‹ PublicAI Index
The LLM benchmark aggregator.
GLM-5
Z.ai · 754B · open weights
Strongest in General intelligence (#21 of 178, on 1 of its 3 boards), weakest in Safety (#181 of 329). Above par in 12 of 18 scopes. Among the models it meets almost everywhere, it finishes behind GPT-5.5 and Claude Opus 5.5 and ahead of DeepSeek V4 Flash and O3.
§ 1 · Profile
What it is good at
Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.
Core abilities57.6−7.7#23/1991/4
General intelligence60.9−8.5#21/1781/3
Human preference62.1−6.7#55/3541/1
Human preference62.1−6.7#55/3541/1
Professional51.6−10.8#77/1941/2
Medical55.7−10.8#36/1491/1
Finance52.7−9.7#77/1621/1
Legal48.5−17.4#102/1731/1
Knowledge52.5−10#78/1971/3
Academic knowledge56−7.9#50/1231/1
Reasoning51.8−13.6#81/1953/5
Mathematics56.8−7#36/1521/2
Science55.1−8.4#58/1221/1
Reasoning46.3−22.7#84/1472/3
Coding46.1−20.1#113/1791/6
Agentic coding45.8−21.1#109/1731/5
Safety49.9−11.5#181/3291/3
Factual grounding49.6−21.1#59/1041/1
§ 2 · Head to head
What it beats, and what beats it
The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for GLM-5, left for the other.
§ 3 · Sources
Where the numbers come from
6 publications, 15 figures. Every one links to the page it was read from.
LMArena Text 1457
ARC-AGI-2 4.9%
Kagi LLM Benchmark 75%
SimpleBench 53.2%
Vals · CaseLaw 52.52%Vals · LegalBench 84.06%Vals · CorpFin 62.9%Vals · TaxEval 70.03%Vals · MedQA 94.27%Vals · SWE-bench Verified 71.4% (Mini-SWE-agent)Vals · Vibe Code Bench 23.36% (OpenHands)Vals · GPQA Diamond 83.33%Vals · MMLU Pro 86.03%Vals · AIME 91.67%
Vectara · Factual consistency 89.9%
Badge
[](https://publicai.io/model-index/m/glm-5)