This model is 14 months old. A newer version of it has since shipped: GLM-5.3-FlashX-Legal (2026-11-02). The details below are still accurate for this model. It just is not what we would recommend today.
GLM-4.6
Zhipu AI🇨🇳 China
Zhipu AI open-weights model focused on coding and agentic tasks.
Context window205K tokens
Input / 1M tokens$0.5
Output / 1M tokens$2
Pricing and context window via OpenRouter, 2026-11-15.
Version History
launchmajor
GLM-4.6 released. Zhipu AI open-weights model focused on coding and agentic tasks.
Benchmark Scores
Full leaderboard →| Benchmark | Score | Rank | Source |
|---|---|---|---|
| Arena Elo | 1424 Elo | 81 of 141 | LMArena, Nov 2026 ↗ |
| GPQA | 63.2% | 146 of 163 | Artificial Analysis, Jul 2026 ↗ |
| SWE-bench Verified | 68.0% | 65 of 80 | llm-stats, Jul 2026 ↗ |
| Hallucination (Summarization) (lower is better) | 9.5% | 22 of 49 | Vectara, Nov 2026 ↗ |
| MMLU-Pro | 78.4% | 49 of 74 | Artificial Analysis, Jul 2026 ↗ |
| LiveCodeBench | 56.1% | 39 of 48 | Artificial Analysis, Jul 2026 ↗ |
Rank is against every model in our database with a sourced score on that benchmark, each counted once with its best score.