Magistral Small 2509 — Benchmarks
Benchmark scores for Magistral Small 2509 aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Overall rank: #66 of 78 open modelscomposite 26.6/100 across 6 benchmarks in 3 categories · methodology
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| SciCode | 35.2% | #43 / 62 | #137 / 161 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| AIME 2024/2025 | 28.1% | #49 / 82 | #206 / 270 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| Chess Puzzles | 3.0% | #38 / 65 | #171 / 205 |
| DTBench | 61.3% | #43 / 67 | #163 / 210 |
| GPQA Diamond | 47.6% | #56 / 94 | #224 / 289 |
| CritPt | 0.3% | #38 / 62 | #129 / 172 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.