Skip to main content

Includes 694 hourly rounds up to 2026-11-16 from NIMStats by Mauro Druwel (source), measured with a different prompt and timeout. Our own probe adds a round every 30 minutes.

nvidia

nemotron-3.5-super-vl-120b-a12b

Serving

Rank 2 of 15 Last probed (22 min ago)

nvidia/nemotron-3.5-super-vl-120b-a12b answered 100% of probes on the NVIDIA NIM free API in the last 7 days, with a median time to first token of 343 ms and 126 tok/s. It ranks 2 of 15 tracked models.

100% Uptime 15/15 probes
93/ 100 Score 2 round wins
343 ms First token p95 1.34 s
2.00 s Full reply median
957 ms Best reply fastest in range
126tok/s Throughput median

Model vs. median

Against the median of models that answered, last 7 days.

Uptime
100% 74.7%
25 pts above median
First token
343 ms 14.8 s
43× better than median
Full reply
2.00 s 22.6 s
11× better than median
Throughput
126 tok/s 22.3 tok/s
5.6× better than median

nemotron-3.5-super-vl-120b-a12b median of answering models

Error breakdown

0 failed of 15 probes, last 7 days.

No failed probes in this range.

Time to first token

Each probe. Lower is better.

0 ms500 ms1.00 s1.50 s2.00 s11-15 22:4411-17 16:13 UTC
answered no answer

Throughput

Tokens per second after the first token, each probe. Higher is better.

0.0 tok/s125 tok/s250 tok/s375 tok/s500 tok/s11-15 22:4411-17 16:13 UTC
answered no answer

Availability heatmap

Last 7 days by UTC hour.

all answered some failed none answered not probed

Run history

Last 20 probes.

TimeResultFirst tokenFull replySpeed
OK799 ms2.51 s117 tok/s
OK562 ms2.47 s105 tok/s
OK455 ms1.84 s144 tok/s
OK393 ms1.99 s126 tok/s
OK304 ms1.60 s154 tok/s
OK322 ms2.80 s80.7 tok/s
OK380 ms2.00 s124 tok/s
OK343 ms2.00 s121 tok/s
OK317 ms1.67 s148 tok/s
OK318 ms1.91 s126 tok/s
OK334 ms1.60 s158 tok/s
OK295 ms957 ms302 tok/s
OK1.34 s2.46 s178 tok/s
OK358 ms2.48 s94.3 tok/s
OK337 ms2.16 s110 tok/s

Call nemotron-3.5-super-vl-120b-a12b

The endpoint is OpenAI-compatible.

Create a free key at build.nvidia.com, then:

curl https://integrate.api.nvidia.com/v1/chat/completions \
  -H "Authorization: Bearer $NVIDIA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3.5-super-vl-120b-a12b",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 256,
    "stream": true
  }'

Other models answering

Top of the leaderboard right now.