Skip to content
Model Pareto

NVIDIA Nemotron Nano 12B v2 VL

NVIDIAOpen weightsartificialanalysis.ai ↗
Compare with nearest rivalsCompare with…
Input
$0.20/M tok
Output
$0.60/M tok
Blended
$0.30/M tok · 3:1
Speed
201tok/s
Context
128Ktokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: NVIDIA Nemotron Nano 12B v2 VL (Reasoning). Price = AA median host price.

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs, compared with the API price above.

Hardware
1× B200 180GB
BF16 weights
Throughput
~8,216 tok/s
many requests batched
Price
$0.11–0.95 /M tok
busy → light use
On your own machine
RTX 5090 32GB (int4, ~200 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • BF16 weights (12.6B params) + 25% KV-cache headroom ≈ 32 GB
  • 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~8,216 output tok/s aggregate at batch 235 (bandwidth-bound)
  • Blended 3:1 input:output; prefill ~42,188 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.

Writing & chat

MMMLUEstimated
~last of 5 (estimated)below measured range (<81.3%)
  1. #1Gemini 3.1 Pro92.6%
  2. #2Gemma 4 31B88.4%
  3. #4gpt-oss-120b81.3%
  4. ~#5NVIDIA Nemotron Nano 12B v2 VLEstimated<81.3%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#44 of 54 (estimated)~1331 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #43gpt-oss-120b1338
  4. ~#44NVIDIA Nemotron Nano 12B v2 VLEstimated1331
  5. #44INTELLECT-3Few votes1327
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#44 of 54 (estimated)~1353 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #43INTELLECT-31356
  4. ~#44NVIDIA Nemotron Nano 12B v2 VLEstimated1353
  5. #44gpt-oss-120b1352
No published score — estimated from related benchmarks

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2NVIDIA Nemotron Nano 12B v2 VLEstimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
CharXiv ReasoningEstimated
~last of 9 (estimated)below measured range (<74.5%)
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #8Gemini 3.5 Flash-Lite74.5%
  4. ~#9NVIDIA Nemotron Nano 12B v2 VLEstimated<74.5%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~last of 8 (estimated)below measured range (<75.8%)
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #7Muse Glimmer75.8%
  4. ~#8NVIDIA Nemotron Nano 12B v2 VLEstimated<75.8%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#40 of 43 (estimated)~1.0%
  1. #1GPT-6 Astra31.0%
  2. #2Muse Spark 1.326.6%
  3. #38Devstral Small 21.0%
  4. ~#40NVIDIA Nemotron Nano 12B v2 VLEstimated1.0%
  5. #40Ministral 3 8B0.8%
No published score — estimated from related benchmarks
ChartographyEstimated
~last of 23 (estimated)below measured range (<9.0%)
  1. #1GPT-6 Astra71.0%
  2. #2Claude Opus 5.566.3%
  3. #22Mistral Large 39.0%
  4. ~#23NVIDIA Nemotron Nano 12B v2 VLEstimated<9.0%
No published score — estimated from related benchmarks

Hard reasoning

Agents

OSWorld-VerifiedEstimated
~#11 of 12 (estimated)~64.8%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #10Muse Glimmer65.9%
  4. ~#11NVIDIA Nemotron Nano 12B v2 VLEstimated64.8%
  5. #11Claude Haiku 4.550.7%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~53.8%
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3NVIDIA Nemotron Nano 12B v2 VLEstimated53.8%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#55 of 87 (estimated)~702 Elo
  1. #1Claude Opus 5.51846
  2. #2Claude Fable 5.11735
  3. #54Claude Haiku 4.5719
  4. ~#55NVIDIA Nemotron Nano 12B v2 VLEstimated702
  5. #55MiniCPM5-2B694
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#72 of 89 (estimated)~6.2%
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. #71North Mini Code6.4%
  4. ~#72NVIDIA Nemotron Nano 12B v2 VLEstimated6.2%
  5. #72Command A+6.0%
No published score — estimated from related benchmarks