Mistral AIProvisional

Codestral

Codestral / Default · codestral-25-08

Automatically tracked from Mistral AI's official model catalog.

Objective score

15

Confidence

85%

Price evidence

$0.3 input / $0.9 output per 1M tokens

Support this model Compare trend Official source

Scenario evidence

Six task-specific rankings

Feature development#64Obj. 150 · 0%Debug and repair#65Obj. 15.50 · 0%Refactoring#66Obj. 14.90 · 0%Code review#64Obj. 19.70 · 0%Large-repo agent work#58Obj. 15.50 · 0%Frontend / UI#65Obj. 15.50 · 0%

Evidence state

Signal coverage

Benchmarks: 3
Rank points: 8
Usage: 2
Agent: 0
Sources: 2

Objective evidence

Benchmarks and public signals

Swebench: —
Livecodebench: —
Aider: 11.1
Artificial Analysis: 38.5
Openrouter Usage: 0
Kilo Usage: —

Persistent history

Recent ranking points

Aug 1#62 · 19

Aug 1#62 · 19

Aug 1#62 · 19

Jul 31#62 · 19

Jul 31#62 · 19

Jul 31#62 · 19

Usage signals

OpenRouter0%

Overall0%

Agent and tool signals

Evidence is being collected. Missing data is not treated as zero.

Source trail

Official Mistral AI model catalog Aider polyglot · ok Mistral model overview · ok