CollabBench Cook - Game Score: leaderboard
Metric: Final game score of the two-agent kitchen team (completed dish orders), Cook-MultiPlayer (Overcooked-style cooperative cooking, five kitchen scenarios): the evaluated model drives Agent 1 inside the ProAgent framework while a DeepSeek-V3.1 simulator role-plays a partner with a Big Five personality profile; mean over all evaluation trajectories; higher is better. Source: arxiv.org. Saturation forecast: Around April 2027. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3.1 | 136.53 |
| 2 | Qwen 2.5 72B Instruct | 135.47 |
| 3 | GPT-5.2 | 135.2 |
| 4 | Qwen 2.5 7B Instruct | 86.93 |
Interactive version: theaggregate.ai/benchmark?slug=collabbench-cook-game-score · How It Works · Data refreshed daily, snapshot 2026-09-29.