GLM-5.2 FP8: benchmark results
Provider: Zhipu. Released 2026-06-13. Access: Open.
Aggregate Rating 1700 ± 24, rank #196 of 1656 rated models, from 27 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Coding Agent Leaderboard - Shellbench (OpenClaw) | 18.7 | Score (%) | 100 |
| ProductWebBench - Repair | 65.61 | Rate (%) | 100 |
| TuRTLe - Icarus Power | 72.08 | Average Score (%) | 90.9 |
| TuRTLe - Icarus Area | 73.05 | Average Score (%) | 88.6 |
| TuRTLe - Icarus Functionality | 73.07 | Average Score (%) | 88.6 |
| TuRTLe - Verilator Power | 71.3 | Average Score (%) | 88.6 |
| TuRTLe - Icarus Performance | 70.43 | Average Score (%) | 86.4 |
| TuRTLe - Icarus Synthesis | 71.89 | Average Score (%) | 86.4 |
| TuRTLe - Verilator Area | 71.85 | Average Score (%) | 86.4 |
| TuRTLe - Verilator Functionality | 73.35 | Average Score (%) | 86.4 |
| TuRTLe - Verilator Performance | 69.34 | Average Score (%) | 86.4 |
| TuRTLe - Verilator Synthesis | 70.39 | Average Score (%) | 86.4 |
Interactive version: theaggregate.ai/model?slug=glm-5-2-fp8 · How It Works · Data refreshed daily, snapshot 2026-10-25.