Skip to main content

AI Hub Rankings

Every major AI, ranked honestly: real prices, quality scores, and promo codes that actually work. Compare 380 paid models side by side.

Value score

Live-recomputes the Value column from your workload.

#Model
1Claude Opus 5 (Adaptive Reasoning, Max Effort) anthropic100.0%99.6%3.1K$5.00 /M in$25.00 /M out1.0M ctx
2Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) anthropic99.0%98.3%3.0K$5.00 /M in$25.00 /M out1.0M ctx
3Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) anthropic98.7%97.7%1.5K$10.00 /M in$50.00 /M out1.0M ctx
4GPT-5.6 Sol (max) openai97.0%98.9%2.8K$5.00 /M in$30.00 /M out1.1M ctx
5Claude Opus 5 (Adaptive Reasoning, High Effort) anthropic97.0%97.7%2.9K$5.00 /M in$25.00 /M out1.0M ctx
6GPT-5.6 Sol (xhigh) openai95.1%100.0%2.7K$5.00 /M in$30.00 /M out1.1M ctx
7Kimi K3 (max) kimi94.1%97.3%4.6K$3.00 /M in$15.00 /M out—
8Claude Opus 5 (Adaptive Reasoning, Medium Effort) anthropic92.8%94.9%2.7K$5.00 /M in$25.00 /M out1.0M ctx
9GPT-5.6 Sol (high) openai92.1%98.6%2.5K$5.00 /M in$30.00 /M out1.1M ctx
10Claude Opus 4.8 (Adaptive Reasoning, Max Effort) anthropic91.8%94.9%2.6K$5.00 /M in$25.00 /M out1.0M ctx
11GPT-5.6 Terra (max) openai90.6%98.0%6.1K$2.00 /M in$12.00 /M out1.1M ctx
12GPT-5.5 (xhigh) openai90.3%95.7%2.4K$5.00 /M in$30.00 /M out1.1M ctx
13Grok 4.5 (high) xai88.6%92.5%6.6K$2.00 /M in$6.00 /M out—
14GPT-5.6 Sol (medium) openai88.3%97.4%2.3K$5.00 /M in$30.00 /M out1.1M ctx
15Claude Opus 4.7 (Adaptive Reasoning, Max Effort) anthropic88.1%94.0%2.4K$5.00 /M in$25.00 /M out1.0M ctx
16Claude Sonnet 5 (Adaptive Reasoning, Max Effort) anthropic88.0%91.3%6.0K$2.00 /M in$10.00 /M out1.0M ctx
17Qwen3.8 Max alibaba88.0%88.0%6.5K$2.00 /M in$6.00 /M out—
18GPT-5.5 (high) openai87.5%91.4%2.3K$5.00 /M in$30.00 /M out1.1M ctx
19GPT-5.6 Terra (xhigh) openai85.0%90.2%5.4K$2.00 /M in$12.00 /M out1.1M ctx
20GPT-5.4 (xhigh) openai84.7%90.8%4.3K$2.50 /M in$15.00 /M out1.1M ctx
21GPT-5.6 Luna (max) openai84.3%91.2%52.8K$0.20 /M in$1.20 /M out1.1M ctx
22GLM-5.2 (max) zai84.2%87.9%8.5K$1.40 /M in$4.40 /M out—
23Muse Spark 1.1 (xhigh) meta83.4%91.1%9.2K$1.25 /M in$4.25 /M out1.0M ctx
24Claude Opus 5 (Adaptive Reasoning, Low Effort) anthropic83.4%85.4%2.2K$5.00 /M in$25.00 /M out1.0M ctx
25GPT-5.5 (medium) openai83.0%91.3%2.0K$5.00 /M in$30.00 /M out1.1M ctx
26Gemini 3.5 Flash (high) google82.7%89.5%6.8K$1.50 /M in$9.00 /M out1.0M ctx
27Gemini 3.6 Flash (high) google82.5%88.4%7.0K$1.50 /M in$7.50 /M out1.0M ctx
28DeepSeek V4 Flash 0731 (Reasoning, Max Effort) deepseek82.2%88.3%85.5K$0.14 /M in$0.28 /M out1.0M ctx
29GPT-5.6 Sol (low) openai81.4%89.0%2.0K$5.00 /M in$30.00 /M out1.1M ctx
30GPT-5.6 Luna (xhigh) openai80.9%87.6%48.6K$0.20 /M in$1.20 /M out1.1M ctx
31GPT-5.6 Terra (high) openai80.7%85.7%4.8K$2.00 /M in$12.00 /M out1.1M ctx
32Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) anthropic77.8%80.5%3.1K$3.00 /M in$15.00 /M out1.0M ctx
33Kimi K3 (low) kimi76.8%92.0%3.0K$3.00 /M in$15.00 /M out—
34Gemini 3.1 Pro Preview google76.6%87.9%4.4K$2.00 /M in$12.00 /M out1.0M ctx
35GPT-5.6 Luna (high) openai75.9%80.8%42.8K$0.20 /M in$1.20 /M out1.1M ctx
36Qwen3.7 Max alibaba75.8%84.3%3.9K$2.50 /M in$7.50 /M out—
37GPT-5.6 Terra (medium) openai75.1%82.6%4.2K$2.00 /M in$12.00 /M out1.1M ctx
38Gemini 3.5 Flash (medium) google74.8%—5.5K$1.50 /M in$9.00 /M out1.0M ctx
39MiniMax-M3 minimax73.1%74.8%28.8K$0.30 /M in$1.20 /M out1.0M ctx
40GPT-5.3 Codex (xhigh) openai73.0%—4.2K$1.75 /M in$14.00 /M out1.1M ctx
41DeepSeek V4 Pro (Reasoning, Max Effort) deepseek73.0%75.9%21.7K$0.43 /M in$0.87 /M out1.0M ctx
42Kimi K2.6 kimi72.8%78.9%8.9K$0.95 /M in$4.00 /M out—
43Claude Opus 4.6 (Adaptive Reasoning, Max Effort) anthropic72.0%—1.6K$5.00 /M in$25.00 /M out1.0M ctx
44GPT-5.5 (low) openai71.7%77.8%1.5K$5.00 /M in$30.00 /M out1.1M ctx
45DeepSeek V4 Pro (Reasoning, High Effort) deepseek71.0%75.0%20.5K$0.43 /M in$0.87 /M out1.0M ctx
46Claude Opus 4.7 (Non-reasoning, High Effort) anthropic70.3%—1.5K$5.00 /M in$25.00 /M out1.0M ctx
47MiMo-V2.5-Pro xiaomi69.5%76.9%19.7K$0.43 /M in$0.87 /M out1.1M ctx
48GPT-5.2 (xhigh) openai69.5%—3.8K$1.75 /M in$14.00 /M out1.1M ctx
49Kimi K2.7 Code kimi69.0%77.7%8.0K$0.95 /M in$4.00 /M out—
50Claude Sonnet 5 (Non-reasoning, High Effort) anthropic68.7%84.8%3.7K$2.00 /M in$10.00 /M out1.0M ctx
51GPT-5.6 Sol (Non-reasoning) openai67.9%83.1%1.4K$5.00 /M in$30.00 /M out1.1M ctx
52Hy3 tencent67.9%75.1%54.5K$0.14 /M in$0.56 /M out262K
53Nex-N2-Pro nex67.5%75.5%14.1K$0.50 /M in$2.50 /M out—
54Claude Opus 4.5 (Reasoning) anthropic67.2%—1.4K$5.00 /M in$25.00 /M out1.0M ctx
55Inkling (xhigh) thinking-machines67.1%66.5%4.2K$1.87 /M in$4.68 /M out—
56GPT-5.6 Terra (low) openai66.7%74.2%3.3K$2.00 /M in$12.00 /M out1.1M ctx
57DeepSeek V4 Flash (Reasoning, Max Effort) deepseek66.4%71.8%57.6K$0.14 /M in$0.28 /M out1.0M ctx
58Inkling Small thinking-machines66.2%67.6%23.6K$0.30 /M in$1.20 /M out—
59GLM-5.1 (Reasoning) zai66.2%71.3%5.3K$1.38 /M in$4.40 /M out—
60GPT-5.2 Codex (xhigh) openai66.1%—3.4K$1.75 /M in$14.00 /M out1.1M ctx
61GPT-5.4 mini (xhigh) openai65.9%71.6%8.6K$0.75 /M in$4.50 /M out1.1M ctx
62Qwen3.6 Max Preview alibaba65.9%—5.0K$1.30 /M in$7.80 /M out—
