Amazon: nova-micro-v1
2 benchmarks
Leaderboard position
#938
Overall rank (of 1122 models)
108
Elo rating
2
Benchmarks
Top 83.6%
Percentile
In Amazon (of 8 models)
Above: vita: freeze-omni #937
Below: LiquidAI: lfm-2-24b-a2b #939
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 | ~73.48 | 50% | — |
| AIME 2025 | ~41.65 | 50% | — |
| AIME 2026 | ~59.1 | 50% | — |
| HMMT Feb 2026 | ~50.54 | 50% | — |
| GPQA Diamond | ~41.71 | 50% | — |
| MMLU-Pro | ~42.97 | 50% | — |
| Humanity's Last Exam (no tools) | ~4 | 50% | — |
| IFEval | ~72.11 | 50% | — |
| IFBench | ~41.03 | 50% | — |
| HumanEval | ~52.11 | 50% | — |
| MBPP | ~48.74 | 50% | — |
| Terminal-Bench v2.1 | ~8.6 | 50% | — |
| MMLU | ~48.5 | 50% | — |
| SWE-bench Verified | ~16.02 | 50% | — |
| SWE-bench Pro | ~5.24 | 50% | — |
| SciCode | ~15.26 | 50% | — |
| AA-LCR | ~28.56 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~12 | 50% | — |
| Humanity's Last Exam (with tools) | ~11.9 | 50% | — |
| GSM8K | ~54.84 | 50% | — |
| -(CoderPPL) | ~-5.53 | 50% | — |
| LiveCodeBench v6 | ~38.94 | 50% | — |
| MMMU-Pro | ~39.07 | 50% | — |
| MATH | ~29.54 | 50% | — |
| BBH | ~48.82 | 50% | — |