GLM-5.2 vs GPT-5.6 Luna
44 SHARED BENCHMARKSAcross 44 shared benchmarks, GLM-5.2 scores higher on 15 and GPT-5.6 Luna on 29. The widest gap is AA-Omniscience · Non-hallucination, where GLM-5.2 scores 73.7 against 7.4. GPT-5.6 Luna is the cheaper of the two on tracked API pricing ($0.20 against $1.40 per million input tokens).
At a glance
Release dates per Artificial Analysis. Prices: Z.ai's own price page for GLM-5.2; Artificial Analysis for GPT-5.6 Luna. ◆ = independently verified score.
Where each leadsby capability area · benchmark wins
Biggest gaps
GLM-5.2 pulls furthest ahead on
- AA-Omniscience · Non-hallucination73.7 vs 7.4
- SimpleBench58.8 vs 46.8
- τ-Bench V3 · Banking34.6 vs 31.1
GPT-5.6 Luna pulls furthest ahead on
- ARC-AGI-259.6 vs 22.8
- FrontierMath Tier 458.5 vs 29.3
- AA-Omniscience · Accuracy42.7 vs 24.3
Every shared benchmark44 · grouped by area
Reasoning 6
Coding 6
Agentic 5
Factuality 3
Instruction Following 1
Long Context 1
Math 5
Other shared benchmarks 17
Each score is the one the model's own page shows — the most authoritative tracked result for that benchmark, on the benchmark's standard methodology (source-attributed). ↓ marks lower-is-better metrics; ◆ an independently verified score. Open either model for its full surface, provenance and pricing. Quoted rates are the price-setter row we currently track for each model — its direct or vendor-official listing where one exists (zai-official, direct), otherwise the lowest tracked offer.