GLM-4.7 Flash (Non-reasoning) — benchmark results
GLM-4.7 Flash evaluated with reasoning disabled. Provider: Zhipu. Released 2026-01-19. Access: Open.
Unified ELO 1565 ± 43, rank #579 of 1776 rated models, from 35 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA TAU-2 Bench | 91.81 | Accuracy (%) | 86.9 |
| UGI - Willingness (W/10) | 6.8 | W/10 Score | 66.6 |
| AA IFBench | 46.26 | Accuracy (%) | 54.4 |
| Artificial Analysis Intelligence Index | 15.52 | Intelligence Index | 50.4 |
| AA Omniscience - Software Engineering (SWE) - Julia | 12 | Accuracy (%) | 47.9 |
| UGI Leaderboard | 33.75 | UGI Score | 47.2 |
| UGI - Natural Intelligence | 20.96 | NatInt Score | 45.8 |
| AA Omniscience - Software Engineering (SWE) - Java | 15 | Accuracy (%) | 41.3 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 12 | Accuracy (%) | 31.1 |
| AA SciCode | 25.46 | Accuracy (%) | 30.4 |
| AA Humanity's Last Exam | 4.87 | Accuracy (%) | 30.1 |
| AA Omniscience - Software Engineering (SWE) - Python | 14 | Accuracy (%) | 28.9 |
Interactive version: theaggregate.ai/model?slug=glm-4-7-flash-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.