Is Mistral Medium 3.1 state of the art?#107Best current rank: #107 in Factuality, as of Nov 22, 2026.
As of Nov 22, 2026, Mistral Medium 3.1 is ranked #107 in Factuality (since Nov 22, 2026; sources LMArena Text factuality; methodology v1.0). Ranked #107 in Factuality.
Facts and scores
Mistral Medium 3.1 is a closed-weights text, image and file model from Mistral, listed on LMArena since Oct 19, 2026; no public parameter count, a 131K-token context window and $0.88 per 1M tokens blended.
How it scores
- On LMArena Text factuality it scores 1429 (CI 1426–1432), #132 of 215 (top 62%); 93 behind Gemini 4 Carbon; level with Kimi K2 5 Instant above and level with Mistral Medium 2508 below.
- On LMArena Vision (style-controlled) it scores 1159 (CI 1153–1166), #122 of 193 (top 64%); 150 behind Claude Fable 5; Gemma 3 27B IT is 1 above and level with Mistral Medium 2508 below.
- On LMArena Text (style-controlled, hard prompts) it scores 1427 (CI 1423–1430), #181 of 263 (top 69%); 120 behind Gemini 4 Carbon; level with Ernie 5.0 Preview 1022 above and level with Mistral Medium 2508 below.
History
First result on isitsota: Nov 19, 2026. Best overall rank so far: #107 in Factuality, first held Nov 22, 2026.
The ruling, in plain English
Ranked #138 in General LLM.
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| LMArena Text (style-controlled, overall) Mistral Medium 3.1 (2508) | 1408 1405–1411 | 2026-11-19 | INDEP. | snap_280a9b5ca493 |
| LMArena Text (style-controlled, hard prompts) Mistral Medium 3.1 (2508) | 1427 1423–1430 | 2026-11-19 | INDEP. | snap_280a9b5ca493 |
| LMArena Text (style-controlled, math) Mistral Medium 3.1 (2508) | 1395 1387–1403 | 2026-11-19 | INDEP. | snap_280a9b5ca493 |
| LMArena Text (style-controlled, coding) Mistral Medium 3.1 (2508) | 1453 1449–1458 | 2026-11-19 | INDEP. | snap_280a9b5ca493 |
| LMArena Text (style-controlled, longer query) Mistral Medium 3.1 (2508) | 1408 1404–1412 | 2026-11-19 | INDEP. | snap_280a9b5ca493 |
| LMArena Vision (style-controlled) Mistral Medium 3.1 (2508) | 1159 1153–1166 | 2026-11-19 | INDEP. | snap_71563b13a9cc |
| LMArena Text factuality Mistral Medium 3.1 (2508) | 1429 1426–1432 | 2026-11-19 | INDEP. | snap_275d95909246 |
Where it sits in the succession
Crown intervals for this model are still empty.
Where it is not the crown
| Category | This model | Rank | Leader |
|---|---|---|---|
| General LLM | #138 in this category | #138 | Gemini 4 Carbon |
| Reasoning | #137 in this category | #137 | Gemini 4 Carbon |
| Math | Not enough data | — | GPT-6 Astra |
| Coding | Not enough data | — | Claude Sonnet 5.5 |
| Long context | #141 in this category | #141 | Gemini 4 Argon |
| Vision | Not enough data | — | — |
| Factuality | #107 in this category | #107 | Gemini 4 Carbon |
Related pages
- General LLM
- Reasoning
- Math
- Coding
- Long context
- Vision
- Factuality
- LMArena Vision (style-controlled)
- LMArena Text (style-controlled, overall)
- LMArena Text (style-controlled, coding)
- LMArena Text (style-controlled, math)
- LMArena Text (style-controlled, hard prompts)
- LMArena Text (style-controlled, longer query)
- LMArena Text factuality
- Lab: Mistral
Is Mistral Medium 3.1 SOTA?
Best current rank: #107 in Factuality, as of Nov 22, 2026.
What is Mistral Medium 3.1 best at?
As of Nov 22, 2026, Mistral Medium 3.1 is ranked #107 in Factuality (since Nov 22, 2026; sources LMArena Text factuality).
How does Mistral Medium 3.1 rank in Coding?
As of Nov 22, 2026, Mistral Medium 3.1 is short of the evidence for a rank in Coding (since Nov 22, 2026; sources LMArena Text (style-controlled, coding); methodology v1.0).