GLM-5.1 (Thinking): benchmark results
Zhipu GLM-5.1 evaluated with thinking enabled. Provider: Zhipu. Released 2026-03-27. Access: Open.
Aggregate Rating 1696 ± 9, rank #374 of 2168 rated models, from 172 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| PortBench-QA - Rebalancing | 88.2 | Item score (%; rebalance-or-hold decision with the correctiv | 100 |
| SKT A.X K2 Card - BrowseComp (10 Searches Max) | 29.1 | Accuracy (%) | 100 |
| Tau2-Bench Telecom | 97.66 | Success Rate (%) | 98.1 |
| AA TAU-2 Bench | 97.66 | Accuracy (%) | 97.9 |
| AA IFBench | 76.26 | Accuracy (%) | 95.1 |
| UGI Leaderboard | 52.88 | UGI Score | 93.9 |
| Wolfram LLM Benchmarking Project | 67.8 | Correct Functionality (%) | 92.9 |
| AA-Omniscience Hallucination Rate | 29.95 | Hallucination Rate (%) | 92.7 |
| UGI - Writing | 61.74 | Writing Score | 92.5 |
| UGI - Natural Intelligence | 57.47 | NatInt Score | 91.2 |
| AA Omniscience - Software Engineering (SWE) - JavaScript | 49.09 | Accuracy (%) | 91 |
| AA Terminal-Bench Hard | 43.18 | Accuracy (%) | 90.3 |
Interactive version: theaggregate.ai/model?slug=glm-5-1-thinking · How It Works · Data refreshed daily, snapshot 2026-10-20.