llmrun

Mistral Small 4 119B 2603 — Benchmarks

Benchmark scores for Mistral Small 4 119B 2603 aggregated from public leaderboards (3 boards), with how it ranks among open models and how it compares with its nearest neighbours. See hardware requirements for what you need to run it.

No llmrun Composite Score for Mistral Small 4 119B 2603: the score is only published for a model measured on at least 4 of the boards in the score panel, spanning at least 2 benchmark categories and including a reasoning or coding board — or on 3 boards that narrow its score to a 90% range of at most 15.6 points. Either way the results must come from at least two different benchmarks. Its individual scores below stand on their own — see how the llmrun Composite Score gets calculated.

Mistral Small 4 119B 2603 reasoning benchmarks

Multi-step logic and problem-solving — can the model think through a hard problem rather than recall an answer.

  • DTBench

    70.9%

    median 69.3%open leader 93.9%

    Overall best: Claude Fable 5.2 (unspecified) 99.2%

    51st percentile · #35 of 71 open · #165 of 241 all

    Lab-reported

    Epoch AI ·

  • LMCA

    20.6%

    median 26.1%open leader 57.6%

    Overall best: Claude Fable 5.2 (xhigh) 70.6%

    38th percentile · #36 of 57 open · #167 of 203 all

    Lab-reported

    Epoch AI ·

Mistral Small 4 119B 2603 coding benchmarks

Writing, editing, and fixing real code — measured by whether the resulting program actually runs and passes tests.

  • ALE-Bench

    497.6

    median 745.2open leader 1932.8

    Overall best: GPT 6 Astra Max 2951.3

    24th percentile · #39 of 51 open · #116 of 138 all

    Lab-reported

    Epoch AI ·

Scores aggregated from public benchmark sources (Epoch AI: 3 boards) — each linked from the benchmark pages. llmrun does not run these benchmarks. Percentiles and ranks are among open models in the llmrun catalogue; the median and leader marks refer to the same field.