whatmodel.sh / GLM-4-Plus
GLM-4-Plus
↗ share
+ contribute
GLM-4-Plus is a closed-weights language model from Z.ai, released August 2024.
Catalogue identity notes
Comparison-only. Arena entry 'glm-4-plus' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'glm-4-plus' as 'GLM-4-Plus' (Zhipu AI, Proprietary), linking https://bigmodel.cn/dev/howuse/glm-4. Released 2024-08: Zhipu GLM-4-Plus announcement (KDD 2024, late August 2024). Arena name equals the undated API id glm-4-plus. The id is still documented on BigModel, but a later '0111' snapshot also appeared on the Arena, so the current endpoint is not asserted to be the rated checkpoint.
$ how it compares
The LLMs ranked either side of GLM-4-Plus, out of 1132 with a score, then more from Z.ai.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 383 |  DeepSeek R1 Distill Qwen 32B | 56±1 | api $1.59/M +local | ||
| 384 |  Qwen2.5-VL 72B Instruct | 56±1 | local | ||
| 385 | GLM-4-Plus | 56±3 | comparison only | ||
| 386 |  Granite 4.1 30B | 56±1 | local | ||
| 387 |  Baichuan-M2-32B | 56±4 | local | ||
| more from Z.ai | |||||
| 33 | GLM-5.3 | 76±1 | api $2.15/M +local | ||
| 53 | GLM-5.3-Flash | 74±1 | api $0.24/M +local | ||
| 59 | GLM-5.2 | 74±1 | api $2.15/M +local | ||
$ what it's good at
chat & writing▁▁▁▃▅▅▆█▆▆▆▂ #273 of 579 * · 95% of its score · 1 test
Beats Granite 4.2 8B, Qwen3-VL 30B-A3B Thinking, Mistral Small 4 (119B-A6.5B) here, though they rank higher overall. Trails LFM2.5 1.2B Instruct, LFM2.5 1.2B Thinking, Gemma 3 12B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena (text) | 1319.4 ✎ | ▁▁▁▂▃▃▃▆▆▇█▃ beats 152/379 | 95% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · LMArena leaderboard dataset 95%
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 | 1 | 95% |
| prior · pull toward the middle | 5% | |
| weighted average | = 55.9 |
$ 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