GLM-4.7 (Non-reasoning): benchmark results
GLM-4.7 evaluated with reasoning disabled. Provider: Zhipu. Released 2025-12-22. Access: Open.
Unified ELO 1554 ± 1, rank #617 of 1761 rated models, from 58 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA TAU-2 Bench | 94.15 | Accuracy (%) | 92 |
| AA Omniscience - Software Engineering (SWE) - PHP | 44 | Accuracy (%) | 88.9 |
| UGI Leaderboard | 49.36 | UGI Score | 88.6 |
| UGI - Natural Intelligence | 42.52 | NatInt Score | 87.5 |
| AA Omniscience - Software Engineering (SWE) - Go | 32 | Accuracy (%) | 85.5 |
| UGI - Writing | 44.16 | Writing Score | 84.5 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 30 | Accuracy (%) | 84.1 |
| AA Omniscience - Software Engineering (SWE) - Swift | 48 | Accuracy (%) | 82.4 |
| AA Omniscience - Software Engineering (SWE) - TypeScript | 33.33 | Accuracy (%) | 79.4 |
| AA Omniscience - Software Engineering (SWE) - C | 48 | Accuracy (%) | 78.3 |
| AA Omniscience - Software Engineering (SWE) - Python | 27.5 | Accuracy (%) | 78 |
| AA Omniscience - Software Engineering (SWE) - Java | 21 | Accuracy (%) | 77.3 |
Interactive version: theaggregate.ai/model?slug=glm-4-7-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.