GLM 4.6 benchmark ranking on every AI leaderboard
open weights · #30 overall, podium score 4.7 · top 10 on 1 of 4 · released Sep 30, 2025
| Rank | Board | Score | |||
|---|---|---|---|---|---|
| 4 |  BFCLAgents and tools · as “GLM-4.6 (FC thinking)” | Agents and tools | 72.4% | 81 | |
| 84 |  WebDev ArenaCoding · as “glm-4.6” | Coding | 1,341 | 100 | |
| 91 | Text ArenaChat · as “glm-4.6” | Chat | 1,425 | 100 | |
| 23 |  SWE-bench VerifiedCoding · stale since 2026-02-26 · as “GLM 4.6 (T=1)” | Coding | 55.4% | 39 |
Category ranks and more models
Rank in each category
More from Z.ai (Zhipu)
Sources: each leaderboard's own published results page, captured every day at 04:30 UTC. Scores exactly as each board published them; we run no evaluations. Logos via logo.dev; trademarks belong to their owners.