- MMLU 87.4
- GPQA Diamond 57.1
- AIME 2025 16
- MATH-500 82
- BigCodeBench Hard 28.1
- MBXP (5 languages) 78.4
- IFEval 91.5
- MMMU 68
- OCRBench-v2 56.9
- CharXiv Reasoning (Descriptive 84.6) 48.8
- EgoSchema 73.8
- TallyQA 61.5
- SimpleQA (SerpAPI), retrieval-augmented 86.3
- BFCL (2025-04-25) 63.7
- Mean of ScreenSpot Web Text 91.7 / Web Icon 84.0 87.8
- SWE-Bench Verified (internal agentic scaffold) 42.4
Amazon Nova Premier
Amazon Nova Premier.
18
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Amazon Apr 2025 Amazon Nova Premier
Closed weights Flagship
No Epoch Capabilities Index score yet
- EgoSchema 73.8% #4 /12
- AIME 2025 16% #141 /143
- CharXiv 48.8% #64 /67
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GPQA Diamond | 57.1% | #216 of 284 | Model card | |
| MATH-500 | 82% | #60 of 67 | Model card | |
| AIME 2025 | 16% | #141 of 143 | Model card |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MBXP | 78.4% | #1 of 3 | Model card | |
| SWE-bench Verified | 42.4% | #38 of 60 | Official leaderboard | |
| BigCodeBench-Hard | 28.1% | #2 of 3 | Model card |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ScreenSpot | 87.8% | #6 of 11 | Model card | |
| Berkeley Function Calling Leaderboard (BFCL) | 63.7% | #39 of 47 | Model card |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| TallyQA | 61.5% | #1 of 4 | Model card | |
| MMMU | 68% | #40 of 136 | Official leaderboard | |
| EgoSchema | 73.8% | #4 of 12 | Model card | |
| OCRBench v2 | 56.9% | #17 of 20 | Model card | |
| CharXiv | 48.8% | #64 of 67 | Model card | |
| CharXiv (DQ) | 84.6% | #7 of 7 | Model card |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HELM Capabilities | 63.7 | #35 of 60 | Official leaderboard |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.
Its system card
Every result in the longer documents the lab published with it. 1 of them isn't in the launch post.
Capabilities
- MMLU 87.4
- GPQA Diamond 57.1
- AIME 2025 16
- MATH-500 82
- BigCodeBench-Hard 28.1
- MBXP 78.4
- IFEval 91.5
- MMMU 68
- OCRBench v2 56.9
- CharXiv 48.8
- CharXiv (DQ) 84.6
- EgoSchema 73.8
- TallyQA 61.5
- SimpleQA 86.3
- Berkeley Function Calling Leaderboard (BFCL) 63.7
- ScreenSpot
- SWE-bench Verified 42.4