Mistral Medium 3 (2505)
MistralProprietary
Mistral Medium 3 (2505) is a vision-language model from Mistral. It ranks 117 of 167 on LMArena’s overall vision board with 1157±8 from 10,793 votes. Its best category is Diagrams (#111 of 123). License: Proprietary.
Key figures
- Developer
- Mistral
- License
- Proprietary
- First seen (our snapshots)
- 2026-10-26
Who it suits
- Overall #117 of 167: lower half; consider it mainly for cost or deployment reasons.
- Strongest category: Diagrams (#111 of 123).
- Proprietary; used through Mistral’s apps or API.
Neighbours on the overall board
| # | Model | Score | Votes | License | Δ vs this model |
|---|---|---|---|---|---|
| 114 |  Gemini 1.5 Pro (002) Google | 1161 | 8,902 | Proprietary | +4 |
| 115 |  GPT-5 nano (High) OpenAI | 1159 | 3,928 | Proprietary | +2 |
| 116 | Gemini 2.0 Flash (001) Google | 1158 | 10,135 | Proprietary | +1 |
| 117 | Mistral Medium 3 (2505) Mistral | 1157 | 10,793 | Proprietary | |
| 118 |  GLM-4.5V Z.ai | 1154 | 3,243 | MIT | -3 |
| 119 |  Qwen2.5-VL-32B-Instruct Alibaba | 1152 | 1,490 | Apache 2.0 | -5 |
| 120 |  Claude 3.7 Sonnet (20250219) Anthropic | 1151 | 4,517 | Proprietary | -6 |
Alternatives · More from Mistral
| # | Model | Score | Votes | License |
|---|---|---|---|---|
| 42 | Mistral Large 4 Mistral | 1272 | 1,008 | Proprietary |
| 83 | Mistral Medium 3.5 Mistral | 1222 | 5,375 | Modified MIT |
| 84 | Mistral Large 3 Mistral | 1220 | 9,254 | Apache 2.0 |
| 109 | Mistral Medium 3.1 (2508) Mistral | 1172 | 41,611 | Proprietary |
| 121 | Mistral Small 3.2 (2506) Mistral | 1142 | 10,843 | Apache 2.0 |
Alternatives · Top open-weight models
| # | Model | Score | Votes | License |
|---|---|---|---|---|
| 24 | GLM-5.3-Flash Z.ai | 1294 | 16,254 | MIT |
| 34 |  Kimi K2.6 Moonshot AI | 1282 | 16,368 | Modified MIT |
| 38 |  DeepSeek-V4.1-Flash-20260910 (Max) DeepSeek | 1278 | 4,100 | MIT |
| 39 | Gemma 4 31B Google | 1276 | 40,219 | Apache 2.0 |
| 44 | Qwen3.8-27B Alibaba | 1269 | 7,614 | Apache 2.0 |
How to read these scores
- If two scores differ by less than their ± intervals, the models are statistically close.
- Each category board is computed independently; do not compare scores across categories.
- Models with few votes move more; ranks of new entries may change.
FAQ
Where does Mistral Medium 3 (2505) rank among vision models?
Overall rank 117 (1157); OCR rank 113 (1154); Diagrams rank 111 (1155); Homework rank 107 (1165); Captioning rank 33 (1094); Entity recognition rank 51 (1141); Creative writing rank 99 (1146); Humor rank 88 (1145); English rank 113 (1172); Chinese rank 98 (1161) (LMArena, data as of Oct 26, 2026).
How good is Mistral Medium 3 (2505) at OCR?
Mistral Medium 3 (2505) ranks 113 of 123 on LMArena’s OCR board with 1154 (4,562 votes).
Is Mistral Medium 3 (2505) better with Chinese or English prompts?
Chinese board: #98 of 128 (1161); English board: #113 of 167 (1172). The boards are computed separately, so compare ranks rather than scores.
Is Mistral Medium 3 (2505) open-weight?
No. LMArena lists it as Proprietary; it is available through Mistral’s apps or API.
How far is Mistral Medium 3 (2505) from #1?
#1 overall is Claude Fable 5 (High) (1325); Mistral Medium 3 (2505) has 1157, 168 points behind.
Sources
LMArena data published Oct 19, 2026.
Synced here Oct 26, 2026.
Price, context length and release date have no reliable public data here and are not shown; all figures come from snapshots, blanks are –.