GLM-5.2: benchmarks and ranking
GLM-5.2 (Z.ai (Zhipu)) — overall rank: #71 / 153, overall score: 54.5 (90% interval 47.6–61.2), leaderboards: 6. Released: 2026-06-13 · Price (in/out): $1.4 / $4.4
Rank on each leaderboard
| Leaderboard | Rank | Published value |
|---|---|---|
| Artificial Analysis | #44 / 141 | 33.7 |
| LiveBench | #44 / 64 | 73.2 |
| Epoch AI | #55 / 230 | 153.07 |
| ARC Prize (ARC-AGI) | #54 / 95 | 22.8 |
| Scale AI SEAL | Not rated | — |
| Vals AI | Not rated | — |
| Terminal-Bench | Not rated | — |
| EQ-Bench | #18 / 32 | 1208.1 |
| SimpleBench | #51 / 112 | 58.8 |
| BenchLM.ai | Not rated | — |
Domain scores
- Coding: 68.8
- Agents: 62.9
- Reasoning: 59.9
- Math: 67.2
- Knowledge: 75.5
- Writing: 62.8
- Instructions: 44.6
- Chat & EQ: 65.1
- Business: 80.9
- Japanese: 78.6
- Long context: 46.6