CoCoBench - Sequential Ordering: leaderboard
Metric: Task success rate (%; sequential-ordering instances, respecting ordering constraints between agents; 897 oracle-validated executable household multi-agent task instances with two to four agents, centralized planner with image observations, task-specific step budgets). Source: arxiv.org. Saturation forecast: Around December 2026. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.8 | 94.7 |
| 2 | GPT-5.6 Sol | 90.2 |
| 3 | Qwen 3.6 Plus | 61.8 |
| 4 | Claude Haiku 4.5 | 47.1 |
| 5 | Qwen 3.5 9B | 37.8 |
| 6 | GPT-5.4 Mini | 30.7 |
| 7 | Qwen 3 VL 8B Instruct | 4.9 |
| 8 | Kimi K2.6 | 3.6 |
Interactive version: theaggregate.ai/benchmark?slug=cocobench-sequential-ordering · How It Works · Data refreshed daily, snapshot 2026-09-26.