api-airforce: image-1
1 benchmarks
Leaderboard position
#685
Overall rank (of 1121 models)
697
Elo rating
1
Benchmarks
Top 61.1%
Percentile
In api-airforce (of 1 models)
Above: LocoreMind: locooperator-4b #684
Below: DeepSeek: deepseek-ocr #686
Benchmark highlights
Nearest competitor from another company
The model from another company with the most similar benchmark scores.
appeared as nearest in 1 of 1 benchmarks
1/1
100.0%
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 | ~83.65 | 50% | — |
| AIME 2025 | ~60.94 | 50% | — |
| AIME 2026 | ~70.45 | 50% | — |
| HMMT Feb 2026 | ~61.95 | 50% | — |
| GPQA Diamond | ~54.62 | 50% | — |
| MMLU-Pro | ~57.36 | 50% | — |
| Humanity's Last Exam (no tools) | ~8.84 | 50% | — |
| IFEval | ~80.12 | 50% | — |
| IFBench | ~50.73 | 50% | — |
| HumanEval | ~69.14 | 50% | — |
| MBPP | ~71.05 | 50% | — |
| Terminal-Bench v2.1 | ~16.05 | 50% | — |
| MMLU | ~63.62 | 50% | — |
| SWE-bench Verified | ~34.25 | 50% | — |
| SWE-bench Pro | ~13.53 | 50% | — |
| SciCode | ~24.46 | 50% | — |
| AA-LCR | ~40.02 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~12 | 50% | — |
| Humanity's Last Exam (with tools) | ~12.11 | 50% | — |
| GSM8K | ~76.9 | 50% | — |
| -(CoderPPL) | ~-1.9 | 50% | — |
| LiveCodeBench v6 | ~52.33 | 50% | — |
| MMMU-Pro | ~50 | 50% | — |
| MATH | ~54.15 | 50% | — |
| BBH | ~61.84 | 50% | — |