63Grok Build 0.1 0616 xai65.6%65.8%7.6K$1.00 /M in$2.00 /M out—
64Qwen3.6 Plus alibaba65.2%69.6%12.6K$0.50 /M in$3.00 /M out—
65Gemini 3 Pro Preview (high) google65.2%—3.2K$2.00 /M in$12.00 /M out1.0M ctx
66GLM-5 (Reasoning) zai65.1%—7.1K$1.00 /M in$3.20 /M out—
67GPT-5.4 (low) openai64.4%—2.5K$2.50 /M in$15.00 /M out1.1M ctx
68Qwen3.7 Plus alibaba64.3%71.4%16.7K$0.40 /M in$1.60 /M out—
69Agnes 2.5 Pro Alpha agnes-ai63.9%75.1%16.1K$0.45 /M in$0.90 /M out—
70GPT-5.4 nano (xhigh) openai62.9%71.6%29.1K$0.20 /M in$1.25 /M out1.1M ctx
71GPT-5.6 Luna (medium) openai62.8%64.8%29.3K$0.20 /M in$1.20 /M out1.1M ctx
72MiniMax-M2.7 minimax62.8%67.2%21.2K$0.30 /M in$1.20 /M out1.0M ctx
73GPT-5.2 (medium) openai62.6%—3.1K$1.75 /M in$14.00 /M out1.1M ctx
74Nemotron 3 Ultra 550B A55B (Reasoning) nvidia62.3%63.0%9.3K$0.68 /M in$2.67 /M out128K
75Gemini 3 Flash Preview (Reasoning) google62.3%—11.5K$0.50 /M in$3.00 /M out1.0M ctx
76Claude Opus 4.6 (Non-reasoning, High Effort) anthropic62.3%—1.2K$5.00 /M in$25.00 /M out1.0M ctx
77Grok 4.3 (high) xai61.9%53.9%5.4K$1.25 /M in$2.50 /M out—
78DeepSeek V4 Flash (Reasoning, High Effort) deepseek61.8%66.4%48.3K$0.14 /M in$0.28 /M out1.0M ctx
79MiMo-V2.5 xiaomi61.3%72.5%47.5K$0.14 /M in$0.28 /M out1.1M ctx
80Qwen3.6 27B (Reasoning) alibaba61.1%68.6%9.2K$0.60 /M in$3.60 /M out—
81Grok 4.20 0309 v2 (Reasoning) xai61.0%—3.1K$2.00 /M in$6.00 /M out—
82GPT-5.1 (high) openai60.8%63.1%4.1K$1.25 /M in$10.00 /M out1.1M ctx
83Gemini 3.5 Flash-Lite google60.1%63.0%16.4K$0.30 /M in$2.50 /M out1.0M ctx
84Grok 4.20 0309 (Reasoning) xai60.1%—3.1K$2.00 /M in$6.00 /M out—
85Claude 4.5 Sonnet (Reasoning) anthropic60.0%66.5%1.9K$3.00 /M in$15.00 /M out1.0M ctx
86GPT-5 Codex (high) openai59.5%—3.9K$1.25 /M in$10.00 /M out1.1M ctx
87Grok 4.3 (medium) xai59.3%—5.0K$1.25 /M in$2.50 /M out—
88Claude Sonnet 4.6 (Non-reasoning, High Effort) anthropic59.1%—1.8K$3.00 /M in$15.00 /M out1.0M ctx
89Grok 4.3 (low) xai58.3%—4.8K$1.25 /M in$2.50 /M out—
90GPT-5.5 (Non-reasoning) openai58.3%72.2%1.0K$5.00 /M in$30.00 /M out1.1M ctx
91Kimi K2.5 (Reasoning) kimi58.3%59.8%8.8K$0.60 /M in$3.00 /M out—
92GLM-5.1 (Non-reasoning) zai58.3%—4.1K$1.38 /M in$4.40 /M out—
93Gemini 3.5 Flash (minimal) google57.5%—3.3K$1.50 /M in$9.00 /M out1.0M ctx
94GPT-5 (high) openai57.2%48.3%3.6K$1.25 /M in$10.00 /M out400K
95GPT-5.1 Codex (high) openai57.2%—3.6K$1.25 /M in$10.00 /M out1.1M ctx
96Claude Opus 4.5 (Non-reasoning) anthropic57.2%—1.0K$5.00 /M in$25.00 /M out1.0M ctx
97Kimi K2.6 (Non-reasoning) kimi57.0%—5.5K$0.95 /M in$4.00 /M out—
98Claude Sonnet 4.6 (Non-reasoning, Low Effort) anthropic56.5%—1.6K$3.00 /M in$15.00 /M out1.0M ctx
99GLM-5.2 (Non-reasoning) zai56.2%59.4%3.9K$1.35 /M in$4.25 /M out—
100GPT-5.6 Terra (Non-reasoning) openai56.0%66.8%2.3K$2.00 /M in$12.00 /M out1.1M ctx
101Qwen3.5 27B (Reasoning) alibaba55.7%—14.2K$0.30 /M in$2.40 /M out—
102KAT Coder Pro V2 kwaikat55.5%76.0%16.6K$0.30 /M in$1.20 /M out—
103Qwen3.5 397B A17B (Reasoning) alibaba55.5%61.6%7.6K$0.60 /M in$3.60 /M out—
104GPT-5 (medium) openai55.5%—3.4K$1.25 /M in$10.00 /M out1.1M ctx
105Claude 4.1 Opus (Reasoning) anthropic55.5%—318$15.00 /M in$75.00 /M out1.0M ctx
106MiniMax-M2.5 minimax55.5%—16.6K$0.30 /M in$1.20 /M out1.0M ctx
107GLM-4.7 (Reasoning) zai55.5%57.9%8.4K$0.60 /M in$2.20 /M out—
108Hy3-preview (Reasoning) tencent55.4%—77.5K$0.07 /M in$0.23 /M out262K
109LongCat 2.0 longcat55.2%57.9%6.6K$0.75 /M in$2.95 /M out—
110GPT-5.5 Instant (May 2026) openai55.2%—905$5.00 /M in$30.00 /M out1.1M ctx
111GPT-5.6 Luna (low) openai54.9%56.4%22.3K$0.20 /M in$1.20 /M out1.1M ctx
112Grok 4 xai54.9%—1.6K$3.00 /M in$15.00 /M out—
113Gemini 3 Pro Preview (low) google54.5%—2.2K$2.00 /M in$12.00 /M out1.0M ctx
114Kimi K2 Thinking kimi53.9%—7.8K$0.60 /M in$2.50 /M out—
115o3-pro openai53.5%—232$20.00 /M in$80.00 /M out200K
116GLM-5 (Non-reasoning) zai53.4%—4.8K$1.00 /M in$3.20 /M out—
117Qwen3.5 122B A10B (Reasoning) alibaba53.2%58.4%9.7K$0.40 /M in$3.20 /M out—
118Qwen3.5 397B A17B (Non-reasoning) alibaba52.7%—6.9K$0.60 /M in$3.60 /M out—
119DeepSeek V3.2 (Reasoning) deepseek52.7%56.4%18.0K$0.28 /M in$0.42 /M out1.0M ctx
120Qwen3.6 35B A3B (Reasoning) alibaba52.1%53.5%16.2K$0.25 /M in$1.49 /M out—
121MiniMax-M2.1 minimax51.7%—14.4K$0.30 /M in$1.20 /M out1.0M ctx
122DeepSeek V4 Pro (Non-reasoning) deepseek51.4%—10.8K$0.43 /M in$0.87 /M out1.0M ctx
123GPT-5 (low) openai51.4%—2.9K$1.25 /M in$10.00 /M out1.1M ctx
124MiMo-V2-Flash (Reasoning) xiaomi51.4%—44.6K$0.10 /M in$0.30 /M out1.1M ctx
125Claude 4 Opus (Reasoning) anthropic51.1%—269$15.00 /M in$75.00 /M out1.0M ctx
126GPT-5 mini (medium) openai50.9%—14.2K$0.25 /M in$2.00 /M out1.1M ctx
127Qwen3.5 Omni Plus alibaba50.4%—7.6K$0.40 /M in$4.80 /M out—
128Ring-2.6-1T inclusionai50.4%54.7%11.5K$0.30 /M in$2.50 /M out262K
129GPT-5.1 Codex mini (high) openai50.4%—14.0K$0.25 /M in$2.00 /M out1.1M ctx
130Qwen3.6 27B (Non-reasoning) alibaba50.2%59.5%6.2K$0.60 /M in$3.60 /M out—
131o3 openai50.1%—2.0K$2.00 /M in$8.00 /M out200K
132DeepSeek V3.1 Terminus (Reasoning) deepseek50.1%55.6%2.8K$1.64 /M in$2.75 /M out1.0M ctx
133Step 3.7 Flash stepfun49.9%50.6%18.7K$0.20 /M in$1.15 /M out262K
