GLM-4.6 (Thinking) — benchmark results
GLM-4.6 evaluated with thinking enabled. Provider: Zhipu. Released 2025-09-30. Access: Open.
Unified ELO 1659 ± 26, rank #348 of 1776 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Gorilla API Bench (BFCL) | 72.38 | Overall Accuracy (%) | 96.3 |
| BenchTable | 72.9 | Total Score (%) | 90.4 |
| LLM2014 Code 2025-11 - C# | 8.38 | Score | 84 |
| SpeechMap Compliance | 78 | % Requests Completed | 72.7 |
| LLM2014 Code 2025-11 | 66.81 | Multi-round Score | 68 |
| LLM2014 Code 2025-11 - Golang | 5.7 | Score | 64 |
| LLM2014 Code 2025-11 - Java | 6.87 | Score | 64 |
| LLM2014 Code 2025-11 - Python | 7.22 | Score | 56 |
| LLM2014 Logic 2025-10 | 39.97 | Median Score | 55.1 |
| LLM2014 Code 2025-11 - TypeScript | 6.82 | Score | 52 |
| LLM2014 Logic 2025-11 | 37.69 | Median Score | 51.9 |
| LLM2014 Logic 2025-12 | 33.1 | Median Score | 38 |
Interactive version: theaggregate.ai/model?slug=glm-4-6-thinking · How the rankings work · Data refreshed daily, snapshot 2026-07-22.