GLM 4.6 — Benchmarks
Benchmark scores for GLM 4.6 aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Overall rank: #118 of 123 open modelscomposite 17.2/100 across 6 benchmarks in 3 categories · methodology
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| Terminal-Bench | 24.5% | #12 / 16 | #49 / 57 |
| SciCode | 38.4% | #27 / 50 | #119 / 155 |
| SWE-bench Verified | 68.2% | #7 / 16 | #50 / 162 |
| SWE-bench Bash Only | 55.4% | #5 / 9 | #32 / 48 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| FrontierMath | 3.8% | #8 / 12 | #76 / 101 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| CritPt | 1.1% | #26 / 50 | #109 / 167 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.