Mistral · released Oct 6, 2026
Mistral Large 4
Mistral Large 4 is Mistral's October flagship and lags the leaders on most jobs.
3 weeks oldThinks before answering
- Input price
- $1.36 / M
- Output price
- $4.18 / M
- Context
- 1M tokens
- Longest reply
- 262K
- Reads
- text, image, pdf
- Knows up to
- –
Where it shines
- It scores 1489 on French prompts.
- It costs $1.36 in, $4.18 out per million tokens.
Where it struggles
- Its SimpleQA score of 20 is the lowest in this lineup.
- Its creative writing score of 1364 is weak.
Where you can use it
- Mistral APIAPI$1.36 in / $4.18 out per million tokens.
- OpenRouterAPIListed as
mistralai/mistral-large-4-0
How it scores on each job
Scores run 0 to 100 and blend every measure we have for that job. The number after the dot is its rank among the 33 models in the lineup.
The evidence
| Measure | Score | Rank in lineup | Source |
|---|---|---|---|
| Epoch Capabilities Index | 150 | #25 | Epoch AI |
| LMArena text | 1432 | #24 | LMArena |
| LMArena hard prompts | 1446 | #24 | LMArena |
| LMArena instruction following | 1424 | #24 | LMArena |
| LMArena multi-turn | 1441 | #24 | LMArena |
| LMArena creative writing | 1364 | #25 | LMArena |
| LMArena writing & language | 1387 | #25 | LMArena |
| LMArena coding | 1480 | #21 | LMArena |
| LMArena math | 1467 | #20 | LMArena |
| LMArena business & finance | 1441 | #21 | LMArena |
| LMArena legal & government | 1427 | #25 | LMArena |
| LMArena medicine | 1432 | #22 | LMArena |
| WebDev Arena | 1543 | #23 | LMArena |
| Vision Arena | 1272 | #15 | LMArena |
| Agent Arena | #37 | #21 | LMArena |
| GPQA Diamond | 88% | #23 | Epoch AI |
| FrontierMath | 59% | #24 | Epoch AI |
| SimpleQA Verified | 20% | #24 | Epoch AI |
Compare it with these
New
OpenAI
GPT-6.1 Terra
GPT-6.1 Terra is OpenAI's new mid-tier model for computer use, and its early math scores are strong.
Hard problems
- Price
- $1 in · $5 out
- Context
- 1.1M
New
OpenAI
GPT-6.1 Terra Pro
GPT-6.1 Terra Pro is Terra in a slower pro reasoning mode, and OpenAI doesn't sell it as its own model.
- Price
- $1 in · $5 out
- Context
- 1.1M
New
Moonshot
Kimi K3.1 Pro
Kimi K3.1 Pro is Moonshot's newest model, and early tests put it near the top for coding and sites.
Websites & appsCoding
- Price
- $2 in · $10 out
- Context
- 1M