Z.aiGLM-4 (GLM-4.7 series)
GLM-4.7
Z.ai · GLM-4 (GLM-4.7 series). Released Dec 22, 2025.
GLM-4.7 is a model from Z.ai in the GLM-4 (GLM-4.7 series) family, released Dec 22, 2025. evals.report tracks 16 reported GLM-4.7 benchmark scores across SWE-bench Verified, GPQA Diamond, Humanity's Last Exam, PostTrainBench, Artificial Analysis Intelligence Index, Epoch Capabilities Index, SWE-rebench, MMLU-Pro, and 8 more — each shown with its benchmark, metric, source status, and date, and never combined into a single ranking.
Open16 results
Benchmark results 16
Compare this model| Benchmark | Category | Score | Metric | Status | Date | |
|---|---|---|---|---|---|---|
| SWE-bench Verified | Coding | 73.8% | % resolved | Verified | Dec 22, 2025 | Details |
| GPQA Diamond | Reasoning | 85.7% | accuracy | Verified | Dec 22, 2025 | Details |
| Humanity's Last Exam | Reasoning | 24.8% | accuracy | Verified | Dec 22, 2025 | Details |
| PostTrainBench | Agents | 7.48% | weighted average score | Official | Dec 22, 2025 | Details |
| Artificial Analysis Intelligence Index | Reasoning | 42.1 | Index | Unverified | Dec 22, 2025 | Details |
| Epoch Capabilities Index | Reasoning | 144.6 | Index | Official | Dec 22, 2025 | Details |
| SWE-rebench | Coding | 58.7% | Resolved rate (pass@1) | Unverified | Dec 22, 2025 | Details |
| MMLU-Pro | Reasoning | 85.6% | accuracy | Verified | Dec 22, 2025 | Details |
| GDPval | Agents | 1185 | Elo | Official | Dec 22, 2025 | Details |
| SciCode | Coding | 45.1% | accuracy | Unverified | Dec 22, 2025 | Details |
| Global-MMLU | Reasoning | 79.9% | accuracy | Unverified | Dec 22, 2025 | Details |
| WebDev Arena | Chat preference | 1440 | Elo | Verified | Dec 22, 2025 | Details |
| EQ-Bench Creative Writing v3 | Chat preference | 1403 | Elo | Verified | Dec 22, 2025 | Details |
| Design Arena | Chat preference | 1273 | Elo | Verified | Dec 22, 2025 | Details |
| Vectara Hallucination Leaderboard | Other | 11.7% | Hallucination Rate | Official | Dec 22, 2025 | Details |
| Terminal-Bench 2.0 | Agents | 41.0% | task success | Verified | Dec 22, 2025 | Details |