134GPT-5.4 nano (medium) openai49.8%—18.2K$0.20 /M in$1.25 /M out1.1M ctx
135Mistral Medium 3.5 mistral49.3%59.9%2.5K$1.50 /M in$7.50 /M out—
136GPT-5.4 mini (medium) openai49.1%—4.8K$0.75 /M in$4.50 /M out1.1M ctx
137Claude 4.5 Haiku (Reasoning) anthropic48.8%56.1%3.7K$1.00 /M in$5.00 /M out1.0M ctx
138Kimi K2.5 (Non-reasoning) kimi48.4%—6.1K$0.60 /M in$3.00 /M out—
139Claude 4.5 Sonnet (Non-reasoning) anthropic48.3%—1.2K$3.00 /M in$15.00 /M out1.0M ctx
140Qwen3.5 27B (Non-reasoning) alibaba48.3%—10.7K$0.30 /M in$2.40 /M out—
141Qwen3.5 35B A3B (Reasoning) alibaba48.3%—12.8K$0.25 /M in$2.00 /M out—
142GPT-5.5 Instant (June 2026) openai47.6%50.3%673$5.00 /M in$30.00 /M out1.1M ctx
143Claude 4 Sonnet (Reasoning) anthropic47.6%48.0%1.2K$3.00 /M in$15.00 /M out1.0M ctx
144DeepSeek V4 Flash (Non-reasoning) deepseek47.3%—28.3K$0.14 /M in$0.28 /M out1.0M ctx
145GLM-4.6 (Reasoning) zai47.3%58.5%6.6K$0.55 /M in$2.20 /M out—
146MiniMax-M2 minimax46.6%—11.7K$0.30 /M in$1.20 /M out205K
147Claude 4.1 Opus (Non-reasoning) anthropic46.5%—223$15.00 /M in$75.00 /M out1.0M ctx
148MiMo-V2.5-Pro (Non-reasoning) xiaomi46.0%—8.6K$0.43 /M in$0.87 /M out1.1M ctx
149GPT-5.4 (Non-reasoning) openai45.6%—1.2K$2.50 /M in$15.00 /M out1.1M ctx
150Qwen3.5 122B A10B (Non-reasoning) alibaba45.5%55.3%7.1K$0.40 /M in$3.20 /M out—
151Gemini 3 Flash Preview (Non-reasoning) google45.1%—6.1K$0.50 /M in$3.00 /M out1.0M ctx
152Grok 4 Fast (Reasoning) xai45.1%—17.6K$0.20 /M in$0.50 /M out—
153GPT-5.6 Luna (Non-reasoning) openai43.8%50.2%14.3K$0.20 /M in$1.20 /M out1.1M ctx
154GLM-4.7 (Non-reasoning) zai43.8%—5.2K$0.60 /M in$2.20 /M out—
155Hy3-preview (Non-reasoning) tencent43.0%—46.7K$0.07 /M in$0.23 /M out262K
156Ling-2.6-1T inclusionai43.0%—8.4K$0.30 /M in$2.50 /M out262K
157GPT-5.2 (Non-reasoning) openai42.8%—1.4K$1.75 /M in$14.00 /M out1.1M ctx
158Step 3.5 Flash 2603 stepfun42.8%—31.0K$0.10 /M in$0.30 /M out262K
159Gemini 2.5 Pro google42.5%42.5%2.0K$1.25 /M in$10.00 /M out1.0M ctx
160Gemma 4 26B A4B (Reasoning) google42.3%50.2%23.2K$0.13 /M in$0.40 /M out262K
161o4-mini (high) openai42.2%—2.6K$1.10 /M in$4.40 /M out200K
162Claude 4 Opus (Non-reasoning) anthropic42.0%—182$15.00 /M in$75.00 /M out1.0M ctx
163Claude 4 Sonnet (Non-reasoning) anthropic42.0%—910$3.00 /M in$15.00 /M out1.0M ctx
164Step 3.5 Flash stepfun42.0%—29.8K$0.10 /M in$0.30 /M out262K
165NVIDIA Nemotron 3 Super 120B A12B (Reasoning) nvidia41.8%48.1%14.1K$0.20 /M in$0.80 /M out128K
166DeepSeek V3.2 Exp (Reasoning) deepseek41.8%—11.3K$0.28 /M in$0.42 /M out1.0M ctx
167GPT-5 mini (high) openai41.7%19.9%9.6K$0.25 /M in$2.00 /M out400K
168Gemini 3.1 Flash-Lite google41.2%44.3%10.1K$0.25 /M in$1.50 /M out1.0M ctx
169Qwen3 Max Thinking (Preview) alibaba41.2%—2.2K$1.20 /M in$6.00 /M out—
170Grok 4.3 (Non-reasoning) xai40.9%45.0%2.4K$1.25 /M in$2.50 /M out—
171DeepSeek V3.2 (Non-reasoning) deepseek40.7%—10.7K$0.28 /M in$0.42 /M out1.0M ctx
172Qwen3.6 35B A3B (Non-reasoning) alibaba39.9%35.9%6.3K$0.38 /M in$2.25 /M out—
173Qwen3.5 35B A3B (Non-reasoning) alibaba39.5%47.3%8.6K$0.25 /M in$2.00 /M out—
174Qwen3 Max alibaba39.5%—2.0K$1.20 /M in$6.00 /M out—
175gpt-oss-120b (high) openai39.2%38.8%16.6K$0.15 /M in$0.60 /M out131K
176Claude 4.5 Haiku (Non-reasoning) anthropic39.0%—2.4K$1.00 /M in$5.00 /M out1.0M ctx
177Claude 3.7 Sonnet (Non-reasoning) anthropic38.7%—773$3.00 /M in$15.00 /M out1.0M ctx
178Kimi K2 0905 kimi38.7%—4.0K$0.60 /M in$2.50 /M out—
179o1 openai38.6%50.7%160$15.00 /M in$60.00 /M out200K
180GLM-4.6 (Non-reasoning) zai37.9%—4.1K$0.57 /M in$2.20 /M out—
181GLM-4.7-Flash (Reasoning) zai37.7%—30.5K$0.07 /M in$0.40 /M out—
182Grok 3 mini Reasoning (high) xai37.1%—8.2K$0.30 /M in$0.50 /M out—
183Grok 4.20 0309 (Non-reasoning) xai37.1%—1.2K$2.00 /M in$6.00 /M out—
184Gemini 2.5 Pro Preview (May' 25) google36.7%—1.5K$1.25 /M in$10.00 /M out1.0M ctx
185Gemma 4 12B (Reasoning) google35.9%39.6%21.8K$0.10 /M in$0.30 /M out262K
186Gemma 4 31B (Non-reasoning) google35.9%42.4%15.7K$0.14 /M in$0.40 /M out262K
187Nova 2.0 Pro Preview (medium) aws35.9%43.4%1.4K$1.25 /M in$10.00 /M out—
188Grok 4.20 0309 v2 (Non-reasoning) xai35.9%—1.1K$2.00 /M in$6.00 /M out—
189Mercury 2 inception35.3%39.7%8.4K$0.25 /M in$0.75 /M out128K
190Qwen3.5 9B (Reasoning) alibaba35.3%36.7%16.7K$0.14 /M in$0.20 /M out—
191DeepSeek V3.1 Terminus (Non-reasoning) deepseek35.3%—7.5K$0.27 /M in$1.00 /M out1.0M ctx
192DeepSeek V3.2 Exp (Non-reasoning) deepseek35.1%—8.0K$0.28 /M in$0.42 /M out1.0M ctx
193Qwen3 Coder Next alibaba34.8%46.2%5.7K$0.35 /M in$1.20 /M out—
194DeepSeek V3.1 (Non-reasoning) deepseek34.6%—3.6K$0.56 /M in$1.68 /M out1.0M ctx
195Nova 2.0 Omni (medium) aws34.4%—5.4K$0.30 /M in$2.50 /M out—
196DeepSeek V3.1 (Reasoning) deepseek34.1%—3.4K$0.59 /M in$1.69 /M out1.0M ctx
197Qwen3 VL 235B A22B (Reasoning) alibaba33.9%—2.0K$0.70 /M in$8.40 /M out—
198GPT-5.1 (Non-reasoning) openai33.6%—1.2K$1.25 /M in$10.00 /M out1.1M ctx
199Gemma 4 26B A4B (Non-reasoning) google33.1%—14.2K$0.13 /M in$0.40 /M out262K
200Qwen3.5 4B (Reasoning) alibaba33.1%28.9%56.6K$0.03 /M in$0.15 /M out—
201Gemini 2.5 Flash (Reasoning) google33.1%—5.0K$0.30 /M in$2.50 /M out1.0M ctx
