiaomi
    Intelligence
    55.4%
    Coding
    —
    Value
    50.5K
    Input
    $0.10/M
    Output
    $0.30/M
    Context
    1.0M
  76. 76
    Gemini 3 Pro Preview (low) google
    Intelligence
    55.3%
    Coding
    —
    Value
    2.2K
    Input
    $2.00/M
    Output
    $12.00/M
    Context
    131K
  77. 77
    GPT-5 mini (high) openai
    Intelligence
    55.1%
    Coding
    —
    Value
    16.2K
    Input
    $0.25/M
    Output
    $2.00/M
    Context
    400K
  78. 78
    GPT-5.5 (Non-reasoning) openai
    Intelligence
    54.6%
    Coding
    —
    Value
    862
    Input
    $5.00/M
    Output
    $30.00/M
    Context
    400K
  79. 79
    Kimi K2 Thinking kimi
    Intelligence
    54.6%
    Coding
    —
    Value
    7.8K
    Input
    $0.60/M
    Output
    $2.50/M
    Context
    —
  80. 80
    o3-pro openai
    Intelligence
    54.3%
    Coding
    —
    Value
    232
    Input
    $20.00/M
    Output
    $80.00/M
    Context
    200K
  81. 81
    GLM-5 (Non-reasoning) zai
    Intelligence
    54.1%
    Coding
    —
    Value
    4.8K
    Input
    $1.00/M
    Output
    $3.20/M
    Context
    —
  82. 82
    Qwen3.5 122B A10B (Reasoning) alibaba
    Intelligence
    53.9%
    Coding
    59.7%
    Value
    9.7K
    Input
    $0.40/M
    Output
    $3.20/M
    Context
    —
  83. 83
    Qwen3.5 397B A17B (Non-reasoning) alibaba
    Intelligence
    53.4%
    Coding
    —
    Value
    6.9K
    Input
    $0.60/M
    Output
    $3.60/M
    Context
    —
  84. 84
    Qwen3 Max Thinking alibaba
    Intelligence
    52.9%
    Coding
    —
    Value
    3.5K
    Input
    $1.20/M
    Output
    $6.00/M
    Context
    —
  85. 85
    Qwen3.6 35B A3B (Reasoning) alibaba
    Intelligence
    52.8%
    Coding
    54.8%
    Value
    16.2K
    Input
    $0.25/M
    Output
    $1.49/M
    Context
    —
  86. 86
    MiniMax-M2.1 minimax
    Intelligence
    52.4%
    Coding
    —
    Value
    14.4K
    Input
    $0.30/M
    Output
    $1.20/M
    Context
    1.0M
  87. 87
    DeepSeek V4 Pro (Non-reasoning) deepseek
    Intelligence
    52.1%
    Coding
    —
    Value
    10.8K
    Input
    $0.43/M
    Output
    $0.87/M
    Context
    1.0M
  88. 88
    GPT-5 (low) openai
    Intelligence
    52.1%
    Coding
    —
    Value
    2.9K
    Input
    $1.25/M
    Output
    $10.00/M
    Context
    400K
  89. 89
    MiMo-V2-Flash (Reasoning) xiaomi
    Intelligence
    52.1%
    Coding
    —
    Value
    44.6K
    Input
    $0.10/M
    Output
    $0.30/M
    Context
    1.0M
  90. 90
    Claude 4 Opus (Reasoning) anthropic
    Intelligence
    51.8%
    Coding
    —
    Value
    269
    Input
    $15.00/M
    Output
    $75.00/M
    Context
    1.0M
  91. 91
    GPT-5 mini (medium) openai
    Intelligence
    51.6%
    Coding
    —
    Value
    14.2K
    Input
    $0.25/M
    Output
    $2.00/M
    Context
    400K
  92. 92
    Claude 4 Sonnet (Reasoning) anthropic
    Intelligence
    51.3%
    Coding
    —
    Value
    1.3K
    Input
    $3.00/M
    Output
    $15.00/M
    Context
    1.0M
  93. 93
    Qwen3.5 Omni Plus alibaba
    Intelligence
    51.1%
    Coding
    —
    Value
    7.6K
    Input
    $0.40/M
    Output
    $4.80/M
    Context
    —
  94. 94
    Ring-2.6-1T inclusionai
    Intelligence
    51.1%
    Coding
    55.9%
    Value
    11.5K
    Input
    $0.30/M
    Output
    $2.50/M
    Context
    262K
  95. 95
    GPT-5.1 Codex mini (high) openai
    Intelligence
    51.1%
    Coding
    —
    Value
    14.0K
    Input
    $0.25/M
    Output
    $2.00/M
    Context
    400K
  96. 96
    o3 openai
    Intelligence
    50.8%
    Coding
    —
    Value
    2.0K
    Input
    $2.00/M
    Output
    $8.00/M
    Context
    200K
  97. 97
    GPT-5.4 nano (medium) openai
    Intelligence
    50.4%
    Coding
    —
    Value
    18.2K
    Input
    $0.20/M
    Output
    $1.25/M
    Context
    400K
  98. 98
    Mistral Medium 3.5 mistral
    Intelligence
    49.9%
    Coding
    61.3%
    Value
    2.5K
    Input
    $1.50/M
    Output
    $7.50/M
    Context
    —
  99. 99
    GPT-5.4 mini (medium) openai
    Intelligence
    49.7%
    Coding
    —
    Value
    4.8K
    Input
    $0.75/M
    Output
    $4.50/M
    Context
    400K
  100. 100
    Step 3.7 Flash stepfun
    Intelligence
    49.6%
    Coding
    48.8%
    Value
    18.0K
    Input
    $0.20/M
    Output
    $1.15/M
    Context
    256K
  101. 101
    Claude 4.5 Haiku (Reasoning) anthropic
    Intelligence
    49.4%
    Coding
    57.4%
    Value
    3.7K
    Input
    $1.00/M
    Output
    $5.00/M
    Context
    1.0M
  102. 102
    Kimi K2.5 (Non-reasoning) kimi
    Intelligence
    49.1%
    Coding
    —
    Value
    6.1K
    Input
    $0.60/M
    Output
    $3.00/M
    Context
    —
  103. 103
    Qwen3.6 27B (Non-reasoning) alibaba
    Intelligence
    48.9%
    Coding
    —
    Value
    5.8K
    Input
    $0.60/M
    Output
    $3.60/M
    Context
    —
  104. 104
    Claude 4.5 Sonnet (Non-reasoning) anthropic
    Intelligence
    48.9%
    Coding
    —
    Value
    1.2K
    Input
    $3.00/M
    Output
    $15.00/M
    Context
    1.0M
  105. 105
    Qwen3.5 35B A3B (Reasoning) alibaba
    Intelligence
    48.9%
    Coding
    —
    Value
    12.8K
    Input
    $0.25/M
    Output
    $2.00/M
    Context
    —
  106. 106
    Qwen3.5 27B (Non-reasoning) alibaba
    Intelligence
    48.9%
    Coding
    —
    Value
    10.4K
    Input
    $0.30/M
    Output
    $2.60/M
    Context
    —
  107. 107
    DeepSeek V4 Flash (Non-reasoning) deepseek
    Intelligence
    47.9%
    Coding
    —
    Value
    28.3K
    Input
    $0.14/M
    Output
    $0.28/M
    Context
    1.0M
  108. 108
    KAT-Coder-Pro V1 kwaikat
    Intelligence
    47.2%
    Coding
    —
    Value
    11.7K
    Input
    $0.30/M
    Output
    $1.20/M
    Context
    —
  109. 109
    MiniMax-M2 minimax
    Intelligence
    47.2%
    Coding
    —
    Value
    11.7K
    Input
    $0.30/M
    Output
    $1.20/M
    Context
    205K
  110. 110
    Claude 4.1 Opus (Non-reasoning) anthropic
    Intelligence
    47.1%
    Coding
    —
    Value
    223
    Input
    $15.00/M
    Output
    $75.00/M
    Context
    1.0M
  111. 111
