GLM-5V-Turbo

Z.aiProprietary

GLM-5V-Turbo is a vision-language model from Z.ai. It ranks 48 of 167 on LMArena’s overall vision board with 1266±5 from 43,637 votes. Its best category is Captioning (#9 of 34). License: Proprietary.

Key figures

LMArena · Overall1266±5#48 / 167 · Votes 43,637
OCR1271±5#52 / 123 · Votes 30,766
Diagrams1284±7#46 / 123 · Votes 11,500
Homework1273±9#63 / 118 · Votes 5,378
Captioning1258±74#9 / 34 · Votes 51
Entity recognition1240±37#23 / 52 · Votes 244
Creative writing1251±12#55 / 106 · Votes 2,971
Humor1271±14#39 / 102 · Votes 1,810
English1277±7#40 / 167 · Votes 17,288
Chinese1329±14#39 / 135 · Votes 2,696
Developer
Z.ai
License
Proprietary
First seen (our snapshots)
2026-10-26

Who it suits

  • Overall #48 of 167: upper half.
  • Strongest category: Captioning (#9 of 34).
  • Proprietary; used through Z.ai’s apps or API.

Neighbours on the overall board

#ModelScoreVotesLicenseΔ vs this model
45Gemini 3.5 Flash-Lite Google126810,800Proprietary+2
46GPT-5.2 Chat (20260210) OpenAI126816,361Proprietary+2
47MiMo-V2.6-Pro Xiaomi12661,826MIT+0
48GLM-5V-Turbo Z.ai126643,637Proprietary
49Gemini 3 Flash (Minimal) Google126536,907Proprietary-1
50Grok 4.6 (High) xAI12648,666Proprietary-2
51Gemini 2.5 Pro Google126388,553Proprietary-3

Alternatives · More from Z.ai

#ModelScoreVotesLicense
24GLM-5.3-Flash Z.ai129531,530MIT
113GLM-4.6V Z.ai11632,440MIT
118GLM-4.5V Z.ai11543,233MIT
163CogVLM2 Llama3 Chat 19B Z.ai9271,991CogVLM2

Alternatives · Top open-weight models

#ModelScoreVotesLicense
24GLM-5.3-Flash Z.ai129531,530MIT
34Kimi K2.6 Moonshot AI128216,265Modified MIT
36Gemma 4 31B Google127941,787Apache 2.0
37DeepSeek-V4.1-Flash-20260910 (Max) DeepSeek12794,247MIT
42Qwen3.8-27B Alibaba12709,632Apache 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 GLM-5V-Turbo rank among vision models?

Overall rank 48 (1266); OCR rank 52 (1271); Diagrams rank 46 (1284); Homework rank 63 (1273); Captioning rank 9 (1258); Entity recognition rank 23 (1240); Creative writing rank 55 (1251); Humor rank 39 (1271); English rank 40 (1277); Chinese rank 39 (1329) (LMArena, data as of Nov 14, 2026).

How good is GLM-5V-Turbo at OCR?

GLM-5V-Turbo ranks 52 of 123 on LMArena’s OCR board with 1271 (30,766 votes).

Is GLM-5V-Turbo better with Chinese or English prompts?

Chinese board: #39 of 135 (1329); English board: #40 of 167 (1277). The boards are computed separately, so compare ranks rather than scores.

Is GLM-5V-Turbo open-weight?

No. LMArena lists it as Proprietary; it is available through Z.ai’s apps or API.

How far is GLM-5V-Turbo from #1?

#1 overall is Claude Fable 5 (High) (1326); GLM-5V-Turbo has 1266, 60 points behind.

Sources

LMArena data published Nov 9, 2026.

Synced here Nov 14, 2026.

Price, context length and release date have no reliable public data here and are not shown; all figures come from snapshots, blanks are –.