Zhipu AI (Z.ai)
GLM-5 benchmark results
12 results on 8 benchmarks from 5 sources.
Also listed as: glm-5 · GLM 5 · GLM 5 (high)
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1458 | 63 | Overall, style control on; 29292 votes; 95% CI 1453–1462“glm-5” | Official leaderboard | Oct 8, 2026 |
| LMArena WebDev | 1434 | 79 | Overall; 7506 votes; 95% CI 1426–1443“glm-5” | Official leaderboard | Oct 8, 2026 |
| GPQA Diamond | 87.8% | 66 | Epoch AI run, accuracy | Independent run | Feb 12, 2026 |
| MMLU-Pro | 86.0% | 29 | Overall accuracy; data source: Self-Reported; 754B | Vendor-reported | Mar 11, 2026 |
| SWE-bench Verified | 72.1% | 22 | Epoch AI run (Epoch scaffold) | Independent run | Feb 15, 2026 |
| SWE-bench Verified | 72.8% | 16 | agent: mini-SWE-agent“glm-5” | Official leaderboard | Feb 17, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 80.0% | 110 | Epoch AI run, OTIS Mock AIME 2024–2025 | Independent run | Feb 12, 2026 |
| τ²-bench | 82.5% | 3 | airline domain, pass^1; effort: enabled; submitted by Sierra; v1.0.1 | Official leaderboard | Feb 27, 2026 |
| τ²-bench | 9.8% | 27 | banking_knowledge domain, pass^1; effort: enabled; submitted by Sierra; v1.0.1 | Official leaderboard | Feb 27, 2026 |
| τ²-bench | 73.7% | 20 | retail domain, pass^1; effort: enabled; submitted by Sierra; v1.0.1 | Official leaderboard | Feb 27, 2026 |
| τ²-bench | 86.8% | 13 | telecom domain, pass^1; effort: enabled; submitted by Sierra; v1.0.1 | Official leaderboard | Feb 27, 2026 |
| Terminal-Bench 2.0 | 52.4% | 64 | Terminal-Bench 2.0; agent: Terminus 2 | Official leaderboard via Epoch AI | Feb 11, 2026 |
FAQ
Where do these GLM-5 scores come from?
From Epoch AI Benchmarking Hub, LMArena leaderboard dataset, MMLU-Pro leaderboard (TIGER-Lab), SWE-bench leaderboards (swebench.com), and τ²-bench leaderboard submissions. Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.