202DeepSeek R1 0528 (May '25) deepseek33.1%—1.4K$1.35 /M in$4.20 /M out164K
203GPT-5 nano (high) openai32.8%—29.5K$0.05 /M in$0.40 /M out400K
204Mistral Small 4 (Reasoning) mistral32.3%34.0%11.2K$0.15 /M in$0.60 /M out—
205Nova 2.0 Pro Preview (low) aws32.3%33.1%1.1K$1.25 /M in$10.00 /M out—
206Qwen3 235B A22B 2507 (Reasoning) alibaba32.3%28.2%1.8K$0.70 /M in$8.40 /M out—
207GPT-4.1 openai32.0%—825$2.00 /M in$8.00 /M out1.1M ctx
208Kimi K2 kimi32.0%—2.9K$0.57 /M in$2.30 /M out—
209Qwen3 Max (Preview) alibaba31.6%—1.3K$1.20 /M in$6.00 /M out—
210Nova 2.0 Lite (medium) aws31.3%—4.4K$0.30 /M in$2.50 /M out—
211Qwen3.5 Omni Flash alibaba31.3%—13.5K$0.10 /M in$0.80 /M out—
212o3-mini openai31.3%—1.4K$1.10 /M in$4.40 /M out200K
213GPT-5 nano (medium) openai31.3%—26.9K$0.05 /M in$0.40 /M out1.1M ctx
214o1-pro openai31.1%—10.4$150.00 /M in$600.00 /M out200K
215DeepSeek R1 (Jan '25) deepseek30.5%31.4%945$1.68 /M in$4.70 /M out1.0M ctx
216Grok 3 xai30.3%—355$4.00 /M in$20.00 /M out—
217Seed-OSS-36B-Instruct bytedance_seed30.1%—7.4K$0.21 /M in$0.57 /M out—
218Nova 2.0 Lite (high) aws30.0%29.4%4.1K$0.30 /M in$2.50 /M out—
219Trinity Large Thinking arcee30.0%33.0%6.3K$0.23 /M in$0.88 /M out—
220Qwen3 235B A22B 2507 Instruct alibaba30.0%—2.1K$0.70 /M in$2.80 /M out—
221Qwen3 Coder 480B A35B Instruct alibaba29.7%—907$1.50 /M in$7.50 /M out—
222Magistral Medium 1.2 mistral29.5%27.2%752$2.00 /M in$5.00 /M out—
223Qwen3 VL 32B (Reasoning) alibaba29.5%—1.5K$0.70 /M in$8.40 /M out—
224Nova 2.0 Lite (low) aws29.3%—3.9K$0.30 /M in$2.50 /M out—
225HyperNova 60B 2605 multiversecomputing29.3%29.6%35.5K$0.04 /M in$0.14 /M out—
226MiniMax M1 80k minimax29.2%—2.5K$0.55 /M in$2.20 /M out1.0M ctx
227GPT-5.4 nano (Non-Reasoning) openai29.0%—6.2K$0.20 /M in$1.25 /M out1.1M ctx
228GPT-5 (minimal) openai28.3%—883$1.25 /M in$10.00 /M out1.1M ctx
229o1-preview openai28.0%43.4%76.8$16.50 /M in$66.00 /M out200K
230GLM-4.6V (Reasoning) zai27.7%—4.3K$0.30 /M in$0.90 /M out—
231Qwen3 Next 80B A3B (Reasoning) alibaba27.5%22.2%1.8K$0.50 /M in$6.00 /M out—
232Nova 2.0 Omni (low) aws27.3%—3.4K$0.30 /M in$2.50 /M out—
233GPT-5.4 mini (Non-Reasoning) openai27.3%—1.5K$0.75 /M in$4.50 /M out1.1M ctx
234Grok 4 Fast (Non-reasoning) xai27.2%—6.4K$0.20 /M in$0.50 /M out—
235GLM-4.5-Air zai27.2%—6.5K$0.17 /M in$0.98 /M out—
236Qwen3.5 4B (Non-reasoning) alibaba26.4%25.9%35.8K$0.03 /M in$0.15 /M out—
237Mistral Large 3 mistral26.2%25.7%2.3K$0.50 /M in$1.50 /M out—
238o3-mini (high) openai25.7%20.8%970$1.10 /M in$4.40 /M out200K
239GLM-4.7-Flash (Non-reasoning) zai25.5%—14.0K$0.07 /M in$0.40 /M out—
240DeepSeek V3 0324 deepseek25.4%27.1%3.8K$0.27 /M in$1.12 /M out1.0M ctx
241Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) google24.9%—10.0K$0.10 /M in$0.40 /M out1.0M ctx
242gpt-oss-20b (high) openai24.5%26.4%14.6K$0.07 /M in$0.20 /M out131K
243gpt-oss-120b (low) openai24.5%27.1%6.5K$0.15 /M in$0.59 /M out1.1M ctx
244Nemotron 3 Nano Omni 30B A3B Reasoning nvidia24.5%17.6%13.0K$0.07 /M in$0.30 /M out128K
245GPT-4.1 mini openai24.4%25.8%2.4K$0.40 /M in$1.60 /M out1.1M ctx
246Mistral Small 3.1 mistral24.2%33.6%9.9K$0.10 /M in$0.30 /M out—
247Mistral Medium 3.1 mistral24.2%26.2%2.3K$0.40 /M in$2.00 /M out—
248Nova 2.0 Pro Preview (Non-reasoning) aws23.7%26.7%619$1.25 /M in$10.00 /M out—
249Qwen3 30B A3B 2507 (Reasoning) alibaba23.7%15.5%3.4K$0.20 /M in$2.40 /M out—
250gpt-oss-20b (low) openai23.6%—13.3K$0.07 /M in$0.23 /M out1.1M ctx
251Llama 4 Maverick meta23.6%20.8%3.4K$0.27 /M in$0.85 /M out—
252GPT-5 mini (minimal) openai23.6%—3.1K$0.25 /M in$2.00 /M out1.1M ctx
253Qwen3 VL 235B A22B Instruct alibaba23.6%—1.3K$0.70 /M in$2.80 /M out—
254NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) nvidia23.4%18.4%17.7K$0.05 /M in$0.20 /M out128K
255DeepSeek V3 (Dec '24) deepseek23.4%29.4%2.6K$0.36 /M in$0.89 /M out1.0M ctx
256Solar Pro 3 upstage23.2%20.7%5.8K$0.15 /M in$0.60 /M out128K
257Ling 2.6 Flash inclusionai23.2%32.3%9.1K$0.10 /M in$0.30 /M out262K
258Gemini 2.5 Flash (Non-reasoning) google23.2%—2.4K$0.30 /M in$2.50 /M out1.0M ctx
259Qwen3 Next 80B A3B Instruct alibaba22.6%—1.6K$0.50 /M in$2.00 /M out—
260Qwen3 Coder 30B A3B Instruct alibaba22.4%—1.7K$0.45 /M in$2.25 /M out—
261Qwen3 235B A22B (Reasoning) alibaba22.1%—833$0.70 /M in$8.40 /M out—
262QwQ 32B alibaba22.1%—1.3K$0.66 /M in$1.00 /M out—
263Qwen3 VL 30B A3B (Reasoning) alibaba21.9%—2.9K$0.20 /M in$2.40 /M out—
264Gemma 4 12B (Non-reasoning) google21.7%—8.0K$0.10 /M in$0.30 /M out262K
265Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) google21.6%—7.5K$0.10 /M in$0.40 /M out1.0M ctx
266Nova Premier aws20.9%—271$2.50 /M in$12.50 /M out—
267Mistral Medium 3 mistral20.6%—1.6K$0.40 /M in$2.00 /M out—
268Mistral Small 4 (Non-reasoning) mistral20.4%—4.5K$0.15 /M in$0.60 /M out—
269Llama Nemotron Super 49B v1.5 (Reasoning) nvidia20.4%—1.9K$0.40 /M in$0.40 /M out—
270Gemma 4 E4B (Reasoning) google20.1%12.0%31.3K$0.02 /M in$0.10 /M out262K
271Sarvam 105B (high) sarvam19.6%—14.8K$0.04 /M in$0.17 /M out—
272Nova 2.0 Lite (Non-reasoning) aws19.4%—1.7K$0.30 /M in$2.50 /M out—
273Celeris-1 celeris19.4%18.4%319$2.00 /M in$6.00 /M out—
274Claude 3 Opus anthropic19.4%24.9%39.0$15.00 /M in$75.00 /M out1.0M ctx
