fal: flux.2-dev-flash
1 benchmarks
Leaderboard position
#564
Overall rank (of 1121 models)
962
Elo rating
1
Benchmarks
Top 50.3%
Percentile
In fal (of 2 models)
Above: Mistral AI: voxtral-small-24b-2507 #563
Below: jaredpalmer: kev-9b #565
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 | ~88.25 | 50% | — |
| AIME 2025 | ~69.63 | 50% | — |
| AIME 2026 | ~75.58 | 50% | — |
| HMMT Feb 2026 | ~67.09 | 50% | — |
| GPQA Diamond | ~60.45 | 50% | — |
| MMLU-Pro | ~63.86 | 50% | — |
| Humanity's Last Exam (no tools) | ~13.55 | 50% | — |
| IFEval | ~83.75 | 50% | — |
| IFBench | ~55.12 | 50% | — |
| HumanEval | ~76.83 | 50% | — |
| MBPP | ~81.13 | 50% | — |
| Terminal-Bench v2.1 | ~25.23 | 50% | — |
| MMLU | ~70.45 | 50% | — |
| SWE-bench Verified | ~42.57 | 50% | — |
| SWE-bench Pro | ~21.28 | 50% | — |
| SciCode | ~28.6 | 50% | — |
| AA-LCR | ~45.2 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~12 | 50% | — |
| Humanity's Last Exam (with tools) | ~18.41 | 50% | — |
| GSM8K | ~86.87 | 50% | — |
| -(CoderPPL) | ~-1.69 | 50% | — |
| LiveCodeBench v6 | ~58.39 | 50% | — |
| MMMU-Pro | ~54.97 | 50% | — |
| MATH | ~65.28 | 50% | — |
| BBH | ~67.72 | 50% | — |