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.
Overall rank: #18 of 123 open modelscomposite 64.5/100 across 9 benchmarks in 4 categories · methodology
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| Terminal-Bench | 52.4% | #1 / 16 | #22 / 57 |
| SWE-bench Verified | 72.8% | #2 / 16 | #27 / 162 |
| SWE-bench Multilingual | 69.7% | #1 / 4 | #4 / 13 |
Knowledge
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| MMLU-Pro | 86.0% | #5 / 119 | #30 / 259 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| AIME 2024/2025 | 80.0% | #22 / 74 | #104 / 270 |
| FrontierMath | 16.4% | #6 / 12 | #48 / 101 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| GPQA Diamond | 87.8% | #14 / 83 | #57 / 291 |
| ARC-AGI | 44.7% | #10 / 16 | #117 / 200 |
| SimpleBench | 53.2% | #6 / 23 | #46 / 101 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.