275Qwen3 32B (Reasoning) alibaba18.9%19.5%613$0.70 /M in$8.40 /M out—
276Gemini 2.5 Flash-Lite (Reasoning) google18.8%—5.7K$0.10 /M in$0.40 /M out1.0M ctx
277Magistral Small 1.2 mistral18.6%18.8%1.2K$0.50 /M in$1.50 /M out—
278GPT-4o (Nov '24) openai18.5%—220$2.50 /M in$10.00 /M out128K
279Ministral 3 14B mistral18.3%18.4%3.1K$0.20 /M in$0.20 /M out—
280Qwen3 VL 32B Instruct alibaba18.3%—772$0.70 /M in$2.80 /M out—
281GLM-4.6V (Non-reasoning) zai18.1%—1.8K$0.30 /M in$0.90 /M out—
282Qwen3 235B A22B (Non-reasoning) alibaba18.0%—744$0.70 /M in$2.80 /M out—
283Mistral Small 3.2 mistral17.5%16.0%5.2K$0.10 /M in$0.30 /M out—
284Qwen3 VL 8B (Reasoning) alibaba17.5%—2.0K$0.18 /M in$2.10 /M out—
285Nova 2.0 Omni (Non-reasoning) aws17.3%—1.4K$0.30 /M in$2.50 /M out—
286Qwen3 14B (Reasoning) alibaba17.1%17.6%1.0K$0.35 /M in$4.20 /M out—
287Llama 4 Scout meta16.5%10.5%2.5K$0.18 /M in$0.66 /M out—
288Hermes 4 - Llama-3.1 70B (Reasoning) nous-research16.5%—3.5K$0.13 /M in$0.40 /M out—
289Qwen3 VL 30B A3B Instruct alibaba16.5%—2.2K$0.20 /M in$0.80 /M out—
290Claude 3.5 Sonnet (Oct '24) anthropic16.3%38.6%137$3.00 /M in$15.00 /M out1.0M ctx
291DeepSeek R1 Distill Llama 70B deepseek16.3%—689$0.70 /M in$1.05 /M out8K
292Ling-flash-2.0 inclusionai16.0%—2.9K$0.14 /M in$0.57 /M out262K
293Qwen3 Omni 30B A3B (Reasoning) alibaba15.8%—1.6K$0.25 /M in$0.97 /M out—
294GPT-4o (Aug '24) openai15.8%—162$2.50 /M in$10.00 /M out128K
295GPT-4.1 nano openai15.8%14.2%4.0K$0.10 /M in$0.40 /M out1.1M ctx
296Qwen2.5 Instruct 72B alibaba15.8%—977$0.47 /M in$0.49 /M out—
297Llama 3.3 Instruct 70B meta15.5%15.2%736$0.60 /M in$0.72 /M out—
298Qwen3 30B A3B (Reasoning) alibaba15.3%—1.4K$0.20 /M in$2.40 /M out—
299Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) nvidia15.0%—633$0.60 /M in$1.80 /M out—
300GLM-4.5V (Reasoning) zai15.0%—633$0.60 /M in$1.80 /M out—
301Qwen3 30B A3B 2507 Instruct alibaba15.0%—1.8K$0.20 /M in$0.80 /M out—
302Ministral 3 8B mistral14.8%12.4%2.7K$0.15 /M in$0.15 /M out—
303NVIDIA Nemotron Nano 12B v2 VL (Reasoning) nvidia14.8%—1.9K$0.20 /M in$0.60 /M out128K
304Hermes 4 - Llama-3.1 405B (Reasoning) nous-research14.8%—371$1.00 /M in$3.00 /M out—
305ERNIE 4.5 300B A47B baidu14.8%—1.3K$0.28 /M in$1.10 /M out123K
306Gemma 4 E4B (Non-reasoning) google14.7%—16.6K$0.02 /M in$0.10 /M out262K
307NVIDIA Nemotron Nano 9B V2 (Reasoning) nvidia14.5%—8.5K$0.04 /M in$0.16 /M out128K
308Hermes 4 - Llama-3.1 405B (Non-reasoning) nous-research14.5%—355$1.00 /M in$3.00 /M out—
309Llama Nemotron Super 49B v1.5 (Non-reasoning) nvidia14.3%—955$0.40 /M in$0.40 /M out—
310GPT-4o (May '24) openai14.2%30.9%67.8$5.00 /M in$15.00 /M out128K
311Qwen3 32B (Non-reasoning) alibaba14.2%—463$0.70 /M in$2.80 /M out—
312Llama 3.1 Instruct 405B meta14.0%—127$2.50 /M in$10.00 /M out—
313Qwen3 VL 8B Instruct alibaba13.8%—1.7K$0.18 /M in$0.70 /M out—
314Claude 3.5 Sonnet (June '24) anthropic13.7%33.2%96.4$3.00 /M in$15.00 /M out1.0M ctx
315Qwen3 8B (Reasoning) alibaba13.7%11.5%1.3K$0.18 /M in$2.10 /M out—
316Ring-flash-2.0 inclusionai13.5%—2.1K$0.14 /M in$0.57 /M out262K
317GPT-5 nano (minimal) openai13.2%—4.8K$0.05 /M in$0.40 /M out1.1M ctx
318GPT-4 Turbo openai13.0%27.5%28.6$10.00 /M in$30.00 /M out128K
319Command A cohere12.7%—104$2.50 /M in$10.00 /M out256K
320Nova Pro aws12.7%—325$0.80 /M in$3.20 /M out—
321Llama 3.1 Nemotron Instruct 70B nvidia12.5%—243$1.20 /M in$1.20 /M out—
322Llama 3.1 Instruct 8B meta12.5%6.9%3.8K$0.07 /M in$0.09 /M out—
323NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) nvidia12.2%—4.8K$0.05 /M in$0.20 /M out128K
324NVIDIA Nemotron Nano 9B V2 (Non-reasoning) nvidia12.2%—4.8K$0.05 /M in$0.20 /M out128K
325Mistral Large 2 (Jul '24) mistral12.0%—122$2.00 /M in$6.00 /M out—
326GPT-4 openai11.5%16.7%7.8$30.00 /M in$60.00 /M out8K
327GLM-4.5V (Non-reasoning) zai11.5%—374$0.60 /M in$1.80 /M out—
328Qwen3 14B (Non-reasoning) alibaba11.5%—614$0.35 /M in$1.40 /M out—
329Hermes 4 - Llama-3.1 70B (Non-reasoning) nous-research11.4%—1.7K$0.13 /M in$0.40 /M out—
330GPT-4o mini openai11.4%14.6%1.4K$0.15 /M in$0.60 /M out128K
331Gemini 2.5 Flash-Lite (Non-reasoning) google11.4%—2.1K$0.10 /M in$0.40 /M out1.0M ctx
332Mistral Small 3 mistral11.4%—2.2K$0.10 /M in$0.30 /M out—
333Nova Lite aws11.4%—3.5K$0.06 /M in$0.24 /M out—
334Ministral 3 3B mistral11.2%6.1%2.3K$0.10 /M in$0.10 /M out—
335Llama 3.1 Instruct 70B meta11.2%—417$0.56 /M in$0.56 /M out—
336Qwen3 30B A3B (Non-reasoning) alibaba11.2%—1.0K$0.20 /M in$0.80 /M out—
337Granite 4.1 8B ibm11.0%12.1%4.3K$0.05 /M in$0.10 /M out—
338Sarvam 30B (high) sarvam10.9%—7.3K$0.03 /M in$0.11 /M out—
339Reka Flash (Sep '24) reka-ai10.4%—870$0.20 /M in$0.80 /M out—
340Qwen2.5 Turbo alibaba10.4%—3.5K$0.05 /M in$0.20 /M out—
341Solar Mini upstage10.2%—1.3K$0.15 /M in$0.15 /M out128K
342Jamba 1.7 Large ai21-labs8.7%—61.6$2.00 /M in$8.00 /M out—
343Granite 4.0 H Small ibm8.6%—2.0K$0.06 /M in$0.25 /M out—
344Qwen3 Omni 30B A3B Instruct alibaba8.4%—459$0.25 /M in$0.97 /M out—
345Hermes 3 - Llama-3.1 70B nous-research8.4%—188$0.70 /M in$0.70 /M out—
346Jamba 1.5 Large ai21-labs8.4%—57.0$2.00 /M in$8.00 /M out—
347Qwen3 8B (Non-reasoning) alibaba8.4%—637$0.18 /M in$0.70 /M out—
