codestral-2508 — benchmark results

Provider: Mistral. Released 2025-08-01. Access: API.

Unified ELO 1532 ± 54, rank #747 of 1839 rated models, from 12 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AI Chess Leaderboard (Reasoning)854Elo74.2
Guesswork0.99MAE (z-score units)67.6
Wolfram LLM Benchmarking Project37.8Correct Functionality (%)43.4
LM Market Cap LMC Score40LMC Score (0-100)28.6
Design Arena (UI Components)1052Elo18
Design Arena (Website)1036Elo15.6
Design Arena (3D)1076Elo15.4
Design Arena (Data Viz)1047Elo14.7
Kagi LLM Benchmark32.5Accuracy (%)12
Design Arena (Game Dev)1018Elo11.2
LisanBench0Mean Path Length / Current Maximum7.8
ALE-Bench137.78Performance (Self-Refine x1) (self-reported)0

Interactive version: theaggregate.ai/model?slug=codestral-2508 · How It Works · Data refreshed daily, snapshot 2026-08-05.