GLM 4.7: benchmarks and ranking
GLM 4.7 (Z.ai (Zhipu)) — overall rank: #90 / 153, overall score: 39.0 (90% interval 24.5–55.8), leaderboards: 2. Released: 2025-12-22 · Price (in/out): $0.6 / $2.2
Rank on each leaderboard
| Leaderboard | Rank | Published value |
|---|---|---|
| Artificial Analysis | Not rated | — |
| LiveBench | Not rated | — |
| Epoch AI | #103 / 230 | 143.34 |
| ARC Prize (ARC-AGI) | Not rated | — |
| Scale AI SEAL | Not rated | — |
| Vals AI | Not rated | — |
| Terminal-Bench | Not rated | — |
| EQ-Bench | Not rated | — |
| SimpleBench | #67 / 112 | 47.7 |
| BenchLM.ai | Not rated | — |
Domain scores
- Coding: 50.3
- Agents: 23.9
- Reasoning: 47.5
- Math: 54.0
- Knowledge: 68.6
- Writing: 44.8
- Instructions: 45.3
- Chat & EQ: 48.5
- Business: 71.4
- Japanese: 75.5