whatmodel.sh / GLM-5V-Turbo
GLM-5V-Turbo
↗ share
+ contribute
GLM-5V-Turbo is a closed-weights language model from Z.ai, released April 2026.
Catalogue identity notes
Comparison-only. Arena entry 'glm-5v-turbo' (zai, Proprietary), first listed 2026-06-03 (document) / 2026-07-10 (text). Vision-language model; not GLM-5.
Model information sources
$ how it compares
The LLMs ranked either side of GLM-5V-Turbo, out of 828 with a score, then more from Z.ai.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 110 |  Claude Sonnet 4.5 | 69±1 | api $6.00/M | ||
| 111 |  Qwen3.5 27B | 69±0 | api $0.84/M +local | ||
| 112 | GLM-5V-Turbo | 69±2 | api $1.90/M | ||
| 113 |  GPT-5.2-Codex | 69±2 | comparison only | ||
| 114 |  LongCat-Flash-Thinking (560B-A27B) | 69±1 | comparison only | ||
| more from Z.ai | |||||
| 33 | GLM-5.3 | 76±1 | api $2.15/M +local | ||
| 52 | GLM-5.3-Flash | 74±1 | api $0.24/M +local | ||
| 57 | GLM-5.2 | 74±1 | api $2.15/M +local | ||
$ what it's good at
coding▁▁▁▃▆██▇▆▄▃▁ #85 of 458 * · 46% of its score · 1 test
Beats Grok 4.20 (0309 reasoning), GPT-5.4 mini, GPT-5.1 here, though they rank higher overall. Trails Llama 3.1 Nemotron Ultra 253B v1 here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena WebDev (Code Arena) | 1399.8 ✎ | ▁▂▄▃▅█▄▇▆▄▁▁ beats 46/119 | 46% |
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #75 of 393 * · 26% of its score · 1 test
Beats LongCat 2.0 (1.6T-A48B), Mistral Large 4 (public preview), Inkling Small (266B-A12B) here, though they rank higher overall. Trails Gemma 4 12B, Gemma 4 26B-A4B, Nemotron Cascade 2 30B-A3B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena (text) | 1433.5 ✎ | ▁▁▁▂▃▃▃▆▆▇█▃ beats 289/379 | 26% |
vision & documents▁▁▃▂▁▃▄▂▆▇█▄ #64 of 147 * · 27% of its score · 2 tests
Beats DeepSeek V4 Flash Vision (Exp), GPT-5, Inkling Small (266B-A12B) here, though they rank higher overall. Trails Gemma 4 26B-A4B, Claude Haiku 4.5, Qwen3.6 Flash here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena vision (style controlled) | 1230.1 ✎ | ▁▁▂▂▂▂▄▅▅▆██ beats 88/145 | 18% |
| Arena document (style controlled) | 1400.1 ✎ | ▃▁▃▃▄▃▇█▅▇▄▅ beats 0/37 | 8.7% |
$ where to run it
Through an API
api · SiliconFlow · $1.90/M · $1.2 in / $4 out per 1M tokens · 200k context · www.siliconflow.com ↗ · price sourceUSD per 1M tokens, SiliconFlow serverless pay-as-you-go, model zai-org/GLM-5V-Turbo (page state 'Available'; SiliconFlow names Z.ai as the model provider; served in FP8): input $1.20, output $4.00; cache-read input $0.24 excluded. Z.ai's own pricing page no longer lists GLM-5V-Turbo (its Vision Models table shows GLM-4.6V, GLM-OCR, GLM-4.6V-FlashX, GLM-4.5V and GLM-4.6V-Flash only); the same $1.20/$4.00 appears for Z.ai in models.dev @a668908. Not a Z.ai direct tariff. Currency: USD. SiliconFlow official model page, observed 2026-09-26.
$ how the score was worked out · LMArena leaderboard dataset 99%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 LMArena leaderboard dataset | 4 | 99% |
| prior · pull toward the middle | 1% | |
| weighted average | = 68.5 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json