Skip to content
Model Pareto

Nemotron Cascade 2 30B A3B

NVIDIAOpen weightsartificialanalysis.ai ↗
Compare with nearest rivalsCompare with…
Input
—
Output
—
Speed
~210tok/sest.
Context
1Mtokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: Nemotron Cascade 2 30B A3B. Price = AA median host price.

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
1× H200 141GB
FP8 weights
Throughput
~8,799 tok/s
many requests batched
Price
$0.044–0.37 /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 (30B params, 3B active per token) + 40% KV-cache headroom ≈ 42 GB
  • 1× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
  • ~8,799 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

MMMLUEstimated
~#3 of 5 (estimated)~86.6%
  1. #1Gemini 3.1 Pro92.6%
  2. #2Gemma 4 31B88.4%
  3. ~#3Nemotron Cascade 2 30B A3BEstimated86.6%
  4. #3Claude Haiku 4.583.0%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#39 of 54 (estimated)~1393 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #38Claude Haiku 4.51395
  4. ~#39Nemotron Cascade 2 30B A3BEstimated1393
  5. #39GPT-5.4 nano1387
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#39 of 54 (estimated)~1409 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #38Mistral Large 31413
  4. ~#39Nemotron Cascade 2 30B A3BEstimated1409
  5. #39GPT-5.4 nano1402
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#18 of 26 (estimated)~1632 Elo
  1. #1GPT-6 Astra2173
  2. #2Claude Fable 5.12162
  3. #17Qwen3.8 27B1671
  4. ~#18Nemotron Cascade 2 30B A3BEstimated1632
  5. #18Inkling1611
No published score — estimated from related benchmarks

Hard reasoning

AIME (latest)Estimated
~#14 of 25 (estimated)~73.5%
  1. #1Inkling97.1%
  2. #2Muse Glimmer94.7%
  3. #13Phi-4-reasoning-plus78.0%
  4. ~#14Nemotron Cascade 2 30B A3BEstimated73.5%
  5. #14Mistral Large 338.0%
No published score — estimated from related benchmarks

Agents

OSWorld-VerifiedEstimated
~#10 of 12 (estimated)~68.8%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #9Nex-N2.5-Mini71.2%
  4. ~#10Nemotron Cascade 2 30B A3BEstimated68.8%
  5. #10Muse Glimmer65.9%
No published score — estimated from related benchmarks
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 Cascade 2 30B A3BEstimated<47.5%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#15 of 18 (estimated)~55.3%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #14Inkling77.1%
  4. ~#15Nemotron Cascade 2 30B A3BEstimated55.3%
  5. #15Mistral Medium 3.548.6%
No published score — estimated from related benchmarks