CoCoBench - Sequential Ordering: leaderboard
CoCoBench (2026) evaluates multimodal LLMs as centralized planners for two to four cooperating embodied agents on 897 executable household tasks. Task success rate in percent, higher is better, on the sequential-ordering instances, where a final action must wait for the other agents.
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: Estimated already saturated. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.8 | 94.7 | #56 |
| 2 | GPT-5.6 Sol | 90.2 | #29 |
| 3 | Qwen 3.6 Plus | 61.8 | #217 |
| 4 | Claude Haiku 4.5 | 47.1 | #568 |
| 5 | Qwen 3.5 9B | 37.8 | #803 |
| 6 | GPT-5.4 Mini | 30.7 | #389 |
| 7 | Qwen 3 VL 8B Instruct | 4.9 | #982 |
| 8 | Kimi K2.6 | 3.6 | #173 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=cocobench-sequential-ordering · How It Works · Data refreshed daily, snapshot 2026-11-12.