evals.report
BenchmarksLabsCompareRun guidesIn the wild
Mistral AIMistral

Mistral Large

Mistral AI · Mistral. Released Feb 26, 2024.

Mistral Large is a model from Mistral AI in the Mistral family, released Feb 26, 2024. evals.report tracks 18 reported Mistral Large benchmark scores across Berkeley Function Calling Leaderboard, GPQA Diamond, AIME (OTIS Mock), LMArena, Epoch Capabilities Index, MMLU-Pro, GDPval, LiveCodeBench, and 10 more — each shown with its benchmark, metric, source status, and date, and never combined into a single ranking.

18 results

Benchmark results 18

Compare this model
BenchmarkCategoryScoreMetricStatusDate
Berkeley Function Calling LeaderboardTool use38.37%accuracyOfficialFeb 26, 2024Details
GPQA DiamondReasoning38.8%accuracyOfficialFeb 26, 2024Details
AIME (OTIS Mock)Reasoning1.9%accuracyOfficialFeb 26, 2024Details
LMArenaChat preference1265source-defined ratingOfficialFeb 26, 2024Details
Epoch Capabilities IndexReasoning121.0IndexOfficialFeb 26, 2024Details
MMLU-ProReasoning69.7%accuracyVerifiedFeb 26, 2024Details
GDPvalAgents864EloOfficialFeb 26, 2024Details
LiveCodeBenchCoding17.8%Pass@1UnverifiedFeb 26, 2024Details
SciCodeCoding20.8%accuracyUnverifiedFeb 26, 2024Details
LongBench v2Reasoning39.6%accuracyOfficialFeb 26, 2024Details
Global-MMLUReasoning80.3%accuracyUnverifiedFeb 26, 2024Details
WebDev ArenaChat preference1223EloVerifiedFeb 26, 2024Details
EQ-Bench Creative Writing v3Chat preference1402EloVerifiedFeb 26, 2024Details
AILuminate AI Safety BenchmarkOtherGoodSafety gradeVerifiedFeb 26, 2024Details
MASK (Model Alignment between Statements and Knowledge)Other47.53Honesty scoreVerifiedFeb 26, 2024Details
BigCodeBenchCoding29.7%calibrated Pass@1VerifiedFeb 26, 2024Details
SuperGPQAReasoning40.65%accuracyVerifiedFeb 26, 2024Details
Vectara Hallucination LeaderboardOther4.5%Hallucination RateOfficialFeb 26, 2024Details