This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement here....
Tested on 14 benchmarks · BenchGecko score 31.3. Top scores: HELM — IFEval (87.6%), HELM — WildBench (80.1%), Lech Mazur Writing (69.0%).
Llama 3.1 8B Instruct scores 30.7 (98% as good) at $0.02/1M input · 99% cheaper
Code editing benchmark from the Aider project. Measures ability to apply targeted code changes while maintaining correctness and style.
Stanford HELM WildBench evaluation. Tests reasoning on challenging real-world tasks.
Deceptively simple questions that humans find easy but AI models often get wrong. Tests common sense and reasoning gaps.
Stanford HELM evaluation of mathematical reasoning across diverse problem types.
Competition-level math from AMC, AIME, and olympiad problems. Level 5 is the hardest tier, requiring creative problem-solving.
Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.
- Typetext
- Context128K tokens (~64 books)
- ReleasedFeb 2024
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.010
Frequently Asked Questions
Key facts · as of 2026-10-05
- Mistral Large by Mistral AI. BenchGecko score 31.3, rank 240 of 312 scored models (normalized average of public benchmark scores).
- List price $2.00 input · $6.00 output per 1M tokens (as of 2026-10-05).
- Sold by 2 providers (as of 2026-10-05): Mistral $2.00 in / $6.00 out · Mistral $2.20 in / $6.60 out. Every provider
How to cite · data as of 2026-10-05
Mistral Large · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/mistral-large
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP