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.
Overall rank: #87 of 123 open modelscomposite 36.1/100 across 9 benchmarks in 4 categories · methodology
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| Terminal-Bench | 33.4% | #8 / 16 | #40 / 57 |
| SciCode | 45.1% | #16 / 50 | #85 / 155 |
Knowledge
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| SimpleQA | 32.2% | #13 / 15 | #55 / 78 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| AIME 2024/2025 | 83.3% | #19 / 74 | #91 / 270 |
| FrontierMath | 2.4% | #9 / 12 | #82 / 101 |
| ProofBench | 6.0% | #16 / 21 | #56 / 64 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| GPQA Diamond | 83.3% | #20 / 83 | #94 / 291 |
| SimpleBench | 47.7% | #9 / 23 | #54 / 101 |
| CritPt | 1.7% | #22 / 50 | #100 / 167 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.