    Qwen3.5 122B A10B (Non-reasoning) alibaba
    Intelligence
    46.9%
    Coding
    —
    Value
    7.4K
    Input
    $0.40/M
    Output
    $3.20/M
    Context
    —
  112. 112
    MiMo-V2.5-Pro (Non-reasoning) xiaomi
    Intelligence
    46.6%
    Coding
    —
    Value
    4.0K
    Input
    $0.90/M
    Output
    $2.70/M
    Context
    1.0M
  113. 113
    GPT-5.4 (Non-reasoning) openai
    Intelligence
    46.2%
    Coding
    —
    Value
    1.2K
    Input
    $2.63/M
    Output
    $15.75/M
    Context
    400K
  114. 114
    Gemini 3 Flash Preview (Non-reasoning) google
    Intelligence
    45.7%
    Coding
    —
    Value
    6.1K
    Input
    $0.50/M
    Output
    $3.00/M
    Context
    131K
  115. 115
    Grok 4 Fast (Reasoning) xai
    Intelligence
    45.7%
    Coding
    —
    Value
    17.6K
    Input
    $0.20/M
    Output
    $0.50/M
    Context
    —
  116. 116
    Gemini 2.5 Pro google
    Intelligence
    45.1%
    Coding
    —
    Value
    2.2K
    Input
    $1.25/M
    Output
    $10.00/M
    Context
    131K
  117. 117
    GLM-4.7 (Non-reasoning) zai
    Intelligence
    44.4%
    Coding
    —
    Value
    5.2K
    Input
    $0.60/M
    Output
    $2.20/M
    Context
    —
  118. 118
    DeepSeek V3.1 Terminus (Reasoning) deepseek
    Intelligence
    43.9%
    Coding
    —
    Value
    2.1K
    Input
    $1.64/M
    Output
    $2.75/M
    Context
    1.0M
  119. 119
    Hy3-preview (Non-reasoning) tencent
    Intelligence
    43.6%
    Coding
    —
    Value
    24.8K
    Input
    $0.12/M
    Output
    $0.43/M
    Context
    262K
  120. 120
    Ling-2.6-1T inclusionai
    Intelligence
    43.6%
    Coding
    —
    Value
    8.4K
    Input
    $0.30/M
    Output
    $2.50/M
    Context
    262K
  121. 121
    Step 3.5 Flash 2603 stepfun
    Intelligence
    43.4%
    Coding
    —
    Value
    31.0K
    Input
    $0.10/M
    Output
    $0.30/M
    Context
    256K
  122. 122
    GPT-5.2 (Non-reasoning) openai
    Intelligence
    43.4%
    Coding
    —
    Value
    1.4K
    Input
    $1.75/M
    Output
    $14.00/M
    Context
    400K
  123. 123
    Gemma 4 26B A4B (Reasoning) google
    Intelligence
    42.9%
    Coding
    51.4%
    Value
    23.2K
    Input
    $0.13/M
    Output
    $0.40/M
    Context
    262K
  124. 124
    o4-mini (high) openai
    Intelligence
    42.7%
    Coding
    —
    Value
    2.6K
    Input
    $1.10/M
    Output
    $4.40/M
    Context
    200K
  125. 125
    Claude 4 Opus (Non-reasoning) anthropic
    Intelligence
    42.6%
    Coding
    —
    Value
    182
    Input
    $15.00/M
    Output
    $75.00/M
    Context
    1.0M
  126. 126
    Claude 4 Sonnet (Non-reasoning) anthropic
    Intelligence
    42.6%
    Coding
    —
    Value
    910
    Input
    $3.00/M
    Output
    $15.00/M
    Context
    1.0M
  127. 127
    Step 3.5 Flash stepfun
    Intelligence
    42.6%
    Coding
    —
    Value
    29.8K
    Input
    $0.10/M
    Output
    $0.30/M
    Context
    256K
  128. 128
    NVIDIA Nemotron 3 Super 120B A12B (Reasoning) nvidia
    Intelligence
    42.4%
    Coding
    49.3%
    Value
    10.1K
    Input
    $0.30/M
    Output
    $0.75/M
    Context
    128K
  129. 129
    DeepSeek V3.2 Exp (Reasoning) deepseek
    Intelligence
    42.4%
    Coding
    —
    Value
    11.5K
    Input
    $0.28/M
    Output
    $0.41/M
    Context
    1.0M
  130. 130
    Mercury 2 inception
    Intelligence
    42.2%
    Coding
    —
    Value
    11.7K
    Input
    $0.25/M
    Output
    $0.75/M
    Context
    128K
  131. 131
    GLM-4.6 (Reasoning) zai
    Intelligence
    41.9%
    Coding
    —
    Value
    5.0K
    Input
    $0.55/M
    Output
    $2.20/M
    Context
    —
  132. 132
    Gemini 3.1 Flash-Lite google
    Intelligence
    41.7%
    Coding
    45.4%
    Value
    10.1K
    Input
    $0.25/M
    Output
    $1.50/M
    Context
    131K
  133. 133
    Qwen3.5 9B (Reasoning) alibaba
    Intelligence
    41.7%
    Coding
    37.5%
    Value
    30.8K
    Input
    $0.10/M
    Output
    $0.15/M
    Context
    —
  134. 134
    Qwen3 Max Thinking (Preview) alibaba
    Intelligence
    41.7%
    Coding
    —
    Value
    2.2K
    Input
    $1.20/M
    Output
    $6.00/M
    Context
    —
  135. 135
    Gemma 4 31B (Non-reasoning) google
    Intelligence
    41.4%
    Coding
    —
    Value
    20.3K
    Input
    $0.14/M
    Output
    $0.40/M
    Context
    262K
  136. 136
    Grok 4.3 (Non-reasoning) xai
    Intelligence
    41.4%
    Coding
    46.0%
    Value
    2.4K
    Input
    $1.25/M
    Output
    $2.50/M
    Context
    —
  137. 137
    DeepSeek V3.2 (Non-reasoning) deepseek
    Intelligence
    41.2%
    Coding
    —
    Value
    5.5K
    Input
    $0.50/M
    Output
    $1.60/M
    Context
    1.0M
  138. 138
    Trinity Large Thinking arcee
    Intelligence
    40.9%
    Coding
    —
    Value
    11.3K
    Input
    $0.23/M
    Output
    $0.88/M
    Context
    —
  139. 139
    Qwen3.6 35B A3B (Non-reasoning) alibaba
    Intelligence
    40.4%
    Coding
    —
    Value
    6.3K
    Input
    $0.38/M
    Output
    $2.25/M
    Context
    —
  140. 140
    Qwen3 Max alibaba
    Intelligence
    40.1%
    Coding
    —
    Value
    1.5K
    Input
    $1.66/M
    Output
    $7.22/M
    Context
    —
  141. 141
    gpt-oss-120b (high) openai
    Intelligence
    39.7%
    Coding
    39.7%
    Value
    16.6K
    Input
    $0.15/M
    Output
    $0.60/M
    Context
    131K
  142. 142
    Claude 4.5 Haiku (Non-reasoning) anthropic
    Intelligence
    39.6%
    Coding
    —
    Value
    2.4K
    Input
    $1.00/M
    Output
    $5.00/M
    Context
    1.0M
  143. 143
    Claude 3.7 Sonnet (Non-reasoning) anthropic
    Intelligence
    39.2%
    Coding
    —
    Value
    773
    Input
    $3.00/M
    Output
    $15.00/M
    Context
    1.0M
  144. 144
    Kimi K2 0905 kimi
    Intelligence
    39.2%
    Coding
    —
    Value
    4.0K
    Input
    $0.60/M
    Output
    $2.50/M
    Context
    —
  145. 145
    Qwen3.5 35B A3B (Non-reasoning) alibaba
    Intelligence
    39.1%
    Coding
    —
    Value
    8.2K
    Input
    $0.25/M
    Output
    $2.00/M
    Context
    —
  146. 146
    o1 openai
    Intelligence
    39.1%
