Amazon: nova-pro-v1
2 benchmarks
Leaderboard position
#780
Overall rank (of 1121 models)
506
Elo rating
2
Benchmarks
Top 69.6%
Percentile
In Amazon (of 8 models)
Above: Meta Llama: llama-3.1-70b-instruct #779
Below: Google: imagen-3-002 #781
Benchmark highlights
Nearest competitor from another company
The model from another company with the most similar benchmark scores.
appeared as nearest in 1 of 2 benchmarks
1/2
50.0%
1/2
50.0%
| Model | Votes | % of benchmarks |
|---|---|---|
| Cohere Labs: c4ai-command-a-03-2025 | 1 | 50.0% |
| Google: gemini-1.5-flash | 1 | 50.0% |
Benchmarks
Predicted scores
Estimated from 25 similar models and the global Elo rating. These are projections, not measured results.
| Benchmark | Predicted | Confidence | Based on |
|---|---|---|---|
| MATH-500 | ~80.34 | 50% | — |
| AIME 2025 | ~54.67 | 50% | — |
| AIME 2026 | ~66.76 | 50% | — |
| HMMT Feb 2026 | ~58.24 | 50% | — |
| GPQA Diamond | ~50.42 | 50% | — |
| MMLU-Pro | ~52.67 | 50% | — |
| Humanity's Last Exam (no tools) | ~5.44 | 50% | — |
| IFEval | ~77.51 | 50% | — |
| IFBench | ~47.57 | 50% | — |
| HumanEval | ~63.59 | 50% | — |
| MBPP | ~63.79 | 50% | — |
| Terminal-Bench v2.1 | ~9.43 | 50% | — |
| MMLU | ~58.69 | 50% | — |
| SWE-bench Verified | ~28.26 | 50% | — |
| SWE-bench Pro | ~7.94 | 50% | — |
| SciCode | ~21.48 | 50% | — |
| AA-LCR | ~36.29 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~12 | 50% | — |
| Humanity's Last Exam (with tools) | ~11.9 | 50% | — |
| GSM8K | ~69.72 | 50% | — |
| -(CoderPPL) | ~-3.08 | 50% | — |
| LiveCodeBench v6 | ~47.97 | 50% | — |
| MMMU-Pro | ~46.41 | 50% | — |
| MATH | ~46.14 | 50% | — |
| BBH | ~57.6 | 50% | — |