Leaderboard
Language ModelsOpen weights
Mistral Large 3
Mistral's open-weights MoE flagship (41B active, Apache-2.0); a non-reasoning model.
Crosshair Index
47.4
#29 of 32 · Language Models
- Provider
- Mistral AI
- Released
- 2025-12-02
- Parameters
- 675B
- Context
- 256K tokens
Token pricing
- Input
- $0.5 /1M
- Output
- $1.5 /1M
USD per 1M tokens · cache read = cached input (hit), cache write = caching surcharge · official list pricing (June 2026).
Industry skill web
Professional-domain strengths, composed from the benchmarks relevant to each field. Highlight an axis to see the benchmarks behind it.
Corporate Law
79
skill
Legal reasoning — issue spotting, rule application, and contract analysis — plus the broad knowledge a generalist counsel needs.
Scorecard
| Benchmark | Score | Source | Status |
|---|---|---|---|
| GPQA Diamond Reasoning | 43.9% | Artificial Analysis — Mistral Large 33rd-party | unverified |
| Humanity's Last Exam Frontier | — | not evaluated | |
| SWE-bench Verified Agentic Coding | — | not evaluated | |
| LiveCodeBench Coding | — | not evaluated | |
| MMLU-Pro Knowledge | — | not evaluated | |
| LMArena Elo Human Preference | 1,418 | LMArena (arena.ai)3rd-party | unverified |
| AA Intelligence Index Composite | 23 | Artificial Analysis3rd-party | unverified |
| Corporate Finance Finance | 61% | Vals AI — CorpFin v23rd-party | unverified |
| LegalBench Law | 79.1% | Vals AI — LegalBench3rd-party | unverified |
| TaxEval Tax & Accounting | 73.1% | Vals AI — TaxEval v23rd-party | unverified |
| Medical Coding Medicine | — | not evaluated |