    Coding
    51.9%
    Value
    160
    Input
    $15.00/M
    Output
    $60.00/M
    Context
    200K
  147. 147
    MiMo-V2-Flash (Non-reasoning) xiaomi
    Intelligence
    38.6%
    Coding
    —
    Value
    24.5K
    Input
    $0.10/M
    Output
    $0.30/M
    Context
    1.0M
  148. 148
    GLM-4.6 (Non-reasoning) zai
    Intelligence
    38.4%
    Coding
    —
    Value
    3.9K
    Input
    $0.60/M
    Output
    $2.20/M
    Context
    —
  149. 149
    GLM-4.7-Flash (Reasoning) zai
    Intelligence
    38.2%
    Coding
    —
    Value
    30.5K
    Input
    $0.07/M
    Output
    $0.40/M
    Context
    —
  150. 150
    Grok 3 mini Reasoning (high) xai
    Intelligence
    37.6%
    Coding
    —
    Value
    8.2K
    Input
    $0.30/M
    Output
    $0.50/M
    Context
    —
  151. 151
    Grok 4.20 0309 (Non-reasoning) xai
    Intelligence
    37.6%
    Coding
    —
    Value
    1.2K
    Input
    $2.00/M
    Output
    $6.00/M
    Context
    —
  152. 152
    Gemini 2.5 Pro Preview (May' 25) google
    Intelligence
    37.2%
    Coding
    —
    Value
    1.5K
    Input
    $1.25/M
    Output
    $10.00/M
    Context
    131K
  153. 153
    Qwen3 235B A22B 2507 (Reasoning) alibaba
    Intelligence
    37.2%
    Coding
    —
    Value
    5.1K
    Input
    $0.40/M
    Output
    $2.15/M
    Context
    —
  154. 154
    HyperNova 60B 2605 multiversecomputing
    Intelligence
    36.9%
    Coding
    —
    Value
    54.7K
    Input
    $0.04/M
    Output
    $0.14/M
    Context
    —
  155. 155
    Gemma 4 12B (Reasoning) google
    Intelligence
    36.7%
    Coding
    —
    Value
    22.2K
    Input
    $0.10/M
    Output
    $0.30/M
    Context
    262K
  156. 156
    Nova 2.0 Pro Preview (medium) aws
    Intelligence
    36.4%
    Coding
    44.4%
    Value
    1.4K
    Input
    $1.25/M
    Output
    $10.00/M
    Context
    —
  157. 157
    Grok 4.20 0309 v2 (Non-reasoning) xai
    Intelligence
    36.4%
    Coding
    —
    Value
    1.1K
    Input
    $2.00/M
    Output
    $6.00/M
    Context
    —
  158. 158
    DeepSeek V3.1 Terminus (Non-reasoning) deepseek
    Intelligence
    35.7%
    Coding
    —
    Value
    7.5K
    Input
    $0.27/M
    Output
    $1.00/M
    Context
    1.0M
  159. 159
    DeepSeek V3.2 Exp (Non-reasoning) deepseek
    Intelligence
    35.6%
    Coding
    —
    Value
    8.1K
    Input
    $0.28/M
    Output
    $0.41/M
    Context
    1.0M
  160. 160
    Qwen3 Coder Next alibaba
    Intelligence
    35.4%
    Coding
    —
    Value
    5.8K
    Input
    $0.35/M
    Output
    $1.20/M
    Context
    —
  161. 161
    DeepSeek V3.1 (Non-reasoning) deepseek
    Intelligence
    35.1%
    Coding
    —
    Value
    3.6K
    Input
    $0.56/M
    Output
    $1.67/M
    Context
    1.0M
  162. 162
    Nova 2.0 Omni (medium) aws
    Intelligence
    34.9%
    Coding
    —
    Value
    5.4K
    Input
    $0.30/M
    Output
    $2.50/M
    Context
    —
  163. 163
    Mistral Small 4 (Reasoning) mistral
    Intelligence
    34.7%
    Coding
    —
    Value
    12.6K
    Input
    $0.15/M
    Output
    $0.60/M
    Context
    —
  164. 164
    DeepSeek V3.1 (Reasoning) deepseek
    Intelligence
    34.6%
    Coding
    —
    Value
    3.4K
    Input
    $0.59/M
    Output
    $1.69/M
    Context
    1.0M
  165. 165
    Qwen3 VL 235B A22B (Reasoning) alibaba
    Intelligence
    34.4%
    Coding
    —
    Value
    1.9K
    Input
    $0.84/M
    Output
    $6.17/M
    Context
    —
  166. 166
    Nova 2.0 Lite (high) aws
    Intelligence
    34.2%
    Coding
    —
    Value
    5.2K
    Input
    $0.30/M
    Output
    $2.50/M
    Context
    —
  167. 167
    GPT-5.1 (Non-reasoning) openai
    Intelligence
    34.1%
    Coding
    —
    Value
    1.2K
    Input
    $1.25/M
    Output
    $10.00/M
    Context
    400K
  168. 168
    Gemma 4 26B A4B (Non-reasoning) google
    Intelligence
    33.6%
    Coding
    —
    Value
    14.2K
    Input
    $0.13/M
    Output
    $0.40/M
    Context
    262K
  169. 169
    Magistral Medium 1.2 mistral
    Intelligence
    33.6%
    Coding
    —
    Value
    948
    Input
    $2.00/M
    Output
    $5.00/M
    Context
    —
  170. 170
    Qwen3.5 4B (Reasoning) alibaba
    Intelligence
    33.6%
    Coding
    29.5%
    Value
    56.6K
    Input
    $0.03/M
    Output
    $0.15/M
    Context
    —
  171. 171
    Gemini 2.5 Flash (Reasoning) google
    Intelligence
    33.6%
    Coding
    —
    Value
    5.0K
    Input
    $0.30/M
    Output
    $2.50/M
    Context
    131K
  172. 172
    DeepSeek R1 0528 (May '25) deepseek
    Intelligence
    33.6%
    Coding
    —
    Value
    1.4K
    Input
    $1.35/M
    Output
    $4.20/M
    Context
    164K
  173. 173
    GPT-5 nano (high) openai
    Intelligence
    33.2%
    Coding
    —
    Value
    29.5K
    Input
    $0.05/M
    Output
    $0.40/M
    Context
    400K
  174. 174
    Qwen3 Next 80B A3B (Reasoning) alibaba
    Intelligence
    33.1%
    Coding
    —
    Value
    2.5K
    Input
    $0.50/M
    Output
    $6.00/M
    Context
    —
  175. 175
    Nova 2.0 Pro Preview (low) aws
    Intelligence
    32.6%
    Coding
    —
    Value
    1.1K
    Input
    $1.25/M
    Output
    $10.00/M
    Context
    —
  176. 176
    GLM-4.5 (Reasoning) zai
    Intelligence
    32.6%
    Coding
    —
    Value
    2.8K
    Input
    $0.60/M
    Output
    $2.20/M
    Context
    —
  177. 177
    GPT-4.1 openai
    Intelligence
    32.4%
    Coding
    —
    Value
    825
    Input
    $2.00/M
    Output
    $8.00/M
    Context
    400K
  178. 178
    Kimi K2 kimi
    Intelligence
    32.4%
    Coding
    —
    Value
    2.8K
    Input
    $0.58/M
    Output
    $2.40/M
    Context
    —
  179. 179
    Ling 2.6 Flash inclusionai
    Intelligence
    32.2%
    Coding
    —
    Value
    17.1K
    Input
    $0.10/M
    Output
    $0.30/M
    Context
    262K
  180. 180
    Qwen3 Max (Preview) alibaba
    Intelligence
    32.1%
    Coding
    —
    Value
    1.3K
    Input
    $1.20/M
    Output
    $6.00/M
    Context
    —
  181. 181
    Nova 2.0 Lite (medium) aws
    Intelligence
    31.7%
    Coding
    —
    Value
    4.4K
    Input
    $0.30/M
    Output
    $2.50/M
    Context
