PolyWorkBench (Codex): leaderboard
Metric: Mean Grade (%; weighted deterministic rubric checks of the output artefacts, mean over 67 multilingual long-horizon workplace tasks in five domains; best of up to three runs, Pass@1; the OpenAI Codex CLI in full-access mode, 1,800 s per task). Source: arxiv.org. Saturation forecast: Around December 2026. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GLM-5.2 | 88.7 |
| 2 | GPT-5.5 | 80.8 |
| 3 | DeepSeek V4 Flash | 79.7 |
| 4 | GLM-5.1 | 78.1 |
| 5 | Qwen 3.6 27B | 76.6 |
| 6 | Claude Opus 4.8 | 69.8 |
| 7 | Qwen 3.6 35B A3B | 68.2 |
| 8 | Claude Opus 4.7 | 61.2 |
Interactive version: theaggregate.ai/benchmark?slug=polyworkbench-codex · How It Works · Data refreshed daily, snapshot 2026-09-29.