GLM 5.1 — Benchmarks
Benchmark scores for GLM 5.1 aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Overall rank: #69 of 123 open modelscomposite 44/100 across 8 benchmarks in 4 categories · methodology
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| SciCode | 43.8% | #19 / 50 | #90 / 155 |
Knowledge
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| SimpleQA | 34.0% | #11 / 15 | #47 / 78 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| AIME 2024/2025 | 93.3% | #8 / 74 | #47 / 270 |
| FrontierMath | 33.5% | #2 / 12 | #21 / 101 |
| ProofBench | 22.2% | #6 / 21 | #32 / 64 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| GPQA Diamond | 89.9% | #10 / 83 | #39 / 291 |
| SimpleBench | 55.1% | #5 / 23 | #42 / 101 |
| CritPt | 4.6% | #14 / 50 | #83 / 167 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.