    —
  182. 182
    Qwen3.5 Omni Flash alibaba
    Intelligence
    31.7%
    Coding
    —
    Value
    13.5K
    Input
    $0.10/M
    Output
    $0.80/M
    Context
    —
  183. 183
    o3-mini openai
    Intelligence
    31.7%
    Coding
    —
    Value
    1.4K
    Input
    $1.10/M
    Output
    $4.40/M
    Context
    200K
  184. 184
    GPT-5 nano (medium) openai
    Intelligence
    31.7%
    Coding
    —
    Value
    26.9K
    Input
    $0.05/M
    Output
    $0.40/M
    Context
    400K
  185. 185
    o1-pro openai
    Intelligence
    31.6%
    Coding
    —
    Value
    10.4
    Input
    $150.00/M
    Output
    $600.00/M
    Context
    200K
  186. 186
    o3-mini (high) openai
    Intelligence
    30.7%
    Coding
    55.0%
    Value
    1.3K
    Input
    $1.10/M
    Output
    $4.40/M
    Context
    200K
  187. 187
    Grok 3 xai
    Intelligence
    30.7%
    Coding
    —
    Value
    355
    Input
    $4.00/M
    Output
    $20.00/M
    Context
    —
  188. 188
    Seed-OSS-36B-Instruct bytedance_seed
    Intelligence
    30.6%
    Coding
    —
    Value
    7.4K
    Input
    $0.21/M
    Output
    $0.57/M
    Context
    —
  189. 189
    Qwen3 235B A22B 2507 Instruct alibaba
    Intelligence
    30.4%
    Coding
    —
    Value
    7.2K
    Input
    $0.20/M
    Output
    $0.82/M
    Context
    —
  190. 190
    Qwen3 Coder 480B A35B Instruct alibaba
    Intelligence
    30.1%
    Coding
    —
    Value
    4.4K
    Input
    $0.30/M
    Output
    $1.80/M
    Context
    —
  191. 191
    Qwen3 VL 32B (Reasoning) alibaba
    Intelligence
    29.9%
    Coding
    —
    Value
    1.5K
    Input
    $0.70/M
    Output
    $8.40/M
    Context
    —
  192. 192
    Nova 2.0 Lite (low) aws
    Intelligence
    29.7%
    Coding
    —
    Value
    3.9K
    Input
    $0.30/M
    Output
    $2.50/M
    Context
    —
  193. 193
    gpt-oss-120b (low) openai
    Intelligence
    29.5%
    Coding
    —
    Value
    9.2K
    Input
    $0.15/M
    Output
    $0.60/M
    Context
    400K
  194. 194
    MiniMax M1 80k minimax
    Intelligence
    29.5%
    Coding
    —
    Value
    2.5K
    Input
    $0.55/M
    Output
    $2.20/M
    Context
    1.0M
  195. 195
    GPT-5.4 nano (Non-Reasoning) openai
    Intelligence
    29.4%
    Coding
    —
    Value
    6.2K
    Input
    $0.20/M
    Output
    $1.25/M
    Context
    400K
  196. 196
    NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) nvidia
    Intelligence
    29.2%
    Coding
    —
    Value
    24.4K
    Input
    $0.06/M
    Output
    $0.22/M
    Context
    128K
  197. 197
    GPT-5 (minimal) openai
    Intelligence
    28.7%
    Coding
    —
    Value
    883
    Input
    $1.25/M
    Output
    $10.00/M
    Context
    400K
  198. 198
    o1-preview openai
    Intelligence
    28.4%
    Coding
    44.4%
    Value
    76.8
    Input
    $16.50/M
    Output
    $66.00/M
    Context
    200K
  199. 199
    GLM-4.6V (Reasoning) zai
    Intelligence
    28.0%
    Coding
    —
    Value
    4.3K
    Input
    $0.30/M
    Output
    $0.90/M
    Context
    —
  200. 200
    GPT-5.4 mini (Non-Reasoning) openai
    Intelligence
    27.7%
    Coding
    —
    Value
    1.5K
    Input
    $0.75/M
    Output
    $4.50/M
    Context
    400K
  201. 201
    Nova 2.0 Omni (low) aws
    Intelligence
    27.7%
    Coding
    —
    Value
    3.4K
    Input
    $0.30/M
    Output
    $2.50/M
    Context
    —
  202. 202
    Grok 4 Fast (Non-reasoning) xai
    Intelligence
    27.5%
    Coding
    —
    Value
    6.4K
    Input
    $0.20/M
    Output
    $0.50/M
    Context
    —
  203. 203
    GLM-4.5-Air zai
    Intelligence
    27.5%
    Coding
    —
    Value
    6.5K
    Input
    $0.17/M
    Output
    $0.98/M
    Context
    —
  204. 204
    Nova 2.0 Pro Preview (Non-reasoning) aws
    Intelligence
    27.4%
    Coding
    —
    Value
    803
    Input
    $1.25/M
    Output
    $10.00/M
    Context
    —
  205. 205
    GPT-4.1 mini openai
    Intelligence
    27.2%
    Coding
    —
    Value
    2.9K
    Input
    $0.40/M
    Output
    $1.60/M
    Context
    400K
  206. 206
    Mistral Large 3 mistral
    Intelligence
    27.0%
    Coding
    —
    Value
    2.4K
    Input
    $0.50/M
    Output
    $1.50/M
    Context
    —
  207. 207
    Qwen3.5 4B (Non-reasoning) alibaba
    Intelligence
    26.7%
    Coding
    26.5%
    Value
    35.8K
    Input
    $0.03/M
    Output
    $0.15/M
    Context
    —
  208. 208
    Qwen3 30B A3B 2507 (Reasoning) alibaba
    Intelligence
    26.4%
    Coding
    —
    Value
    3.5K
    Input
    $0.28/M
    Output
    $1.85/M
    Context
    —
  209. 209
    DeepSeek V3 0324 deepseek
    Intelligence
    26.2%
    Coding
    —
    Value
    1.0K
    Input
    $1.20/M
    Output
    $1.25/M
    Context
    1.0M
  210. 210
    GLM-4.7-Flash (Non-reasoning) zai
    Intelligence
    25.9%
    Coding
    —
    Value
    14.0K
    Input
    $0.07/M
    Output
    $0.40/M
    Context
    —
  211. 211
    GPT-5 (ChatGPT) openai
    Intelligence
    25.5%
    Coding
    —
    Value
    699
    Input
    $1.25/M
    Output
    $10.00/M
    Context
    400K
  212. 212
    Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) google
    Intelligence
    25.2%
    Coding
    —
    Value
    10.0K
    Input
    $0.10/M
    Output
    $0.40/M
    Context
    131K
  213. 213
    gpt-oss-20B (high) openai
    Intelligence
    24.9%
    Coding
    27.1%
    Value
    19.5K
    Input
    $0.05/M
    Output
    $0.20/M
    Context
    131K
  214. 214
    Nemotron 3 Nano Omni 30B A3B Reasoning nvidia
    Intelligence
    24.9%
    Coding
    —
    Value
    13.0K
    Input
    $0.07/M
    Output
    $0.30/M
    Context
    128K
  215. 215
    Mistral Medium 3.1 mistral
    Intelligence
    24.7%
    Coding
    —
    Value
    2.3K
    Input
    $0.40/M
    Output
    $2.00/M
    Context
    —
  216. 216
    gpt-oss-20B (low) openai
    Intelligence
    23.9%
    Coding
    —
    Value
    15.4K
    Input
    $0.06/M
    Output
    $0.20/M
    Context
    400K
  217. 217
    Llama 4 Maverick meta
    Intelligence
    23.9%
    Coding
    21.3%
    Value
    2.8K
    Input
    $0.35/M
    Output
    $0.85/M
    Context
