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

#ModelScore
1GLM-5.288.7
2GPT-5.580.8
3DeepSeek V4 Flash79.7
4GLM-5.178.1
5Qwen 3.6 27B76.6
6Claude Opus 4.869.8
7Qwen 3.6 35B A3B68.2
8Claude Opus 4.761.2

Interactive version: theaggregate.ai/benchmark?slug=polyworkbench-codex · How It Works · Data refreshed daily, snapshot 2026-09-29.