GLM-5-Turbo: benchmark results
Zhipu's speed-oriented GLM-5 Turbo variant. Provider: Zhipu. Released 2026-03-15. Access: API.
Aggregate Rating 1749 ± 11, rank #120 of 1656 rated models, from 240 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| GABench - Open-Ended QA - Insight (Text-Paired Graphs) | 14.29 | Task success rate (%; share of tasks whose final answer a De | 100 |
| GABench - Open-Ended QA - Prediction (Text-Attributed Graphs) | 10.47 | Task success rate (%; share of tasks whose final answer a De | 100 |
| GABench - Open-Ended QA - Prediction (Text-Paired Graphs) | 12.5 | Task success rate (%; share of tasks whose final answer a De | 100 |
| PinchBench - 123 Tasks - OpenClaw 2026.4.5 (3e72c03) | 86.3 | Best Official Run Score (%) | 100 |
| AGC-Bench - historical_analogy | 1.94 | Dataset z-score | 99.4 |
| AGC-Bench - ttcw | 2.27 | Dataset z-score | 99.4 |
| Tau2-Bench Telecom | 98.54 | Success Rate (%) | 99.2 |
| AA TAU-2 Bench | 98.54 | Accuracy (%) | 99 |
| AGC-Bench - riddlesense | 1.15 | Dataset z-score | 98.8 |
| AGC-Bench - cue_word_story | 1.15 | Dataset z-score | 97.6 |
| AGC-Bench - ocw_connections | 1.15 | Dataset z-score | 97.6 |
| AGC-Bench - scar | 1 | Dataset z-score | 97.6 |
Interactive version: theaggregate.ai/model?slug=glm-5-turbo · How It Works · Data refreshed daily, snapshot 2026-10-21.