    —
  218. 218
    GPT-5 mini (minimal) openai
    Intelligence
    23.9%
    Coding
    —
    Value
    3.1K
    Input
    $0.25/M
    Output
    $2.00/M
    Context
    400K
  219. 219
    Qwen3 VL 235B A22B Instruct alibaba
    Intelligence
    23.9%
    Coding
    —
    Value
    2.7K
    Input
    $0.30/M
    Output
    $1.90/M
    Context
    —
  220. 220
    Gemini 2.5 Flash (Non-reasoning) google
    Intelligence
    23.5%
    Coding
    —
    Value
    2.4K
    Input
    $0.30/M
    Output
    $2.50/M
    Context
    131K
  221. 221
    Qwen3 Next 80B A3B Instruct alibaba
    Intelligence
    22.9%
    Coding
    —
    Value
    1.6K
    Input
    $0.50/M
    Output
    $2.00/M
    Context
    —
  222. 222
    Qwen3 Coder 30B A3B Instruct alibaba
    Intelligence
    22.7%
    Coding
    —
    Value
    4.2K
    Input
    $0.19/M
    Output
    $0.84/M
    Context
    —
  223. 223
    QwQ 32B alibaba
    Intelligence
    22.4%
    Coding
    —
    Value
    1.3K
    Input
    $0.66/M
    Output
    $1.00/M
    Context
    —
  224. 224
    Qwen3 235B A22B (Reasoning) alibaba
    Intelligence
    22.4%
    Coding
    —
    Value
    833
    Input
    $0.70/M
    Output
    $8.40/M
    Context
    —
  225. 225
    Qwen3 VL 30B A3B (Reasoning) alibaba
    Intelligence
    22.2%
    Coding
    —
    Value
    3.9K
    Input
    $0.20/M
    Output
    $0.75/M
    Context
    —
  226. 226
    Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) google
    Intelligence
    21.9%
    Coding
    —
    Value
    7.5K
    Input
    $0.10/M
    Output
    $0.40/M
    Context
    131K
  227. 227
    Nova Premier aws
    Intelligence
    21.2%
    Coding
    —
    Value
    271
    Input
    $2.50/M
    Output
    $12.50/M
    Context
    —
  228. 228
    DeepSeek R1 (Jan '25) deepseek
    Intelligence
    21.0%
    Coding
    —
    Value
    438
    Input
    $1.68/M
    Output
    $4.70/M
    Context
    1.0M
  229. 229
    Mistral Medium 3 mistral
    Intelligence
    20.9%
    Coding
    —
    Value
    1.6K
    Input
    $0.40/M
    Output
    $2.00/M
    Context
    —
  230. 230
    Mistral Small 4 (Non-reasoning) mistral
    Intelligence
    20.7%
    Coding
    —
    Value
    4.5K
    Input
    $0.15/M
    Output
    $0.60/M
    Context
    —
  231. 231
    Llama Nemotron Super 49B v1.5 (Reasoning) nvidia
    Intelligence
    20.7%
    Coding
    —
    Value
    6.7K
    Input
    $0.10/M
    Output
    $0.40/M
    Context
    131K
  232. 232
    Claude 3.5 Haiku anthropic
    Intelligence
    20.7%
    Coding
    —
    Value
    807
    Input
    $0.80/M
    Output
    $4.00/M
    Context
    1.0M
  233. 233
    Devstral Medium mistral
    Intelligence
    20.7%
    Coding
    —
    Value
    1.6K
    Input
    $0.40/M
    Output
    $2.00/M
    Context
    —
  234. 234
    Gemini 2.0 Flash (Feb '25) google
    Intelligence
    20.5%
    Coding
    —
    Value
    4.4K
    Input
    $0.15/M
    Output
    $0.60/M
    Context
    131K
  235. 235
    Magistral Small 1.2 mistral
    Intelligence
    19.9%
    Coding
    —
    Value
    1.3K
    Input
    $0.50/M
    Output
    $1.50/M
    Context
    —
  236. 236
    Sarvam 105B (high) sarvam
    Intelligence
    19.9%
    Coding
    —
    Value
    14.8K
    Input
    $0.04/M
    Output
    $0.17/M
    Context
    —
  237. 237
    Nova 2.0 Lite (Non-reasoning) aws
    Intelligence
    19.7%
    Coding
    —
    Value
    1.7K
    Input
    $0.30/M
    Output
    $2.50/M
    Context
    —
  238. 238
    Claude 3 Opus anthropic
    Intelligence
    19.7%
    Coding
    25.5%
    Value
    39.0
    Input
    $15.00/M
    Output
    $75.00/M
    Context
    1.0M
  239. 239
    Gemini 2.5 Flash-Lite (Reasoning) google
    Intelligence
    19.0%
    Coding
    —
    Value
    5.7K
    Input
    $0.10/M
    Output
    $0.40/M
    Context
    131K
  240. 240
    GPT-4o (Nov '24) openai
    Intelligence
    18.7%
    Coding
    —
    Value
    220
    Input
    $2.50/M
    Output
    $10.00/M
    Context
    128K
  241. 241
    Qwen3 VL 32B Instruct alibaba
    Intelligence
    18.5%
    Coding
    —
    Value
    772
    Input
    $0.70/M
    Output
    $2.80/M
    Context
    —
  242. 242
    GLM-4.6V (Non-reasoning) zai
    Intelligence
    18.4%
    Coding
    —
    Value
    1.8K
    Input
    $0.30/M
    Output
    $0.90/M
    Context
    —
  243. 243
    Qwen3 235B A22B (Non-reasoning) alibaba
    Intelligence
    18.2%
    Coding
    —
    Value
    1.2K
    Input
    $0.45/M
    Output
    $1.80/M
    Context
    —
  244. 244
    Qwen3 VL 8B (Reasoning) alibaba
    Intelligence
    17.7%
    Coding
    —
    Value
    2.0K
    Input
    $0.18/M
    Output
    $2.10/M
    Context
    —
  245. 245
    Nova 2.0 Omni (Non-reasoning) aws
    Intelligence
    17.5%
    Coding
    —
    Value
    1.4K
    Input
    $0.30/M
    Output
    $2.50/M
    Context
    —
  246. 246
    Qwen3 32B (Reasoning) alibaba
    Intelligence
    17.5%
    Coding
    —
    Value
    2.6K
    Input
    $0.20/M
    Output
    $0.52/M
    Context
    —
  247. 247
    DeepSeek V3 (Dec '24) deepseek
    Intelligence
    17.4%
    Coding
    —
    Value
    1.3K
    Input
    $0.40/M
    Output
    $0.89/M
    Context
    1.0M
  248. 248
    Qwen3.5 2B (Reasoning) alibaba
    Intelligence
    17.0%
    Coding
    25.8%
    Value
    21.8K
    Input
    $0.02/M
    Output
    $0.10/M
    Context
    —
  249. 249
    Qwen2.5 Max alibaba
    Intelligence
    17.0%
    Coding
    —
    Value
    285
    Input
    $1.60/M
    Output
    $6.40/M
    Context
    —
  250. 250
    Qwen3 14B (Reasoning) alibaba
    Intelligence
    16.9%
    Coding
    —
    Value
    1.5K
    Input
    $0.23/M
    Output
    $2.22/M
    Context
    —
  251. 251
    Llama 4 Scout meta
    Intelligence
    16.7%
    Coding
    10.7%
    Value
    2.6K
    Input
    $0.17/M
    Output
    $0.66/M
    Context
    —
  252. 252
    Ministral 3 14B mistral
    Intelligence
    16.7%
    Coding
    19.1%
    Value
    2.5K
    Input
    $0.20/M
    Output
    $0.20/M
    Context
    —
  253. 253
    Hermes 4 - Llama-3.1 70B (Reasoning) nous-research
    Intelligence
    16.7%
    Coding
    —
    Value
    3.5K
