Pricing and context window via OpenRouter, 2026-11-13.
GLM-5.3 uses the same base model as GLM-5.2 with extended post-training, adding cybersecurity-focused training data and improving agentic coding task performance. Weights are set to open source in about two weeks pending security review.
| Benchmark | Score | Rank | Source |
|---|---|---|---|
| AA Intelligence Index | 31.7 index | 21 of 47 | Artificial Analysis, Nov 2026 ↗ |
| Arena Elo | 1483 Elo | 19 of 140 | LMArena, Nov 2026 ↗ |
| GPQA | 91.7% | 27 of 162 | Artificial Analysis, Aug 2026 ↗ |
| Speed (tok/s) | 71 tok/s | 64 of 100 | Artificial Analysis, Nov 2026 ↗ |
Rank is against every model in our database with a sourced score on that benchmark, each counted once with its best score.
Zhipu AI has released GLM-5.3, a coding-focused model built on the same base as GLM-5.2 with additional post-training. The company claims it's the strongest open-weights coding model available, with gains concentrated in agentic and cybersecurity tasks, though independent benchmarks are not yet published.