Zhipu AI (Z.ai)
GLM-5.2 benchmark results
4 results on 4 benchmarks from 2 sources.
Also listed as: glm-5.2_none · glm-5.2_low · glm-5.2_max
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| GPQA Diamond | 71.2% | 158 | Epoch AI run, accuracy | Independent run | Aug 10, 2026 |
| SWE-bench Verified | 78.7% | 5 | Epoch AI run (Epoch scaffold) | Independent run | Jun 25, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 28.9% | 194 | Epoch AI run, OTIS Mock AIME 2024–2025 | Independent run | Aug 10, 2026 |
| τ²-bench | 37.1% | 11 | banking_knowledge domain, pass^1; effort: xhigh; submitted by Sierra; v1.0.1 | Official leaderboard | Jul 24, 2026 |
Related on this site
FAQ
Where do these GLM-5.2 scores come from?
From Epoch AI Benchmarking Hub and τ²-bench leaderboard submissions. Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.