    Input
    $0.13/M
    Output
    $0.40/M
    Context
    —
  254. 254
    Qwen3 VL 30B A3B Instruct alibaba
    Intelligence
    16.7%
    Coding
    —
    Value
    2.3K
    Input
    $0.20/M
    Output
    $0.60/M
    Context
    —
  255. 255
    Claude 3.5 Sonnet (Oct '24) anthropic
    Intelligence
    16.5%
    Coding
    39.5%
    Value
    137
    Input
    $3.00/M
    Output
    $15.00/M
    Context
    1.0M
  256. 256
    DeepSeek R1 Distill Llama 70B deepseek
    Intelligence
    16.5%
    Coding
    —
    Value
    689
    Input
    $0.70/M
    Output
    $1.05/M
    Context
    128K
  257. 257
    Ling-flash-2.0 inclusionai
    Intelligence
    16.2%
    Coding
    —
    Value
    2.9K
    Input
    $0.14/M
    Output
    $0.57/M
    Context
    262K
  258. 258
    Qwen3 Omni 30B A3B (Reasoning) alibaba
    Intelligence
    16.0%
    Coding
    —
    Value
    1.6K
    Input
    $0.25/M
    Output
    $0.97/M
    Context
    —
  259. 259
    GPT-4o (Aug '24) openai
    Intelligence
    16.0%
    Coding
    —
    Value
    162
    Input
    $2.50/M
    Output
    $10.00/M
    Context
    128K
  260. 260
    Qwen2.5 Instruct 72B alibaba
    Intelligence
    16.0%
    Coding
    —
    Value
    1.3K
    Input
    $0.36/M
    Output
    $0.40/M
    Context
    —
  261. 261
    Devstral Small (Jul '25) mistral
    Intelligence
    15.5%
    Coding
    —
    Value
    4.0K
    Input
    $0.10/M
    Output
    $0.30/M
    Context
    —
  262. 262
    Qwen3 30B A3B (Reasoning) alibaba
    Intelligence
    15.5%
    Coding
    —
    Value
    4.0K
    Input
    $0.09/M
    Output
    $0.45/M
    Context
    —
  263. 263
    Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) nvidia
    Intelligence
    15.2%
    Coding
    —
    Value
    633
    Input
    $0.60/M
    Output
    $1.80/M
    Context
    131K
  264. 264
    Mistral Large 2 (Nov '24) mistral
    Intelligence
    15.2%
    Coding
    —
    Value
    190
    Input
    $2.00/M
    Output
    $6.00/M
    Context
    —
  265. 265
    Mistral Small 3.2 mistral
    Intelligence
    15.2%
    Coding
    —
    Value
    4.4K
    Input
    $0.09/M
    Output
    $0.25/M
    Context
    —
  266. 266
    GLM-4.5V (Reasoning) zai
    Intelligence
    15.2%
    Coding
    —
    Value
    633
    Input
    $0.60/M
    Output
    $1.80/M
    Context
    —
  267. 267
    Qwen3 30B A3B 2507 Instruct alibaba
    Intelligence
    15.2%
    Coding
    —
    Value
    2.6K
    Input
    $0.15/M
    Output
    $0.40/M
    Context
    —
  268. 268
    NVIDIA Nemotron Nano 12B v2 VL (Reasoning) nvidia
    Intelligence
    15.0%
    Coding
    —
    Value
    1.9K
    Input
    $0.20/M
    Output
    $0.60/M
    Context
    128K
  269. 269
    Hermes 4 - Llama-3.1 405B (Reasoning) nous-research
    Intelligence
    15.0%
    Coding
    —
    Value
    371
    Input
    $1.00/M
    Output
    $3.00/M
    Context
    —
  270. 270
    ERNIE 4.5 300B A47B baidu
    Intelligence
    15.0%
    Coding
    —
    Value
    1.3K
    Input
    $0.28/M
    Output
    $1.10/M
    Context
    131K
  271. 271
    Ministral 3 8B mistral
    Intelligence
    14.9%
    Coding
    14.9%
    Value
    2.7K
    Input
    $0.15/M
    Output
    $0.15/M
    Context
    —
  272. 272
    NVIDIA Nemotron Nano 9B V2 (Reasoning) nvidia
    Intelligence
    14.7%
    Coding
    —
    Value
    8.5K
    Input
    $0.04/M
    Output
    $0.16/M
    Context
    128K
  273. 273
    Hermes 4 - Llama-3.1 405B (Non-reasoning) nous-research
    Intelligence
    14.7%
    Coding
    —
    Value
    355
    Input
    $1.00/M
    Output
    $3.00/M
    Context
    —
  274. 274
    Qwen3.5 2B (Non-reasoning) alibaba
    Intelligence
    14.7%
    Coding
    22.7%
    Value
    16.3K
    Input
    $0.02/M
    Output
    $0.10/M
    Context
    —
  275. 275
    Llama Nemotron Super 49B v1.5 (Non-reasoning) nvidia
    Intelligence
    14.5%
    Coding
    —
    Value
    3.3K
    Input
    $0.10/M
    Output
    $0.40/M
    Context
    131K
  276. 276
    Llama 3.3 Instruct 70B meta
    Intelligence
    14.4%
    Coding
    —
    Value
    636
    Input
    $0.58/M
    Output
    $0.71/M
    Context
    —
  277. 277
    GPT-4o (May '24) openai
    Intelligence
    14.4%
    Coding
    31.6%
    Value
    67.8
    Input
    $5.00/M
    Output
    $15.00/M
    Context
    128K
  278. 278
    Mistral Small 3.1 mistral
    Intelligence
    14.4%
    Coding
    —
    Value
    3.3K
    Input
    $0.10/M
    Output
    $0.23/M
    Context
    —
  279. 279
    Qwen3 32B (Non-reasoning) alibaba
    Intelligence
    14.4%
    Coding
    —
    Value
    2.2K
    Input
    $0.15/M
    Output
    $0.59/M
    Context
    —
  280. 280
    Llama 3.1 Instruct 405B meta
    Intelligence
    14.2%
    Coding
    —
    Value
    124
    Input
    $2.75/M
    Output
    $6.50/M
    Context
    —
  281. 281
    Qwen3 4B (Reasoning) alibaba
    Intelligence
    14.0%
    Coding
    —
    Value
    2.1K
    Input
    $0.11/M
    Output
    $1.26/M
    Context
    —
  282. 282
    Qwen3 VL 8B Instruct alibaba
    Intelligence
    14.0%
    Coding
    —
    Value
    1.7K
    Input
    $0.18/M
    Output
    $0.70/M
    Context
    —
  283. 283
    Claude 3.5 Sonnet (June '24) anthropic
    Intelligence
    13.9%
    Coding
    34.0%
    Value
    96.4
    Input
    $3.00/M
    Output
    $15.00/M
    Context
    1.0M
  284. 284
    Ring-flash-2.0 inclusionai
    Intelligence
    13.7%
    Coding
    —
    Value
    2.1K
    Input
    $0.14/M
    Output
    $0.57/M
    Context
    262K
  285. 285
    Pixtral Large mistral
    Intelligence
    13.5%
    Coding
    —
    Value
    150
    Input
    $2.00/M
    Output
    $6.00/M
    Context
    —
  286. 286
    GPT-5 nano (minimal) openai
    Intelligence
    13.4%
    Coding
    —
    Value
    4.8K
    Input
    $0.05/M
    Output
    $0.40/M
    Context
    400K
  287. 287
    GPT-4 Turbo openai
    Intelligence
    13.2%
    Coding
    28.1%
    Value
    28.6
    Input
    $10.00/M
    Output
    $30.00/M
    Context
    128K
  288. 288
    Command A cohere
    Intelligence
    12.9%
    Coding
    —
    Value
    104
    Input
    $2.50/M
    Output
    $10.00/M
    Context
