GLM-5.1 (Thinking) — benchmark results
Zhipu GLM-5.1 evaluated with thinking enabled. Provider: Zhipu. Released 2026-04-07. Access: Open.
Unified ELO 1812 ± 17, rank #129 of 1776 rated models, from 82 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA TAU-2 Bench | 97.66 | Accuracy (%) | 97.9 |
| Wolfram LLM Benchmarking Project | 67.8 | Correct Functionality (%) | 97 |
| AA IFBench | 76.26 | Accuracy (%) | 95.1 |
| UGI - Writing | 61.74 | Writing Score | 94.5 |
| UGI Leaderboard | 52.88 | UGI Score | 94.5 |
| UGI - Natural Intelligence | 57.47 | NatInt Score | 93.6 |
| Artificial Analysis Intelligence Index | 40.16 | Intelligence Index | 90.4 |
| AA Terminal-Bench Hard | 43.18 | Accuracy (%) | 90.3 |
| Qwen3.7 Launch - IFEval | 94.5 | Score (%) | 90 |
| AA Omniscience | 1.93 | Score | 88.2 |
| AA Humanity's Last Exam | 28.04 | Accuracy (%) | 88.1 |
| AA GPQA Diamond | 86.77 | Accuracy (%) | 87.7 |
Interactive version: theaggregate.ai/model?slug=glm-5-1-thinking · How the rankings work · Data refreshed daily, snapshot 2026-07-22.