348Jamba 1.6 Large ai21-labs8.2%—54.8$2.00 /M in$8.00 /M out—
349Phi-4 azure8.1%—842$0.13 /M in$0.50 /M out—
350Nova Micro aws7.7%—2.8K$0.04 /M in$0.14 /M out—
351Claude 3 Sonnet anthropic7.7%—30.9$3.00 /M in$15.00 /M out1.0M ctx
352Mistral Small (Sep '24) mistral7.7%—506$0.20 /M in$0.60 /M out—
353NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) nvidia7.6%—485$0.20 /M in$0.60 /M out128K
354Mistral Large (Feb '24) mistral7.2%—22.2$4.00 /M in$12.00 /M out—
355Llama 2 Chat 7B meta7.1%—1.6K$0.05 /M in$0.25 /M out—
356Reka Flash 3 reka-ai6.8%—368$0.20 /M in$0.80 /M out—
357Claude 3 Haiku anthropic6.4%—256$0.25 /M in$1.25 /M out200K
358GPT-3.5 Turbo openai5.9%13.7%119$0.50 /M in$1.50 /M out1.1M ctx
359Mistral Small (Feb '24) mistral5.9%—379$0.15 /M in$0.60 /M out—
360Mistral Medium mistral5.9%—36.3$1.50 /M in$7.50 /M out—
361Llama 3 Instruct 70B meta5.8%—81.8$0.65 /M in$2.75 /M out—
362Llama 3.2 Instruct 11B (Vision) meta5.4%—159$0.34 /M in$0.34 /M out—
363Command-R+ (Apr '24) cohere4.9%—12.6$3.00 /M in$15.00 /M out256K
364Olmo 3 7B Instruct ai24.6%—377$0.10 /M in$0.20 /M out—
365Jamba 1.5 Mini ai21-labs4.4%—175$0.20 /M in$0.40 /M out—
366Jamba 1.6 Mini ai21-labs4.3%—162$0.20 /M in$0.40 /M out—
367Apertus 70B Instruct swiss-ai-initiative4.0%—31.4$0.82 /M in$2.92 /M out—
368Mixtral 8x7B Instruct mistral4.0%—62.9$0.45 /M in$0.70 /M out—
369Mistral 7B Instruct mistral3.5%—89.0$0.25 /M in$0.25 /M out—
370Command-R (Mar '24) cohere3.5%—40.4$0.50 /M in$1.50 /M out256K
371Granite 3.3 8B (Non-reasoning) ibm3.0%—398$0.03 /M in$0.25 /M out—
372Llama 3 Instruct 8B meta2.0%—145$0.04 /M in$0.14 /M out—
373Gemma 3n E4B Instruct google2.0%4.1%115$0.06 /M in$0.12 /M out262K
374Apertus 8B Instruct swiss-ai-initiative1.6%—48.1$0.10 /M in$0.20 /M out—
375Claude Sonnet 5 (Adaptive Reasoning, High Effort) anthropic———$2.00 /M in$10.00 /M out1.0M ctx
376Claude Sonnet 5 (Adaptive Reasoning, Medium Effort) anthropic———$2.00 /M in$10.00 /M out1.0M ctx
377Claude Sonnet 5 (Adaptive Reasoning, Low Effort) anthropic———$2.00 /M in$10.00 /M out1.0M ctx
378Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort) anthropic———$2.00 /M in$10.00 /M out1.0M ctx
379Cogito v2.1 (Reasoning) deepcogito———$1.25 /M in$1.25 /M out128K
380GPT-5.4 Pro (xhigh) openai———$30.00 /M in$180.00 /M out1.1M ctx
  1. 1 Claude Opus 5 (Adaptive Reasoning, Max Effort)
  2. 2 Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)
  3. 3 Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)
  4. 4 GPT-5.6 Sol (max)
  5. 5 Claude Opus 5 (Adaptive Reasoning, High Effort)
  6. 6 GPT-5.6 Sol (xhigh)
  7. 7 Kimi K3 (max)
  8. 8 Claude Opus 5 (Adaptive Reasoning, Medium Effort)
  9. 9 GPT-5.6 Sol (high)
  10. 10 Claude Opus 4.8 (Adaptive Reasoning, Max Effort)
  11. 11 GPT-5.6 Terra (max)
  12. 12 GPT-5.5 (xhigh)
  13. 13 Grok 4.5 (high)
  14. 14 GPT-5.6 Sol (medium)
  15. 15 Claude Opus 4.7 (Adaptive Reasoning, Max Effort)
  16. 16 Claude Sonnet 5 (Adaptive Reasoning, Max Effort)
  17. 17 Qwen3.8 Max
  18. 18 GPT-5.5 (high)
  19. 19 GPT-5.6 Terra (xhigh)
  20. 20 GPT-5.4 (xhigh)
  21. 21 GPT-5.6 Luna (max)
  22. 22 GLM-5.2 (max)
  23. 23 Muse Spark 1.1 (xhigh)
  24. 24 Claude Opus 5 (Adaptive Reasoning, Low Effort)
  25. 25 GPT-5.5 (medium)
  26. 26 Gemini 3.5 Flash (high)
  27. 27 Gemini 3.6 Flash (high)
  28. 28 DeepSeek V4 Flash 0731 (Reasoning, Max Effort)
  29. 29 GPT-5.6 Sol (low)
  30. 30 GPT-5.6 Luna (xhigh)
  31. 31 GPT-5.6 Terra (high)
  32. 32 Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)
  33. 33 Kimi K3 (low)
  34. 34 Gemini 3.1 Pro Preview
  35. 35 GPT-5.6 Luna (high)
  36. 36 Qwen3.7 Max
  37. 37 GPT-5.6 Terra (medium)
  38. 38 Gemini 3.5 Flash (medium)
  39. 39 MiniMax-M3
  40. 40 GPT-5.3 Codex (xhigh)
  41. 41 DeepSeek V4 Pro (Reasoning, Max Effort)
  42. 42 Kimi K2.6
  43. 43 Claude Opus 4.6 (Adaptive Reasoning, Max Effort)
  44. 44 GPT-5.5 (low)
  45. 45 DeepSeek V4 Pro (Reasoning, High Effort)
  46. 46 Claude Opus 4.7 (Non-reasoning, High Effort)
  47. 47 MiMo-V2.5-Pro
  48. 48 GPT-5.2 (xhigh)
  49. 49 Kimi K2.7 Code
  50. 50 Claude Sonnet 5 (Non-reasoning, High Effort)
  51. 51 GPT-5.6 Sol (Non-reasoning)
  52. 52 Hy3
  53. 53 Nex-N2-Pro
  54. 54 Claude Opus 4.5 (Reasoning)
  55. 55 Inkling (xhigh)
  56. 56 GPT-5.6 Terra (low)
  57. 57 DeepSeek V4 Flash (Reasoning, Max Effort)
  58. 58 Inkling Small
  59. 59 GLM-5.1 (Reasoning)
  60. 60 GPT-5.2 Codex (xhigh)
  61. 61 GPT-5.4 mini (xhigh)
  62. 62 Qwen3.6 Max Preview
  63. 63 Grok Build 0.1 0616
  64. 64 Qwen3.6 Plus
  65. 65 Gemini 3 Pro Preview (high)
  66. 66 GLM-5 (Reasoning)
  67. 67 GPT-5.4 (low)
  68. 68 Qwen3.7 Plus
  69. 69 Agnes 2.5 Pro Alpha
  70. 70 GPT-5.4 nano (xhigh)
  71. 71 GPT-5.6 Luna (medium)
  72. 72 MiniMax-M2.7
  73. 73 GPT-5.2 (medium)
  74. 74 Nemotron 3 Ultra 550B A55B (Reasoning)
  75. 75 Gemini 3 Flash Preview (Reasoning)
  76. 76 Claude Opus 4.6 (Non-reasoning, High Effort)
  77. 77 Grok 4.3 (high)
  78. 78 DeepSeek V4 Flash (Reasoning, High Effort)
  79. 79 MiMo-V2.5
  80. 80 Qwen3.6 27B (Reasoning)
  81. 81 Grok 4.20 0309 v2 (Reasoning)
  82. 82 GPT-5.1 (high)
  83. 83 Gemini 3.5 Flash-Lite
  84. 84 Grok 4.20 0309 (Reasoning)
