Mistral · model passport
Mistral Large 2402
mistral-large-2402- Cloud only
- Proprietary licence
- Released 2024-02-01(from model name)
- Overall · LMArena
- 1,243#303 of 396
- Best percentile
- 25.3Coding
- Cohort standing
- 30.1median 29.9
What the data says
Benchmarked on 7 of 27 tracked axes. Every figure below is the model's own published result on that board.
Weakest axes
- 8.5 pct — AIME (math) (1.9%)
Uneven: 16.8 percentile points between its best and worst axis — 25.3 pct on Coding versus 8.5 pct on AIME (math).
- Coding25.3 pct1,296Verify →
- Hard prompts25 pct1,263Verify →
- LiveBench24.7 pct38.9%Verify →
- Instruction following24 pct1,238Verify →
- Overall23.7 pct1,243Verify →
- GPQA Diamond19.9 pct38.8%Verify →
- AIME (math)8.5 pct1.9%Verify →
- WebDev ArenaNot benchmarked
- Vision ArenaNot benchmarked
- Factuality ArenaNot benchmarked
- Search ArenaNot benchmarked
- Document ArenaNot benchmarked
- Agent ArenaNot benchmarked
- FrontierMathNot benchmarked
- SimpleQA VerifiedNot benchmarked
- ARC-AGI-2Not benchmarked
- Humanity's Last ExamNot benchmarked
- SimpleBenchNot benchmarked
- BFCL v4 (function calling)Not benchmarked
- SWE-bench Verified (live board)Not benchmarked
- Terminal-Bench 4.0Not benchmarked
- MMLU-Pro (Artificial Analysis)Not benchmarked
- LiveCodeBench (Artificial Analysis)Not benchmarked
- IFBench (Artificial Analysis)Not benchmarked
- HHEM Hallucination (Vectara)Not benchmarked
- SWE-bench VerifiedNot benchmarked
- Terminal-BenchNot benchmarked
Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.
mistral-large-2402 stands at 30.1 (raw mean 21.6) — measured on 7 of 27 axes.
mistral-large-2402 stands at 30.1 versus a cohort median of 29.9 across 91 models released within 180 days — above the peer median.
mistral-large-2402 scores at percentile 8.5 on AIME (math).
mistral-large-2402 ranks between #291 and #979 across 5 built-in weightings — best under "Coding-focused", worst under "All sources".
Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →