‹ PublicAI Index
The LLM benchmark aggregator.
GLM-5.3
Z.ai · 753B · open weights
Strongest in Agentic coding (#12 of 173, on 3 of its 5 boards), weakest in Mathematics (#98 of 152). Above par in 22 of 25 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5 and Muse Wonder and ahead of GPT-6 Sol and Grok 4.7.
§ 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.
Coding59.4−6.8#13/1793/6
Agentic coding59.8−7.1#12/1733/5
Repository Q&A46−20.7—/0✱✱
Agents59.4−7#19/2982/6
Knowledge work65.1−5.6#23/2082/2
Workflow automation54.1−11.9—/0✱✱
Human preference64.6−4.2#22/3541/1
Human preference64.6−4.2#22/3541/1
Professional55−7.4#31/1941/2
IT operations46−27.8#16/331/1
Cybersecurity56.4−7.5#18/471/1
Legal57.9−8#21/1731/1
Medical55.1−11.4#41/1491/1
Finance55.1−7.3#46/1621/1
Knowledge52.9−9.6#68/1971/3
Academic knowledge56.9−7#37/1231/1
Core abilities52.4−12.9#71/1992/4
Language52.4−14.2#29/621/1
Instruction following52.3−21.5#31/621/1
General intelligence52.9−16.5#62/1781/3
Reasoning52.2−13.2#77/1953/5
Science58.4−5.1#36/1221/1
Reasoning55.8−13.2#43/1471/3
Mathematics47.2−16.6#98/1522/2
Expert reasoning54.6−11.8—/0✱✱
§ 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-5.3, left for the other.
§ 3 · Sources
Where the numbers come from
9 publications, 41 figures. Every one links to the page it was read from.
LMArena Text 1483
Artificial Analysis Intelligence Index 32
GDPval-AA 1657
AA-Briefcase 1503
Terminal-Bench 41.2% (Claude Code)
LiveBench 1.0 76.1LiveBench 1.0 · Reasoning 85.8LiveBench 1.0 · Coding 79LiveBench 1.0 · Agentic Coding 60.9LiveBench 1.0 · Mathematics 87.9LiveBench 1.0 · Data Analysis 70.2LiveBench 1.0 · Language 79.9LiveBench 1.0 · Instruction Following 69.3
SimpleBench 66.2%
Vals · Legal Research Bench 49.04%Vals · LegalBench 84.84%Vals · Harvey Legal Agent Benchmark 14.58%Vals · Finance Agent 55.84%Vals · TaxEval 72.36%Vals · MedCode 42.86%Vals · MedScribe 88.81%Vals · CyberBench 72.08%Vals · SRE Bench 9.16%Vals · SWE-bench Verified 95.4% (Mini-SWE-agent)Vals · Vibe Code Bench 78.13% (OpenHands)Vals · Code Migration 44.22%Vals · GPQA Diamond 88.13%Vals · MMLU Pro 86.77%Vals · ProofBench 49%
GPQA Diamond (Pass@1) 88.1%Terminal-Bench 2.1 (Pass@1) 88.2%Terminal-Bench 3.0 (Pass@1) 28.3%Terminal-Bench 4.0 (Pass@1) 37.9%DeepSWE v1.1 (Resolved) 66.9%ProgramBench (Almost@1) 19%NL2Repo-Bench (Score) 58%CyberGym (Pass@1) 84.5%ExploitGym (Pass@1) 15%HLE w/ tools (Pass@1) 62.5%AutomationBench (Pass@1) 48.8%Agent's Last Exam (Pass@1) 28.5%
Badge
[](https://publicai.io/model-index/m/glm-5-3)