Zhipu AI (Z.ai)
GLM-4.6 benchmark results
7 results on 5 benchmarks from 4 sources.
Also listed as: glm-4.6 · GLM 4.6 · https://huggingface.co/zai-org/GLM-4.6 · GLM 4.6 (T=1) · GLM-4.6 (FC thinking)
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1424 | 124 | Overall, style control on; 35828 votes; 95% CI 1420–1428“glm-4.6” | Official leaderboard | Oct 8, 2026 |
| LMArena WebDev | 1340 | 113 | Overall; 6781 votes; 95% CI 1329–1351“glm-4.6” | Official leaderboard | Oct 8, 2026 |
| SWE-bench Verified | 68.2% | 30 | agent: Undisclosed“https://huggingface.co/zai-org/GLM-4.6” | Official leaderboard | Sep 30, 2025 |
| SWE-bench Verified | 55.4% | 57 | agent: mini-SWE-agent“glm-4.6” | Official leaderboard | Dec 1, 2025 |
| Terminal-Bench 2.0 | 24.5% | 154 | Terminal-Bench 2.0; agent: Terminus 2 | Official leaderboard via Epoch AI | Sep 30, 2025 |
| Terminal-Bench 2.0 | 24.5% | 155 | Terminal-Bench 2.0; agent: Terminus 2 | Official leaderboard via Epoch AI | Nov 1, 2025 |
| BFCL v4 (function calling) | 72.4% | 4 | Overall accuracy“GLM-4.6 (FC thinking)” | Official leaderboard | Oct 17, 2026 |
FAQ
Where do these GLM-4.6 scores come from?
From Berkeley Function Calling Leaderboard (BFCL), LMArena leaderboard dataset, SWE-bench leaderboards (swebench.com), and Epoch AI Benchmarking Hub. Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.