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

BenchmarkScoreOpen rankAll models
SciCode35.2%#43 / 62#137 / 161

Math

BenchmarkScoreOpen rankAll models
AIME 2024/202528.1%#49 / 82#206 / 270

Reasoning

BenchmarkScoreOpen rankAll models
Chess Puzzles3.0%#38 / 65#171 / 205
DTBench61.3%#43 / 67#163 / 210
GPQA Diamond47.6%#56 / 94#224 / 289
CritPt0.3%#38 / 62#129 / 172

Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.