InternVL2 4B
OpenGVLabOpenMIT
InternVL2 4B is a vision-language model from OpenGVLab. It ranks 160 of 167 on LMArena’s overall vision board with 941±13 from 3,703 votes. License: MIT.
Key figures
- Developer
- OpenGVLab
- License
- MIT
- First seen (our snapshots)
- 2026-10-26
No data: OCR, Diagrams, Homework, Captioning, Entity recognition, Creative writing, Humor.
Who it suits
- Overall #160 of 167: lower half; consider it mainly for cost or deployment reasons.
- Open weights (MIT): you can self-host it.
Neighbours on the overall board
| # | Model | Score | Votes | License | Δ vs this model |
|---|---|---|---|---|---|
| 157 |  Llama 3.2 11B Vision Instruct Meta | 966 | 4,817 | Llama 3.2 | +25 |
| 158 |  Molmo 7B-D (0924) Ai2 | 959 | 2,815 | Apache 2.0 | +18 |
| 159 |  Claude 3 Haiku (20240307) Anthropic | 950 | 13,380 | Proprietary | +9 |
| 160 | OInternVL2 4B OpenGVLab | 941 | 3,703 | MIT | |
| 161 | Nnvila-internal-15b-v1 NVIDIA | 940 | 1,077 | - | -1 |
| 162 | LLLaVA 1.6 34B | 936 | 4,531 | Apache 2.0 | -5 |
| 163 |  CogVLM2 Llama3 Chat 19B Z.ai | 928 | 1,991 | CogVLM2 | -13 |
Alternatives · More from OpenGVLab
| # | Model | Score | Votes | License |
|---|---|---|---|---|
| 148 | OInternVL2 26B OpenGVLab | 1005 | 5,148 | MIT |
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 InternVL2 4B rank among vision models?
Overall rank 160 (941); English rank 158 (986); Chinese rank 122 (950) (LMArena, data as of Oct 26, 2026).
How good is InternVL2 4B at OCR?
InternVL2 4B is not on LMArena’s OCR board yet, so there is no score to cite.
Is InternVL2 4B better with Chinese or English prompts?
Chinese board: #122 of 128 (950); English board: #158 of 167 (986). The boards are computed separately, so compare ranks rather than scores.
Is InternVL2 4B open-weight?
LMArena lists its license as MIT, not proprietary; check the license text for commercial use.
How far is InternVL2 4B from #1?
#1 overall is Claude Fable 5 (High) (1325); InternVL2 4B has 941, 384 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 –.