Efficiency tier of GLM 5.3 that gives up little: AA Intelligence Index 57.5 against the full model's 59.5.
| Benchmark | Score | Rank |
|---|---|---|
aaAgentic | 58.2% | #4 / 15 |
AA Intelligence Independent composite of agentic work, coding, scientific reasoning, and general capability | 57.5% | #8 / 21 |
AA Coding Independent composite of implementation, terminal use, and real-codebase agent performance | 71.5% | #16 / 21 |
hleArtificial Analysis | 39.9% | #22 / 79 |
GPQAArtificial Analysis PhD-level science questions even experts struggle with | 91.2% | #26 / 91 |