Codestral · Aider coding benchmarks · Polyglot · percent correct ↗
Mistral / MODEL EVIDENCE
Codestral
2 benchmarks · 4 observations · 2 sources · released 2025-01-13
Scores at a glance
2 benchmarks · large dot: Codestral; small dots: closest models where reported
Commit0 ↗6.34%
Codestral · Commit0 · Commit0 Lite · Stage 1 · unit-test pass rate · SDE-I ↗
2 more reported results
6.34% · Codestral · Commit0 · Commit0 Lite · Stage 2 · unit-test pass rate · SDE-I · Commit0: Library Generation from Scratch ↗
7.41% · Codestral · Commit0 · Commit0 Lite · Stage 3 · unit-test pass rate · SDE-I · Commit0: Library Generation from Scratch ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
There are not enough shared scored settings to identify close comparisons reliably.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
- Aider LLM Leaderboards — Polyglot coding benchmark ↗
- Commit0: Library Generation from Scratch — published result table ↗
All 7 authors
Zhao, Wenting, Jiang, Nan, Lee, Celine, Chiu, Justin T, Cardie, Claire, Gallé, Matthias, Rush, Alexander M
Names used in source tables
Codestral