GLM 5 — Benchmarks
Benchmark scores for GLM 5 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 |
|---|---|---|
| SWE-bench Verified | 72.1% | #2 / 2 |
| Terminal-Bench | 52.4% | #1 / 11 |
Math
| Benchmark | Score | Rank |
|---|---|---|
| AIME 2024/2025 | 80.0% | #4 / 22 |
| FrontierMath | 16.4% | #2 / 3 |
Reasoning
| Benchmark | Score | Rank |
|---|---|---|
| GPQA Diamond | 87.8% | #1 / 28 |
| ARC-AGI | 44.7% | #2 / 7 |
| SimpleBench | 53.2% | #2 / 10 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.