fireredteam: firered-ocr
1 benchmarks
Leaderboard position
#795
Overall rank (of 1121 models)
474
Elo rating
1
Benchmarks
Top 70.9%
Percentile
In fireredteam (of 1 models)
Above: Prism ML: bonsai-8b #794
Below: Stability AI: stable-audio-2.0 #796
Benchmark highlights
Best benchmark
olmOCR-bench
70.2
Worst benchmark
olmOCR-bench
70.2
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 | ~79.78 | 50% | — |
| AIME 2025 | ~53.62 | 50% | — |
| AIME 2026 | ~66.14 | 50% | — |
| HMMT Feb 2026 | ~57.62 | 50% | — |
| GPQA Diamond | ~49.71 | 50% | — |
| MMLU-Pro | ~51.89 | 50% | — |
| Humanity's Last Exam (no tools) | ~4.87 | 50% | — |
| IFEval | ~77.08 | 50% | — |
| IFBench | ~47.04 | 50% | — |
| HumanEval | ~62.66 | 50% | — |
| MBPP | ~62.57 | 50% | — |
| Terminal-Bench v2.1 | ~8.6 | 50% | — |
| MMLU | ~57.87 | 50% | — |
| SWE-bench Verified | ~27.26 | 50% | — |
| SWE-bench Pro | ~7.01 | 50% | — |
| SciCode | ~20.98 | 50% | — |
| AA-LCR | ~35.66 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~12 | 50% | — |
| Humanity's Last Exam (with tools) | ~11.9 | 50% | — |
| GSM8K | ~68.51 | 50% | — |
| -(CoderPPL) | ~-3.28 | 50% | — |
| LiveCodeBench v6 | ~47.24 | 50% | — |
| MMMU-Pro | ~45.81 | 50% | — |
| MATH | ~44.79 | 50% | — |
| BBH | ~56.89 | 50% | — |