  85. 85 Claude 4.5 Sonnet (Reasoning)
  86. 86 GPT-5 Codex (high)
  87. 87 Grok 4.3 (medium)
  88. 88 Claude Sonnet 4.6 (Non-reasoning, High Effort)
  89. 89 Grok 4.3 (low)
  90. 90 GPT-5.5 (Non-reasoning)
  91. 91 Kimi K2.5 (Reasoning)
  92. 92 GLM-5.1 (Non-reasoning)
  93. 93 Gemini 3.5 Flash (minimal)
  94. 94 GPT-5 (high)
  95. 95 GPT-5.1 Codex (high)
  96. 96 Claude Opus 4.5 (Non-reasoning)
  97. 97 Kimi K2.6 (Non-reasoning)
  98. 98 Claude Sonnet 4.6 (Non-reasoning, Low Effort)
  99. 99 GLM-5.2 (Non-reasoning)
  100. 100 GPT-5.6 Terra (Non-reasoning)
  101. 101 Qwen3.5 27B (Reasoning)
  102. 102 KAT Coder Pro V2
  103. 103 Qwen3.5 397B A17B (Reasoning)
  104. 104 GPT-5 (medium)
  105. 105 Claude 4.1 Opus (Reasoning)
  106. 106 MiniMax-M2.5
  107. 107 GLM-4.7 (Reasoning)
  108. 108 Hy3-preview (Reasoning)
  109. 109 LongCat 2.0
  110. 110 GPT-5.5 Instant (May 2026)
  111. 111 GPT-5.6 Luna (low)
  112. 112 Grok 4
  113. 113 Gemini 3 Pro Preview (low)
  114. 114 Kimi K2 Thinking
  115. 115 o3-pro
  116. 116 GLM-5 (Non-reasoning)
  117. 117 Qwen3.5 122B A10B (Reasoning)
  118. 118 Qwen3.5 397B A17B (Non-reasoning)
  119. 119 DeepSeek V3.2 (Reasoning)
  120. 120 Qwen3.6 35B A3B (Reasoning)
  121. 121 MiniMax-M2.1
  122. 122 DeepSeek V4 Pro (Non-reasoning)
  123. 123 GPT-5 (low)
  124. 124 MiMo-V2-Flash (Reasoning)
  125. 125 Claude 4 Opus (Reasoning)
  126. 126 GPT-5 mini (medium)
  127. 127 Qwen3.5 Omni Plus
  128. 128 Ring-2.6-1T
  129. 129 GPT-5.1 Codex mini (high)
  130. 130 Qwen3.6 27B (Non-reasoning)
  131. 131 o3
  132. 132 DeepSeek V3.1 Terminus (Reasoning)
  133. 133 Step 3.7 Flash
  134. 134 GPT-5.4 nano (medium)
  135. 135 Mistral Medium 3.5
  136. 136 GPT-5.4 mini (medium)
  137. 137 Claude 4.5 Haiku (Reasoning)
  138. 138 Kimi K2.5 (Non-reasoning)
  139. 139 Claude 4.5 Sonnet (Non-reasoning)
  140. 140 Qwen3.5 27B (Non-reasoning)
  141. 141 Qwen3.5 35B A3B (Reasoning)
  142. 142 GPT-5.5 Instant (June 2026)
  143. 143 Claude 4 Sonnet (Reasoning)
  144. 144 DeepSeek V4 Flash (Non-reasoning)
  145. 145 GLM-4.6 (Reasoning)
  146. 146 MiniMax-M2
  147. 147 Claude 4.1 Opus (Non-reasoning)
  148. 148 MiMo-V2.5-Pro (Non-reasoning)
  149. 149 GPT-5.4 (Non-reasoning)
  150. 150 Qwen3.5 122B A10B (Non-reasoning)
  151. 151 Gemini 3 Flash Preview (Non-reasoning)
  152. 152 Grok 4 Fast (Reasoning)
  153. 153 GPT-5.6 Luna (Non-reasoning)
  154. 154 GLM-4.7 (Non-reasoning)
  155. 155 Hy3-preview (Non-reasoning)
  156. 156 Ling-2.6-1T
  157. 157 GPT-5.2 (Non-reasoning)
  158. 158 Step 3.5 Flash 2603
  159. 159 Gemini 2.5 Pro
  160. 160 Gemma 4 26B A4B (Reasoning)
  161. 161 o4-mini (high)
  162. 162 Claude 4 Opus (Non-reasoning)
  163. 163 Claude 4 Sonnet (Non-reasoning)
  164. 164 Step 3.5 Flash
  165. 165 NVIDIA Nemotron 3 Super 120B A12B (Reasoning)
  166. 166 DeepSeek V3.2 Exp (Reasoning)
  167. 167 GPT-5 mini (high)
  168. 168 Gemini 3.1 Flash-Lite
  169. 169 Qwen3 Max Thinking (Preview)
  170. 170 Grok 4.3 (Non-reasoning)
  171. 171 DeepSeek V3.2 (Non-reasoning)
  172. 172 Qwen3.6 35B A3B (Non-reasoning)
  173. 173 Qwen3.5 35B A3B (Non-reasoning)
  174. 174 Qwen3 Max
  175. 175 gpt-oss-120b (high)
  176. 176 Claude 4.5 Haiku (Non-reasoning)
  177. 177 Claude 3.7 Sonnet (Non-reasoning)
  178. 178 Kimi K2 0905
  179. 179 o1
  180. 180 GLM-4.6 (Non-reasoning)
  181. 181 GLM-4.7-Flash (Reasoning)
  182. 182 Grok 3 mini Reasoning (high)
  183. 183 Grok 4.20 0309 (Non-reasoning)
  184. 184 Gemini 2.5 Pro Preview (May' 25)
  185. 185 Gemma 4 12B (Reasoning)
  186. 186 Gemma 4 31B (Non-reasoning)
  187. 187 Nova 2.0 Pro Preview (medium)
  188. 188 Grok 4.20 0309 v2 (Non-reasoning)
  189. 189 Mercury 2
  190. 190 Qwen3.5 9B (Reasoning)
  191. 191 DeepSeek V3.1 Terminus (Non-reasoning)
  192. 192 DeepSeek V3.2 Exp (Non-reasoning)
  193. 193 Qwen3 Coder Next
  194. 194 DeepSeek V3.1 (Non-reasoning)
  195. 195 Nova 2.0 Omni (medium)
  196. 196 DeepSeek V3.1 (Reasoning)
  197. 197 Qwen3 VL 235B A22B (Reasoning)
  198. 198 GPT-5.1 (Non-reasoning)
  199. 199 Gemma 4 26B A4B (Non-reasoning)
  200. 200 Qwen3.5 4B (Reasoning)
  201. 201 Gemini 2.5 Flash (Reasoning)
  202. 202 DeepSeek R1 0528 (May '25)
  203. 203 GPT-5 nano (high)
  204. 204 Mistral Small 4 (Reasoning)
  205. 205 Nova 2.0 Pro Preview (low)
  206. 206 Qwen3 235B A22B 2507 (Reasoning)
  207. 207 GPT-4.1
  208. 208 Kimi K2
  209. 209 Qwen3 Max (Preview)
  210. 210 Nova 2.0 Lite (medium)
  211. 211 Qwen3.5 Omni Flash
  212. 212 o3-mini
  213. 213 GPT-5 nano (medium)
  214. 214 o1-pro
  215. 215 DeepSeek R1 (Jan '25)
  216. 216 Grok 3
  217. 217 Seed-OSS-36B-Instruct
  218. 218 Nova 2.0 Lite (high)
  219. 219 Trinity Large Thinking
  220. 220 Qwen3 235B A22B 2507 Instruct
  221. 221 Qwen3 Coder 480B A35B Instruct
  222. 222 Magistral Medium 1.2
  223. 223 Qwen3 VL 32B (Reasoning)
  224. 224 Nova 2.0 Lite (low)
  225. 225 HyperNova 60B 2605
  226. 226 MiniMax M1 80k
  227. 227 GPT-5.4 nano (Non-Reasoning)
  228. 228 GPT-5 (minimal)
  229. 229 o1-preview
  230. 230 GLM-4.6V (Reasoning)
  231. 231 Qwen3 Next 80B A3B (Reasoning)
  232. 232 Nova 2.0 Omni (low)
  233. 233 GPT-5.4 mini (Non-Reasoning)
  234. 234 Grok 4 Fast (Non-reasoning)
