Skip to content
Model Pareto

Nemotron 3.5 Super VL

NVIDIAOpen weightshuggingface.co ↗
Compare with nearest rivalsCompare with…
Input
—
Output
—
Speed
~160tok/sest.
Context
1Mtokens
Price
—
Time
—

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs. No API sells this model, so this is its price on the chart.

Hardware
2× B200 180GB
FP8 weights
Throughput
~12,551 tok/s
many requests batched
Price
$0.11–0.96 /M tok
busy → light use
On your own machine
Mac Studio M5 Max 128GB (int4, ~72 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • FP8 weights (120B params, 12B active per token) + 40% KV-cache headroom ≈ 168 GB
  • 2× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~12,551 output tok/s aggregate at batch 359 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~177,188 tok/s
  • Low = 75% utilization at the low GPU price; high = 20% at the high price

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

Writing & chat

MMMLUEstimated
~#3 of 5 (estimated)~87.9%
  1. #1Gemini 3.1 Pro92.6%
  2. #2Gemma 4 31B88.4%
  3. ~#3Nemotron 3.5 Super VLEstimated87.9%
  4. #3Claude Haiku 4.583.0%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#36 of 57 (estimated)~1413 Elo
  1. #1Gemini 4 ArgonFew votes1512
  2. #2Claude Opus 5.51497
  3. #35Muse GlimmerFew votes1418
  4. ~#36Nemotron 3.5 Super VLEstimated1413
  5. #36MiMo-V2.51411
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#36 of 57 (estimated)~1428 Elo
  1. #1Gemini 4 Argon1525
  2. #2Claude Opus 5.51507
  3. #35MiMo-V2.51434
  4. ~#36Nemotron 3.5 Super VLEstimated1428
  5. #36Mistral Medium 3.51426
No published score — estimated from related benchmarks

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2Nemotron 3.5 Super VLEstimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
MMMU-ProEstimated
~#46 of 88 (estimated)~71.9%
  1. #1Claude Opus 5.587.7%
  2. #2GPT-6 Astra86.9%
  3. #45GPT-5.4 mini73.3%
  4. ~#46Nemotron 3.5 Super VLEstimated71.9%
  5. #46Qwen3.5 Omni Plus70.5%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#4 of 8 (estimated)~85.4%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #2Qwen3.8 27B91.1%
  4. ~#4Nemotron 3.5 Super VLEstimated85.4%
  5. #4Gemini 3.1 Pro85.3%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#25 of 47 (estimated)~14.5%
  1. #1Muse Wonder Full32.6%
  2. #2GPT-6 Astra31.0%
  3. #24Step 5 Preview14.8%
  4. ~#25Nemotron 3.5 Super VLEstimated14.5%
  5. #25Gemini 3.5 Flash-Lite13.6%
No published score — estimated from related benchmarks
ChartographyEstimated
~#15 of 24 (estimated)~22.8%
  1. #1GPT-6 Astra71.0%
  2. #2Claude Opus 5.566.3%
  3. #14Gemini 3.1 Pro26.1%
  4. ~#15Nemotron 3.5 Super VLEstimated22.8%
  5. #15Grok 4.620.5%
No published score — estimated from related benchmarks

Hard reasoning

AIME (latest)Estimated
~#5 of 33 (estimated)~94.8%
  1. #1GLM-5.3 NVFP499.5%
  2. #2Beam 1.0 501B A23B97.7%
  3. #4Ternary Bonsai 2 27B95.8%
  4. ~#5Nemotron 3.5 Super VLEstimated94.8%
  5. #5Muse Glimmer94.7%
No published score — estimated from related benchmarks

Agents

OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. #4GPT-5.547.5%
  4. ~#5Nemotron 3.5 Super VLEstimated<47.5%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#28 of 91 (estimated)~1417 Elo
  1. #1Claude Opus 5.51866
  2. #2Muse Wonder Full1857
  3. #27Qwen3.8 27B1419
  4. ~#28Nemotron 3.5 Super VLEstimated1417
  5. #28K2 Horizon 375B A23B1361
No published score — estimated from related benchmarks
AutomationBench-AAEstimated
~#33 of 84 (estimated)~26.9%
  1. #1Muse Wonder Full71.3%
  2. #2Claude Opus 5.569.5%
  3. #32Apodex 1.128.2%
  4. ~#33Nemotron 3.5 Super VLEstimated26.9%
  5. #33GPT-5.4 mini26.2%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#32 of 91 (estimated)~22.9%
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. #31Hy322.9%
  4. ~#32Nemotron 3.5 Super VLEstimated22.9%
  5. #32K2-Horizon-32B22.5%
No published score — estimated from related benchmarks