Skip to content
Model Pareto

Nova 2.0 Pro Preview

Amazon NovaProprietaryartificialanalysis.ai ↗
Compare with nearest rivalsCompare with…
Input
$1.25/M tok
Output
$10/M tok
Blended
$3.438/M tok · 3:1
Speed
120tok/s
Context
256Ktokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: Nova 2.0 Pro Preview (medium). Price = AA median host price.

Rankings

Benchmark scores

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

Writing & chat

MMMLUEstimated
~#3 of 5 (estimated)~88.4%
  1. #1Gemini 3.1 Pro92.6%
  2. #2Gemma 4 31B88.4%
  3. ~#3Nova 2.0 Pro PreviewEstimated88.4%
  4. #3Claude Haiku 4.583.0%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#33 of 54 (estimated)~1416 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #32Muse GlimmerFew votes1418
  4. ~#33Nova 2.0 Pro PreviewEstimated1416
  5. #33MiMo-V2.51411
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#33 of 54 (estimated)~1430 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #32MiMo-V2.51434
  4. ~#33Nova 2.0 Pro PreviewEstimated1430
  5. #33Mistral 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. ~#2Nova 2.0 Pro PreviewEstimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
CharXiv ReasoningEstimated
~#8 of 9 (estimated)~76.1%
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #7Claude Sonnet 577.0%
  4. ~#8Nova 2.0 Pro PreviewEstimated76.1%
  5. #8Gemini 3.5 Flash-Lite74.5%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#5 of 8 (estimated)~82.9%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #4Gemini 3.1 Pro85.3%
  4. ~#5Nova 2.0 Pro PreviewEstimated82.9%
  5. #5Claude Haiku 4.579.6%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#28 of 43 (estimated)~10.5%
  1. #1GPT-6 Astra31.0%
  2. #2Muse Spark 1.326.6%
  3. #26Qwen3.7 Plus12.2%
  4. ~#28Nova 2.0 Pro PreviewEstimated10.5%
  5. #28Muse Glimmer10.0%
No published score — estimated from related benchmarks
ChartographyEstimated
~#19 of 23 (estimated)~12.6%
  1. #1GPT-6 Astra71.0%
  2. #2Claude Opus 5.566.3%
  3. #18Grok 4.714.7%
  4. ~#19Nova 2.0 Pro PreviewEstimated12.6%
  5. #19DeepSeek V4.1 Flash11.6%
No published score — estimated from related benchmarks

Hard reasoning

Agents

OSWorld-VerifiedEstimated
~#9 of 12 (estimated)~71.3%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #8Gemini 3.5 Flash-Lite74.0%
  4. ~#9Nova 2.0 Pro PreviewEstimated71.3%
  5. #9Nex-N2.5-Mini71.2%
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. ~#5Nova 2.0 Pro PreviewEstimated<47.5%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#15 of 18 (estimated)~71.1%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #14Inkling77.1%
  4. ~#15Nova 2.0 Pro PreviewEstimated71.1%
  5. #15Mistral Medium 3.548.6%
No published score — estimated from related benchmarks
AutomationBench-AAEstimated
~#36 of 80 (estimated)~19.9%
  1. #1Claude Opus 5.569.5%
  2. #2DeepSeek V4.1 Flash68.9%
  3. #35K2 Horizon 7B20.9%
  4. ~#36Nova 2.0 Pro PreviewEstimated19.9%
  5. #36Hy318.4%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#40 of 89 (estimated)~18.8%
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. #39Inkling Small18.8%
  4. ~#40Nova 2.0 Pro PreviewEstimated18.8%
  5. #40Ring-2.6-1T17.9%
No published score — estimated from related benchmarks