GLM vision model for visual reasoning, documents, and multimodal agents
Benchmarks
| Benchmark | Category | Score | Variant | Provenance | Source | Observed |
|---|---|---|---|---|---|---|
| AA Intelligence Index | intelligence | 11.0 | — | independent | aa | Jul 24, 2026 |
| LMArena Text | preference | 1433 | — | crowd | lmarena | Jul 21, 2026 |
| LMArena Vision | preference | 1165 | — | crowd | lmarena | Jul 21, 2026 |
| Median output speed | speed | 44 tok/s | — | independent | aa | Jul 24, 2026 |
| Median time to first token | speed | 4.46s | — | independent | aa | Jul 24, 2026 |
Includes index data from Artificial Analysis.