Gemini 4 Argon
Claude Opus 5.5
Muse Wonder
MiMo-V2.6-Pro
Qwen3.8-Max
Kimi K3
GLM-5.3
GPT-5.5
ERNIE 5.1
DeepSeek-V4.1-Flash-20260910
Grok 4.20 Beta
amazon-nova-experimental-chat
Dola Seed 2.0 Pro
NVIDIA-Nemotron-3-Ultra-550B-A55B
Gemma 4 31B
Step 5 Preview
Mistral Large
Mistral Large is an open-weight model from Mistral AI, released Dec 1, 2025. It ranks #286 of 351 on the LMArena text leaderboard with a rating of 1265. It costs $0.50 per million input tokens and $1.50 per million output tokens, with a 256K-token context window.
- Developer
- Mistral AI
- Released
- Dec 1, 2025
- Context window
- 256K
- Price in / out, per 1M tokens
- $0.50 / $1.50
- Weights
- Open · MRL
- Inputs
- Text, Images, Files
- Reasoning
- No
- Tool use
- Yes
The rating LMArena published at each update since Mar 5, 2024. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| SWE-benchCoding | 41.40% | 83 / 85 | $0.32 | |
| LiveCodeBenchCoding | 37.09% | 133 / 143 | $2 / $6 | |
| MedQAMedicine | 76.22% | 76 / 92 | $2 / $6 | |
| GPQA DiamondReasoning | 47.73% | 126 / 138 | $2 / $6 | |
| MMLU-ProReasoning | 69.71% | 122 / 138 | $2 / $6 | |
| AIMEReasoning | 9.17% | 91 / 96 | $2 / $6 | |
| MMMUReasoning | 66.19% | 74 / 93 | $0.5 / $1.5 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1265 | 286 / 351 | 28.1K |
| CodingLMArena | 1275 | 279 / 346 | 4.2K |
| MathLMArena | 1261 | 276 / 339 | 3.6K |
| Creative writingLMArena | 1242 | 278 / 349 | 4.4K |
| Instruction followingLMArena | 1249 | 279 / 351 | 11K |
| Hard promptsLMArena | 1257 | 281 / 351 | 7K |
| Multi-turnLMArena | 1260 | 284 / 349 | 4.4K |
| Long queriesLMArena | 1261 | 280 / 330 | 3.6K |
| ExpertLMArena | 1208 | 287 / 305 | 1.5K |
| Legal and governmentIndustries | 1275 | 277 / 325 | 1.6K |
| Medicine and healthcareIndustries | 1255 | 276 / 325 | 1.2K |
| Business and financeIndustries | 1238 | 282 / 344 | 3K |
| ChineseLanguages | 1239 | 284 / 328 | 1.9K |
| SpanishLanguages | 1268 | 235 / 249 | 153 |
| GermanLanguages | 1242 | 240 / 261 | 648 |
| FrenchLanguages | 1325 | 208 / 252 | 204 |
| JapaneseLanguages | 1170 | 227 / 236 | 629 |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown (Mistral Large (2411), Mistral Large (2402)).
Compare Mistral Large
Mistral AI
Europe’s leading model lab, with efficient open and commercial models and EU hosting. Founded 2023, based in Paris. mistral.ai
Questions
Who makes Mistral Large?
Mistral Large is made by Mistral AI, founded 2023 and based in Paris.
How much does Mistral Large cost?
$0.50 per million input tokens and $1.50 per million output tokens, at its provider’s list price.
What is Mistral Large’s context window?
256K tokens (262,144).
How does Mistral Large rank?
#286 of 351 on LMArena’s text leaderboard, rated 1265 (95% interval 1261–1270) from 28,073 votes, as of Oct 22, 2026.
Is Mistral Large open source?
Mistral Large has open weights under the MRL license.