CogVLM2 Llama3 Chat 19B
Z.aiOpenCogVLM2
CogVLM2 Llama3 Chat 19B is a vision-language model from Z.ai. It ranks 163 of 167 on LMArena’s overall vision board with 928±15 from 1,991 votes. License: CogVLM2.
Key figures
- Developer
- Z.ai
- License
- CogVLM2
- First seen (our snapshots)
- 2026-10-26
No data: OCR, Diagrams, Homework, Captioning, Entity recognition, Creative writing, Humor, Chinese.
Who it suits
- Overall #163 of 167: lower half; consider it mainly for cost or deployment reasons.
- Open weights (CogVLM2): you can self-host it.
Neighbours on the overall board
| # | Model | Score | Votes | License | Δ vs this model |
|---|---|---|---|---|---|
| 160 | OInternVL2 4B OpenGVLab | 941 | 3,703 | MIT | +13 |
| 161 | Nnvila-internal-15b-v1 NVIDIA | 940 | 1,077 | - | +12 |
| 162 | LLLaVA 1.6 34B | 936 | 4,531 | Apache 2.0 | +8 |
| 163 | CogVLM2 Llama3 Chat 19B Z.ai | 928 | 1,991 | CogVLM2 | |
| 164 | LLLaVA-OneVision Qwen2 72B OV | 923 | 1,321 | Apache 2.0 | -5 |
| 165 | OMiniCPM-V 2.6 OpenBMB | 912 | 1,987 | Apache 2.0 | -16 |
| 166 | MPhi-3.5 Vision Instruct Microsoft | 851 | 2,592 | MIT | -77 |
Alternatives · More from Z.ai
| # | Model | Score | Votes | License |
|---|---|---|---|---|
| 24 | GLM-5.3-Flash Z.ai | 1294 | 16,254 | MIT |
| 50 | GLM-5V-Turbo Z.ai | 1264 | 42,757 | Proprietary |
| 113 | GLM-4.6V Z.ai | 1164 | 2,455 | MIT |
| 118 | GLM-4.5V Z.ai | 1154 | 3,243 | 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 CogVLM2 Llama3 Chat 19B rank among vision models?
Overall rank 163 (928); English rank 161 (969) (LMArena, data as of Oct 26, 2026).
How good is CogVLM2 Llama3 Chat 19B at OCR?
CogVLM2 Llama3 Chat 19B is not on LMArena’s OCR board yet, so there is no score to cite.
Is CogVLM2 Llama3 Chat 19B open-weight?
LMArena lists its license as CogVLM2, not proprietary; check the license text for commercial use.
How far is CogVLM2 Llama3 Chat 19B from #1?
#1 overall is Claude Fable 5 (High) (1325); CogVLM2 Llama3 Chat 19B has 928, 397 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 –.