Amazon: nova-micro-v1
2 benchmarks
Leaderboard position
#939
Overall rank (of 1121 models)
110
Elo rating
2
Benchmarks
Top 83.8%
Percentile
In Amazon (of 8 models)
Above: Anthropic: claude-2.0 #938
Below: Black Forest Labs: flux.2-klein-4b #940
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 |
|---|---|---|
| Anthropic: claude-3-sonnet | 1 | 50.0% |
| Microsoft: phi-3-mini-4k-instruct | 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 | ~73.47 | 50% | — |
| AIME 2025 | ~41.68 | 50% | — |
| AIME 2026 | ~59.1 | 50% | — |
| HMMT Feb 2026 | ~50.55 | 50% | — |
| GPQA Diamond | ~41.7 | 50% | — |
| MMLU-Pro | ~42.96 | 50% | — |
| Humanity's Last Exam (no tools) | ~4 | 50% | — |
| IFEval | ~72.1 | 50% | — |
| IFBench | ~41.01 | 50% | — |
| HumanEval | ~52.09 | 50% | — |
| MBPP | ~48.72 | 50% | — |
| Terminal-Bench v2.1 | ~8.6 | 50% | — |
| MMLU | ~48.49 | 50% | — |
| SWE-bench Verified | ~15.84 | 50% | — |
| SWE-bench Pro | ~5.24 | 50% | — |
| SciCode | ~15.29 | 50% | — |
| AA-LCR | ~28.55 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~12 | 50% | — |
| Humanity's Last Exam (with tools) | ~11.9 | 50% | — |
| GSM8K | ~54.82 | 50% | — |
| -(CoderPPL) | ~-5.53 | 50% | — |
| LiveCodeBench v6 | ~38.93 | 50% | — |
| MMMU-Pro | ~38.98 | 50% | — |
| MATH | ~29.52 | 50% | — |
| BBH | ~48.81 | 50% | — |