    256K
  289. 289
    Nova Pro aws
    Intelligence
    12.9%
    Coding
    —
    Value
    325
    Input
    $0.80/M
    Output
    $3.20/M
    Context
    —
  290. 290
    Llama 3.1 Nemotron Instruct 70B nvidia
    Intelligence
    12.7%
    Coding
    —
    Value
    243
    Input
    $1.20/M
    Output
    $1.20/M
    Context
    131K
  291. 291
    NVIDIA Nemotron Nano 9B V2 (Non-reasoning) nvidia
    Intelligence
    12.4%
    Coding
    —
    Value
    4.8K
    Input
    $0.05/M
    Output
    $0.20/M
    Context
    128K
  292. 292
    NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) nvidia
    Intelligence
    12.4%
    Coding
    —
    Value
    4.8K
    Input
    $0.05/M
    Output
    $0.20/M
    Context
    128K
  293. 293
    Qwen3 8B (Reasoning) alibaba
    Intelligence
    12.4%
    Coding
    —
    Value
    1.7K
    Input
    $0.11/M
    Output
    $1.15/M
    Context
    —
  294. 294
    GPT-4.1 nano openai
    Intelligence
    12.2%
    Coding
    —
    Value
    2.3K
    Input
    $0.10/M
    Output
    $0.40/M
    Context
    400K
  295. 295
    Mistral Large 2 (Jul '24) mistral
    Intelligence
    12.2%
    Coding
    —
    Value
    122
    Input
    $2.00/M
    Output
    $6.00/M
    Context
    —
  296. 296
    GPT-4 openai
    Intelligence
    11.7%
    Coding
    17.1%
    Value
    7.8
    Input
    $30.00/M
    Output
    $60.00/M
    Context
    8K
  297. 297
    GLM-4.5V (Non-reasoning) zai
    Intelligence
    11.7%
    Coding
    —
    Value
    374
    Input
    $0.60/M
    Output
    $1.80/M
    Context
    —
  298. 298
    Qwen3 14B (Non-reasoning) alibaba
    Intelligence
    11.7%
    Coding
    —
    Value
    935
    Input
    $0.23/M
    Output
    $0.82/M
    Context
    —
  299. 299
    Hermes 4 - Llama-3.1 70B (Non-reasoning) nous-research
    Intelligence
    11.5%
    Coding
    —
    Value
    1.7K
    Input
    $0.13/M
    Output
    $0.40/M
    Context
    —
  300. 300
    GPT-4o mini openai
    Intelligence
    11.5%
    Coding
    —
    Value
    1.4K
    Input
    $0.15/M
    Output
    $0.60/M
    Context
    128K
  301. 301
    Gemini 2.5 Flash-Lite (Non-reasoning) google
    Intelligence
    11.5%
    Coding
    —
    Value
    2.1K
    Input
    $0.10/M
    Output
    $0.40/M
    Context
    131K
  302. 302
    Mistral Small 3 mistral
    Intelligence
    11.5%
    Coding
    —
    Value
    3.0K
    Input
    $0.07/M
    Output
    $0.19/M
    Context
    —
  303. 303
    Nova Lite aws
    Intelligence
    11.5%
    Coding
    —
    Value
    3.5K
    Input
    $0.06/M
    Output
    $0.24/M
    Context
    —
  304. 304
    Llama 3.1 Instruct 70B meta
    Intelligence
    11.4%
    Coding
    —
    Value
    417
    Input
    $0.56/M
    Output
    $0.56/M
    Context
    —
  305. 305
    Qwen3 4B (Non-reasoning) alibaba
    Intelligence
    11.4%
    Coding
    —
    Value
    1.9K
    Input
    $0.11/M
    Output
    $0.42/M
    Context
    —
  306. 306
    Qwen3 30B A3B (Non-reasoning) alibaba
    Intelligence
    11.4%
    Coding
    —
    Value
    2.6K
    Input
    $0.08/M
    Output
    $0.29/M
    Context
    —
  307. 307
    Granite 4.1 8B ibm
    Intelligence
    11.2%
    Coding
    12.4%
    Value
    4.3K
    Input
    $0.05/M
    Output
    $0.10/M
    Context
    —
  308. 308
    Sarvam 30B (high) sarvam
    Intelligence
    11.0%
    Coding
    —
    Value
    7.3K
    Input
    $0.03/M
    Output
    $0.11/M
    Context
    —
  309. 309
    Reka Flash (Sep '24) reka-ai
    Intelligence
    10.5%
    Coding
    —
    Value
    870
    Input
    $0.20/M
    Output
    $0.80/M
    Context
    —
  310. 310
    Qwen2.5 Turbo alibaba
    Intelligence
    10.5%
    Coding
    —
    Value
    3.5K
    Input
    $0.05/M
    Output
    $0.20/M
    Context
    —
  311. 311
    Llama 3.2 Instruct 90B (Vision) meta
    Intelligence
    10.4%
    Coding
    —
    Value
    141
    Input
    $1.38/M
    Output
    $1.38/M
    Context
    —
  312. 312
    Solar Mini upstage
    Intelligence
    10.4%
    Coding
    —
    Value
    1.3K
    Input
    $0.15/M
    Output
    $0.15/M
    Context
    128K
  313. 313
    Llama 3.1 Instruct 8B meta
    Intelligence
    10.2%
    Coding
    —
    Value
    1.9K
    Input
    $0.10/M
    Output
    $0.10/M
    Context
    —
  314. 314
    Ministral 3 3B mistral
    Intelligence
    9.3%
    Coding
    6.3%
    Value
    1.6K
    Input
    $0.10/M
    Output
    $0.10/M
    Context
    —
  315. 315
    Jamba 1.7 Large ai21-labs
    Intelligence
    8.8%
    Coding
    —
    Value
    61.6
    Input
    $2.00/M
    Output
    $8.00/M
    Context
    —
  316. 316
    Granite 4.0 H Small ibm
    Intelligence
    8.7%
    Coding
    —
    Value
    2.0K
    Input
    $0.06/M
    Output
    $0.25/M
    Context
    —
  317. 317
    Qwen3 Omni 30B A3B Instruct alibaba
    Intelligence
    8.5%
    Coding
    —
    Value
    459
    Input
    $0.25/M
    Output
    $0.97/M
    Context
    —
  318. 318
    Hermes 3 - Llama-3.1 70B nous-research
    Intelligence
    8.5%
    Coding
    —
    Value
    438
    Input
    $0.30/M
    Output
    $0.30/M
    Context
    —
  319. 319
    Jamba 1.5 Large ai21-labs
    Intelligence
    8.5%
    Coding
    —
    Value
    57.0
    Input
    $2.00/M
    Output
    $8.00/M
    Context
    —
  320. 320
    Qwen3 8B (Non-reasoning) alibaba
    Intelligence
    8.5%
    Coding
    —
    Value
    725
    Input
    $0.18/M
    Output
    $0.20/M
    Context
    —
  321. 321
    Qwen3.5 0.8B (Reasoning) alibaba
    Intelligence
    8.3%
    Coding
    19.6%
    Value
    10.5K
    Input
    $0.01/M
    Output
    $0.05/M
    Context
    —
  322. 322
    Jamba 1.6 Large ai21-labs
    Intelligence
    8.3%
    Coding
    —
    Value
    54.8
    Input
    $2.00/M
    Output
    $8.00/M
    Context
    —
  323. 323
    Phi-4 azure
    Intelligence
    8.2%
    Coding
    —
    Value
    842
    Input
    $0.13/M
    Output
    $0.50/M
    Context
    —
  324. 324
    LFM2 24B A2B liquidai
    Intelligence
    8.2%
    Coding
    —
    Value
    3.5K
    Input
    $0.03/M
    Output
    $0.12/M
    Context
    —
  325. 325
    Gemma 3 27B Instruct google
    Intelligence
    8.0%
