GLM 4.7 — Benchmarks
Benchmark scores for GLM 4.7 aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Coding
| Benchmark | Score | Rank |
|---|---|---|
| Terminal-Bench | 33.3% | #5 / 11 |
Knowledge
| Benchmark | Score | Rank |
|---|---|---|
| SimpleQA | 31.5% | #3 / 4 |
Math
| Benchmark | Score | Rank |
|---|---|---|
| AIME 2024/2025 | 83.3% | #3 / 22 |
Reasoning
| Benchmark | Score | Rank |
|---|---|---|
| GPQA Diamond | 83.3% | #3 / 28 |
| SimpleBench | 47.7% | #3 / 10 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.