  235. 235 GLM-4.5-Air
  236. 236 Qwen3.5 4B (Non-reasoning)
  237. 237 Mistral Large 3
  238. 238 o3-mini (high)
  239. 239 GLM-4.7-Flash (Non-reasoning)
  240. 240 DeepSeek V3 0324
  241. 241 Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)
  242. 242 gpt-oss-20b (high)
  243. 243 gpt-oss-120b (low)
  244. 244 Nemotron 3 Nano Omni 30B A3B Reasoning
  245. 245 GPT-4.1 mini
  246. 246 Mistral Small 3.1
  247. 247 Mistral Medium 3.1
  248. 248 Nova 2.0 Pro Preview (Non-reasoning)
  249. 249 Qwen3 30B A3B 2507 (Reasoning)
  250. 250 gpt-oss-20b (low)
  251. 251 Llama 4 Maverick
  252. 252 GPT-5 mini (minimal)
  253. 253 Qwen3 VL 235B A22B Instruct
  254. 254 NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
  255. 255 DeepSeek V3 (Dec '24)
  256. 256 Solar Pro 3
  257. 257 Ling 2.6 Flash
  258. 258 Gemini 2.5 Flash (Non-reasoning)
  259. 259 Qwen3 Next 80B A3B Instruct
  260. 260 Qwen3 Coder 30B A3B Instruct
  261. 261 Qwen3 235B A22B (Reasoning)
  262. 262 QwQ 32B
  263. 263 Qwen3 VL 30B A3B (Reasoning)
  264. 264 Gemma 4 12B (Non-reasoning)
  265. 265 Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)
  266. 266 Nova Premier
  267. 267 Mistral Medium 3
  268. 268 Mistral Small 4 (Non-reasoning)
  269. 269 Llama Nemotron Super 49B v1.5 (Reasoning)
  270. 270 Gemma 4 E4B (Reasoning)
  271. 271 Sarvam 105B (high)
  272. 272 Nova 2.0 Lite (Non-reasoning)
  273. 273 Celeris-1
  274. 274 Claude 3 Opus
  275. 275 Qwen3 32B (Reasoning)
  276. 276 Gemini 2.5 Flash-Lite (Reasoning)
  277. 277 Magistral Small 1.2
  278. 278 GPT-4o (Nov '24)
  279. 279 Ministral 3 14B
  280. 280 Qwen3 VL 32B Instruct
  281. 281 GLM-4.6V (Non-reasoning)
  282. 282 Qwen3 235B A22B (Non-reasoning)
  283. 283 Mistral Small 3.2
  284. 284 Qwen3 VL 8B (Reasoning)
  285. 285 Nova 2.0 Omni (Non-reasoning)
  286. 286 Qwen3 14B (Reasoning)
  287. 287 Llama 4 Scout
  288. 288 Hermes 4 - Llama-3.1 70B (Reasoning)
  289. 289 Qwen3 VL 30B A3B Instruct
  290. 290 Claude 3.5 Sonnet (Oct '24)
  291. 291 DeepSeek R1 Distill Llama 70B
  292. 292 Ling-flash-2.0
  293. 293 Qwen3 Omni 30B A3B (Reasoning)
  294. 294 GPT-4o (Aug '24)
  295. 295 GPT-4.1 nano
  296. 296 Qwen2.5 Instruct 72B
  297. 297 Llama 3.3 Instruct 70B
  298. 298 Qwen3 30B A3B (Reasoning)
  299. 299 Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)
  300. 300 GLM-4.5V (Reasoning)
  301. 301 Qwen3 30B A3B 2507 Instruct
  302. 302 Ministral 3 8B
  303. 303 NVIDIA Nemotron Nano 12B v2 VL (Reasoning)
  304. 304 Hermes 4 - Llama-3.1 405B (Reasoning)
  305. 305 ERNIE 4.5 300B A47B
  306. 306 Gemma 4 E4B (Non-reasoning)
  307. 307 NVIDIA Nemotron Nano 9B V2 (Reasoning)
  308. 308 Hermes 4 - Llama-3.1 405B (Non-reasoning)
  309. 309 Llama Nemotron Super 49B v1.5 (Non-reasoning)
  310. 310 GPT-4o (May '24)
  311. 311 Qwen3 32B (Non-reasoning)
  312. 312 Llama 3.1 Instruct 405B
  313. 313 Qwen3 VL 8B Instruct
  314. 314 Claude 3.5 Sonnet (June '24)
  315. 315 Qwen3 8B (Reasoning)
  316. 316 Ring-flash-2.0
  317. 317 GPT-5 nano (minimal)
  318. 318 GPT-4 Turbo
  319. 319 Command A
  320. 320 Nova Pro
  321. 321 Llama 3.1 Nemotron Instruct 70B
  322. 322 Llama 3.1 Instruct 8B
  323. 323 NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
  324. 324 NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
  325. 325 Mistral Large 2 (Jul '24)
  326. 326 GPT-4
  327. 327 GLM-4.5V (Non-reasoning)
  328. 328 Qwen3 14B (Non-reasoning)
  329. 329 Hermes 4 - Llama-3.1 70B (Non-reasoning)
  330. 330 GPT-4o mini
  331. 331 Gemini 2.5 Flash-Lite (Non-reasoning)
  332. 332 Mistral Small 3
  333. 333 Nova Lite
  334. 334 Ministral 3 3B
  335. 335 Llama 3.1 Instruct 70B
  336. 336 Qwen3 30B A3B (Non-reasoning)
  337. 337 Granite 4.1 8B
  338. 338 Sarvam 30B (high)
  339. 339 Reka Flash (Sep '24)
  340. 340 Qwen2.5 Turbo
  341. 341 Solar Mini
  342. 342 Jamba 1.7 Large
  343. 343 Granite 4.0 H Small
  344. 344 Qwen3 Omni 30B A3B Instruct
  345. 345 Hermes 3 - Llama-3.1 70B
  346. 346 Jamba 1.5 Large
  347. 347 Qwen3 8B (Non-reasoning)
  348. 348 Jamba 1.6 Large
  349. 349 Phi-4
  350. 350 Nova Micro
  351. 351 Claude 3 Sonnet
  352. 352 Mistral Small (Sep '24)
  353. 353 NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)
  354. 354 Mistral Large (Feb '24)
  355. 355 Llama 2 Chat 7B
  356. 356 Reka Flash 3
  357. 357 Claude 3 Haiku
  358. 358 GPT-3.5 Turbo
  359. 359 Mistral Small (Feb '24)
  360. 360 Mistral Medium
  361. 361 Llama 3 Instruct 70B
  362. 362 Llama 3.2 Instruct 11B (Vision)
  363. 363 Command-R+ (Apr '24)
  364. 364 Olmo 3 7B Instruct
  365. 365 Jamba 1.5 Mini
  366. 366 Jamba 1.6 Mini
  367. 367 Apertus 70B Instruct
  368. 368 Mixtral 8x7B Instruct
  369. 369 Mistral 7B Instruct
  370. 370 Command-R (Mar '24)
  371. 371 Granite 3.3 8B (Non-reasoning)
  372. 372 Llama 3 Instruct 8B
  373. 373 Gemma 3n E4B Instruct
  374. 374 Apertus 8B Instruct
  375. 375 Claude Sonnet 5 (Adaptive Reasoning, High Effort)
  376. 376 Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)
  377. 377 Claude Sonnet 5 (Adaptive Reasoning, Low Effort)
  378. 378 Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)
  379. 379 Cogito v2.1 (Reasoning)
  380. 380 GPT-5.4 Pro (xhigh)