    Coding
    —
    Value
    993
    Input
    $0.11/M
    Output
    $0.25/M
    Context
    262K
  326. 326
    Nova Micro aws
    Intelligence
    7.8%
    Coding
    —
    Value
    2.8K
    Input
    $0.04/M
    Output
    $0.14/M
    Context
    —
  327. 327
    Claude 3 Sonnet anthropic
    Intelligence
    7.8%
    Coding
    —
    Value
    30.9
    Input
    $3.00/M
    Output
    $15.00/M
    Context
    1.0M
  328. 328
    Mistral Small (Sep '24) mistral
    Intelligence
    7.8%
    Coding
    —
    Value
    506
    Input
    $0.20/M
    Output
    $0.60/M
    Context
    —
  329. 329
    NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) nvidia
    Intelligence
    7.7%
    Coding
    —
    Value
    485
    Input
    $0.20/M
    Output
    $0.60/M
    Context
    128K
  330. 330
    Qwen3.5 0.8B (Non-reasoning) alibaba
    Intelligence
    7.3%
    Coding
    28.6%
    Value
    8.1K
    Input
    $0.01/M
    Output
    $0.05/M
    Context
    —
  331. 331
    Mistral Large (Feb '24) mistral
    Intelligence
    7.3%
    Coding
    —
    Value
    22.2
    Input
    $4.00/M
    Output
    $12.00/M
    Context
    —
  332. 332
    Llama 2 Chat 7B meta
    Intelligence
    7.2%
    Coding
    —
    Value
    1.6K
    Input
    $0.05/M
    Output
    $0.25/M
    Context
    —
  333. 333
    Llama 3.2 Instruct 3B meta
    Intelligence
    7.0%
    Coding
    —
    Value
    594
    Input
    $0.15/M
    Output
    $0.15/M
    Context
    —
  334. 334
    Reka Flash 3 reka-ai
    Intelligence
    6.8%
    Coding
    —
    Value
    368
    Input
    $0.20/M
    Output
    $0.80/M
    Context
    —
  335. 335
    Claude 3 Haiku anthropic
    Intelligence
    6.5%
    Coding
    —
    Value
    256
    Input
    $0.25/M
    Output
    $1.25/M
    Context
    200K
  336. 336
    GPT-3.5 Turbo openai
    Intelligence
    6.0%
    Coding
    14.0%
    Value
    119
    Input
    $0.50/M
    Output
    $1.50/M
    Context
    400K
  337. 337
    Mistral Small (Feb '24) mistral
    Intelligence
    6.0%
    Coding
    —
    Value
    59.4
    Input
    $1.00/M
    Output
    $3.00/M
    Context
    —
  338. 338
    Mistral Medium mistral
    Intelligence
    6.0%
    Coding
    —
    Value
    21.7
    Input
    $2.75/M
    Output
    $8.10/M
    Context
    —
  339. 339
    Llama 3 Instruct 70B meta
    Intelligence
    5.8%
    Coding
    —
    Value
    81.8
    Input
    $0.65/M
    Output
    $2.75/M
    Context
    —
  340. 340
    Gemma 3 12B Instruct google
    Intelligence
    5.7%
    Coding
    —
    Value
    583
    Input
    $0.09/M
    Output
    $0.29/M
    Context
    262K
  341. 341
    Llama 3.2 Instruct 11B (Vision) meta
    Intelligence
    5.5%
    Coding
    —
    Value
    224
    Input
    $0.24/M
    Output
    $0.24/M
    Context
    —
  342. 342
    Command-R+ (Apr '24) cohere
    Intelligence
    5.0%
    Coding
    —
    Value
    12.6
    Input
    $3.00/M
    Output
    $15.00/M
    Context
    256K
  343. 343
    Olmo 3 7B Instruct ai2
    Intelligence
    4.7%
    Coding
    —
    Value
    377
    Input
    $0.10/M
    Output
    $0.20/M
    Context
    —
  344. 344
    Jamba 1.5 Mini ai21-labs
    Intelligence
    4.5%
    Coding
    —
    Value
    175
    Input
    $0.20/M
    Output
    $0.40/M
    Context
    —
  345. 345
    Jamba 1.6 Mini ai21-labs
    Intelligence
    4.3%
    Coding
    —
    Value
    162
    Input
    $0.20/M
    Output
    $0.40/M
    Context
    —
  346. 346
    Qwen3 1.7B (Reasoning) alibaba
    Intelligence
    4.3%
    Coding
    —
    Value
    203
    Input
    $0.11/M
    Output
    $1.26/M
    Context
    —
  347. 347
    Apertus 70B Instruct swiss-ai-initiative
    Intelligence
    4.0%
    Coding
    —
    Value
    31.4
    Input
    $0.82/M
    Output
    $2.92/M
    Context
    —
  348. 348
    Mixtral 8x7B Instruct mistral
    Intelligence
    4.0%
    Coding
    —
    Value
    62.9
    Input
    $0.45/M
    Output
    $0.70/M
    Context
    —
  349. 349
    Mistral 7B Instruct mistral
    Intelligence
    3.5%
    Coding
    —
    Value
    111
    Input
    $0.20/M
    Output
    $0.23/M
    Context
    —
  350. 350
    Command-R (Mar '24) cohere
    Intelligence
    3.5%
    Coding
    —
    Value
    40.4
    Input
    $0.50/M
    Output
    $1.50/M
    Context
    256K
  351. 351
    Granite 3.3 8B (Non-reasoning) ibm
    Intelligence
    3.0%
    Coding
    —
    Value
    398
    Input
    $0.03/M
    Output
    $0.25/M
    Context
    —
  352. 352
    Qwen3 1.7B (Non-reasoning) alibaba
    Intelligence
    2.5%
    Coding
    —
    Value
    90.4
    Input
    $0.11/M
    Output
    $0.42/M
    Context
    —
  353. 353
    Qwen3 0.6B (Reasoning) alibaba
    Intelligence
    2.2%
    Coding
    —
    Value
    50.8
    Input
    $0.11/M
    Output
    $1.26/M
    Context
    —
  354. 354
    Llama 3 Instruct 8B meta
    Intelligence
    2.0%
    Coding
    —
    Value
    145
    Input
    $0.04/M
    Output
    $0.14/M
    Context
    —
  355. 355
    Gemma 3n E4B Instruct google
    Intelligence
    2.0%
    Coding
    —
    Value
    346
    Input
    $0.02/M
    Output
    $0.04/M
    Context
    262K
  356. 356
    Llama 3.2 Instruct 1B meta
    Intelligence
    1.8%
    Coding
    —
    Value
    122
    Input
    $0.05/M
    Output
    $0.05/M
    Context
    —
  357. 357
    Gemma 3 4B Instruct google
    Intelligence
    1.8%
    Coding
    —
    Value
    145
    Input
    $0.04/M
    Output
    $0.08/M
    Context
    262K
  358. 358
    Apertus 8B Instruct swiss-ai-initiative
    Intelligence
    1.7%
    Coding
    —
    Value
    48.1
    Input
    $0.10/M
    Output
    $0.20/M
    Context
    —
  359. 359
    Qwen3 0.6B (Non-reasoning) alibaba
    Intelligence
    1.7%
    Coding
    —
    Value
    40.2
    Input
    $0.11/M
    Output
    $0.42/M
    Context
    —
  360. 360
    Cogito v2.1 (Reasoning) deepcogito
    Intelligence
    —
    Coding
    —
    Value
    —
    Input
    $1.25/M
    Output
    $1.25/M
    Context
    128K
  361. 361
    GPT-5.4 Pro (xhigh) openai
    Intelligence
    —
    Coding
    —
    Value
    —
    Input
    $30.00/M
    Output
    $180.00/M
    Context
    400K