RankingAutomationBench (v1.0.6) · v1.0.6
AutomationBench (v1.0.6) · v1.0.6
- Bucket
- Agentic
- Unit
- percent
- Direction
- Higher is better
- Version
- v1.0.6
- Display harness
- zai-org/GLM-5.3
- Board
- https://huggingface.co/zai-org/GLM-5.3
Compare published benchmark results with category weights →
Models
| Model | Score | Harness | Evidence | Source-recorded date |
|---|---|---|---|---|
| GLM-5.3Z.ai | 48.2%Reported settings & sourceGLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details. First-party reported result. zai-org/GLM-5.3 · Performance table: AutomationBench (v1.0.6) · reviewed 2026-09-12 | zai-org/GLM-5.3 | lab self-report | 2026-09-12 |
| Kimi K3Moonshot | 46.7%Reported settings & sourceGLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details. First-party reported result. zai-org/GLM-5.3 · Performance table: AutomationBench (v1.0.6) · reviewed 2026-09-12 | zai-org/GLM-5.3 | lab self-report | 2026-09-12 |
| Claude Fable 5Anthropic | 46.2%Reported settings & sourceGLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details. First-party reported result. Comparison limit: The source column includes fallback execution without a documented exact effort. zai-org/GLM-5.3 · Performance table: AutomationBench (v1.0.6) · reviewed 2026-09-12 | zai-org/GLM-5.3 | lab self-report | 2026-09-12 |
| GPT-5.6 SolOpenAI | 45.8%Reported settings & sourceGLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details. First-party reported result. zai-org/GLM-5.3 · Performance table: AutomationBench (v1.0.6) · reviewed 2026-09-12 | zai-org/GLM-5.3 | lab self-report | 2026-09-12 |
| DeepSeek V4-Pro 0813DeepSeek | 43.2%Reported settings & sourceGLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details. First-party reported result. zai-org/GLM-5.3 · Performance table: AutomationBench (v1.0.6) · reviewed 2026-09-12 | zai-org/GLM-5.3 | lab self-report | 2026-09-12 |
| Claude Opus 4.8Anthropic | 41%Reported settings & sourceGLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details. First-party reported result. zai-org/GLM-5.3 · Performance table: AutomationBench (v1.0.6) · reviewed 2026-09-12 | zai-org/GLM-5.3 | lab self-report | 2026-09-12 |
| Qwen 3.8-MaxQwen | 39.8%Reported settings & sourceGLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details. First-party reported result. zai-org/GLM-5.3 · Performance table: AutomationBench (v1.0.6) · reviewed 2026-09-12 | zai-org/GLM-5.3 | lab self-report | 2026-09-12 |
| GLM-5.2Z.ai | 26.2%Reported settings & sourceGLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details. First-party reported result. zai-org/GLM-5.3 · Performance table: AutomationBench (v1.0.6) · reviewed 2026-09-12 | zai-org/GLM-5.3 | lab self-report | 2026-09-12 |