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 Medium 3.5
Mistral Medium 3.5 is an open-weight model from Mistral AI, released Apr 30, 2026. It ranks #113 of 351 on the LMArena text leaderboard with a rating of 1421. It costs $1.50 per million input tokens and $7.50 per million output tokens, with a 256K-token context window.
- Developer
- Mistral AI
- Released
- Apr 30, 2026
- Context window
- 256K
- Price in / out, per 1M tokens
- $1.50 / $7.50
- Weights
- Open · Modified MIT
- Inputs
- Text, Images, Files
- Reasoning
- Yes
- Tool use
- Yes
The rating LMArena published at each update since Jun 3, 2026. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| SWE-benchCoding | 66.40% | 69 / 85 | $4.00 | |
| Vibe Code BenchCoding | 2.89% | 109 / 115 | $16.74 | |
| Tax Agent BenchFinance | 4.48% | 73 / 76 | $1.44 | |
| Legal Research BenchLaw | 9.13% | 78 / 85 | $1.31 | |
| MedCodeMedicine | 33.75% | 85 / 107 | $1.5 / $7.5 | |
| GPQA DiamondReasoning | 34.85% | 134 / 138 | $1.5 / $7.5 | |
| MMLU-ProReasoning | 75.33% | 111 / 138 | $1.5 / $7.5 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1421 | 113 / 351 | 11.8K |
| CodingLMArena | 1461 | 84 / 346 | 3.3K |
| MathLMArena | 1432 | 95 / 339 | 567 |
| Creative writingLMArena | 1374 | 141 / 349 | 2.1K |
| Instruction followingLMArena | 1415 | 97 / 351 | 3.8K |
| Hard promptsLMArena | 1436 | 101 / 351 | 7.7K |
| Multi-turnLMArena | 1423 | 113 / 349 | 1.9K |
| Long queriesLMArena | 1415 | 119 / 330 | 5.1K |
| ExpertLMArena | 1432 | 115 / 305 | 1.2K |
| Legal and governmentIndustries | 1437 | 97 / 325 | 889 |
| Medicine and healthcareIndustries | 1409 | 150 / 325 | 843 |
| Business and financeIndustries | 1426 | 90 / 344 | 2.3K |
| ChineseLanguages | 1444 | 138 / 328 | 616 |
| SpanishLanguages | 1411 | 132 / 249 | 389 |
| GermanLanguages | 1455 | 47 / 261 | 173 |
| FrenchLanguages | 1448 | 90 / 252 | 453 |
| WebDevLMArena | 1264 | 134 / 124 | 2.3K |
| VisionLMArena | 1223 | 83 / 146 | 5.4K |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown.
Compare Mistral Medium 3.5
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 Medium 3.5?
Mistral Medium 3.5 is made by Mistral AI, founded 2023 and based in Paris.
How much does Mistral Medium 3.5 cost?
$1.50 per million input tokens and $7.50 per million output tokens, at its provider’s list price.
What is Mistral Medium 3.5’s context window?
256K tokens (262,144).
How does Mistral Medium 3.5 rank?
#113 of 351 on LMArena’s text leaderboard, rated 1421 (95% interval 1414–1427) from 11,791 votes, as of Oct 22, 2026.
Is Mistral Medium 3.5 open source?
Mistral Medium 3.5 has open weights under the Modified MIT license.