DeepSeek-V4.1-Flash-20260910 (Max)
DeepSeekOpenMIT
DeepSeek-V4.1-Flash-20260910 (Max) is a vision-language model from DeepSeek. It ranks 38 of 167 on LMArena’s overall vision board with 1278±10 from 4,100 votes. Its best category is Homework (#34 of 118). License: MIT.
Key figures
- Developer
- DeepSeek
- License
- MIT
- First seen (our snapshots)
- 2026-10-26
No data: Captioning, Entity recognition.
Who it suits
- Overall #38 of 167: upper half.
- Strongest category: Homework (#34 of 118).
- Open weights (MIT): you can self-host it.
Neighbours on the overall board
| # | Model | Score | Votes | License | Δ vs this model |
|---|---|---|---|---|---|
| 35 |  GPT-5.6 Sol (xHigh) OpenAI | 1281 | 11,439 | Proprietary | +3 |
| 36 | GPT-6 Astra (Max) OpenAI | 1280 | 4,012 | Proprietary | +2 |
| 37 |  Qwen3.7-Plus Alibaba | 1278 | 14,212 | Proprietary | +0 |
| 38 | DeepSeek-V4.1-Flash-20260910 (Max) DeepSeek | 1278 | 4,100 | MIT | |
| 39 |  Gemma 4 31B Google | 1276 | 40,219 | Apache 2.0 | -2 |
| 40 |  Dola Seed 2.0 Pro ByteDance | 1274 | 10,972 | Proprietary | -4 |
| 41 |  Claude Sonnet 5 (High) Anthropic | 1273 | 14,034 | Proprietary | -5 |
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 |
| 39 | Gemma 4 31B Google | 1276 | 40,219 | Apache 2.0 |
| 44 | Qwen3.8-27B Alibaba | 1269 | 7,614 | Apache 2.0 |
| 46 | Kimi K2.5 (Thinking) Moonshot AI | 1269 | 28,249 | Modified MIT |
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 DeepSeek-V4.1-Flash-20260910 (Max) rank among vision models?
Overall rank 38 (1278); OCR rank 41 (1282); Diagrams rank 37 (1297); Homework rank 34 (1307); Creative writing rank 34 (1275); Humor rank 47 (1260); English rank 32 (1288); Chinese rank 37 (1327) (LMArena, data as of Oct 26, 2026).
How good is DeepSeek-V4.1-Flash-20260910 (Max) at OCR?
DeepSeek-V4.1-Flash-20260910 (Max) ranks 41 of 123 on LMArena’s OCR board with 1282 (2,786 votes).
Is DeepSeek-V4.1-Flash-20260910 (Max) better with Chinese or English prompts?
Chinese board: #37 of 128 (1327); English board: #32 of 167 (1288). The boards are computed separately, so compare ranks rather than scores.
Is DeepSeek-V4.1-Flash-20260910 (Max) open-weight?
LMArena lists its license as MIT, not proprietary; check the license text for commercial use.
How far is DeepSeek-V4.1-Flash-20260910 (Max) from #1?
#1 overall is Claude Fable 5 (High) (1325); DeepSeek-V4.1-Flash-20260910 (Max) has 1278, 47 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 –.