Mistral Small 3.1 24B Instruct (2503)
MistralOpenApache 2.0
Mistral Small 3.1 24B Instruct (2503) is a vision-language model from Mistral. It ranks 125 of 167 on LMArena’s overall vision board with 1136±8 from 28,490 votes. Its best category is Captioning (#29 of 34). License: Apache 2.0.
Key figures
- Developer
- Mistral
- License
- Apache 2.0
- First seen (our snapshots)
- 2026-10-26
Who it suits
- Overall #125 of 167: lower half; consider it mainly for cost or deployment reasons.
- Strongest category: Captioning (#29 of 34).
- Open weights (Apache 2.0): you can self-host it.
Neighbours on the overall board
| # | Model | Score | Votes | License | Δ vs this model |
|---|---|---|---|---|---|
| 122 |  Llama 4 Maverick 17B 128E Instruct Meta | 1142 | 6,923 | Llama 4 | +6 |
| 123 |  Gemini 1.5 Flash (002) Google | 1141 | 7,241 | Proprietary | +5 |
| 124 |  GPT-4o (2024-05-13) OpenAI | 1137 | 23,273 | Proprietary | +1 |
| 125 | Mistral Small 3.1 24B Instruct (2503) Mistral | 1136 | 28,490 | Apache 2.0 | |
| 126 |  Claude 3.5 Sonnet (20241022) Anthropic | 1126 | 10,374 | Proprietary | -10 |
| 127 | SStep-1o Vision 32K (High Res) StepFun | 1122 | 2,833 | Proprietary | -14 |
| 128 | Claude 3.5 Sonnet (20240620) Anthropic | 1120 | 21,624 | Proprietary | -16 |
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 |
| 117 | Mistral Medium 3 (2505) Mistral | 1157 | 10,793 | Proprietary |
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 Small 3.1 24B Instruct (2503) rank among vision models?
Overall rank 125 (1136); OCR rank 120 (1132); Diagrams rank 121 (1119); Homework rank 111 (1158); Captioning rank 29 (1153); Entity recognition rank 47 (1155); Creative writing rank 102 (1123); Humor rank 89 (1142); English rank 121 (1157); Chinese rank 99 (1155) (LMArena, data as of Oct 26, 2026).
How good is Mistral Small 3.1 24B Instruct (2503) at OCR?
Mistral Small 3.1 24B Instruct (2503) ranks 120 of 123 on LMArena’s OCR board with 1132 (7,209 votes).
Is Mistral Small 3.1 24B Instruct (2503) better with Chinese or English prompts?
Chinese board: #99 of 128 (1155); English board: #121 of 167 (1157). The boards are computed separately, so compare ranks rather than scores.
Is Mistral Small 3.1 24B Instruct (2503) open-weight?
LMArena lists its license as Apache 2.0, not proprietary; check the license text for commercial use.
How far is Mistral Small 3.1 24B Instruct (2503) from #1?
#1 overall is Claude Fable 5 (High) (1325); Mistral Small 3.1 24B Instruct (2503) has 1136, 189 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 –.