CalBench - Uniform Costs - Coordination: leaderboard
Metric: Coordination (%). Source: arxiv.org. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.6 Plus | 93.33 |
| 2 | DeepSeek V4 Pro | 89.63 |
| 3 | Gemini 3 Flash (Preview) | 86.17 |
| 4 | Gemini 3.1 Pro (Preview) | 85.93 |
| 5 | Claude Sonnet 4.6 | 84.69 |
| 6 | GPT-5.4 Mini | 83.21 |
| 7 | Llama 4 Maverick Instruct | 77.04 |
Interactive version: theaggregate.ai/benchmark?slug=calbench-uniform-costs-coordination · How It Works · Data refreshed daily, snapshot 2026-09-19.