Skip to content
Model Pareto

Nemotron 3 Nano Omni 30B A3B Reasoning

NVIDIAOpen weightsartificialanalysis.ai ↗
Compare with nearest rivalsCompare with…
Input
$0.195/M tok
Output
$1.095/M tok
Blended
$0.42/M tok · 3:1
Speed
275tok/s
Context
256Ktokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: Nemotron 3 Nano Omni 30B A3B 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× H200 141GB
FP8 weights
Throughput
~8,714 tok/s
many requests batched
Price
$0.045–0.37 /M tok
busy → light use
On your own machine
RTX 5090 32GB (int4, 300+ tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • FP8 weights (31B params, 3B active per token) + 25% KV-cache headroom ≈ 39 GB
  • 1× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
  • ~8,714 output tok/s aggregate at batch 256 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~155,846 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

LMArena Text, Non-English (Elo)Estimated
~#42 of 54 (estimated)~1359 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #41GLM-4.6VFew votes1361
  4. ~#42Nemotron 3 Nano Omni 30B A3B ReasoningEstimated1359
  5. #42Trinity Large Thinking1353
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#41 of 54 (estimated)~1378 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #40Qwen3 Next 80B A3B Instruct1399
  4. ~#41Nemotron 3 Nano Omni 30B A3B ReasoningEstimated1378
  5. #41GLM-4.6VFew votes1378
No published score — estimated from related benchmarks

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2Nemotron 3 Nano Omni 30B A3B ReasoningEstimated71.3%
  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. ~#9Nemotron 3 Nano Omni 30B A3B ReasoningEstimated<74.5%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#8 of 8 (estimated)~75.8%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #7Muse Glimmer75.8%
  4. ~#8Nemotron 3 Nano Omni 30B A3B ReasoningEstimated75.8%
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. ~#23Nemotron 3 Nano Omni 30B A3B ReasoningEstimated<9.0%
No published score — estimated from related benchmarks

Hard reasoning

AIME (latest)Estimated
~#16 of 25 (estimated)~35.0%
  1. #1Inkling97.1%
  2. #2Muse Glimmer94.7%
  3. #15Devstral 236.7%
  4. ~#16Nemotron 3 Nano Omni 30B A3B ReasoningEstimated35.0%
  5. #16Devstral Small 234.3%
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 Nano Omni 30B A3B ReasoningEstimated<47.5%
No published score — estimated from related benchmarks