ChronosBench - Complex Scenes (Guided Prompt): leaderboard
Metric: Task Completion Rate (%; equal-weight mean of positive and negative branches, 54 complex cases, basic prompt plus guidance, thinking disabled). Source: arxiv.org. Saturation forecast: Estimated already saturated. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4 (Non-reasoning) | 72.22 |
| 2 | GPT-4.1 | 61.11 |
| 3 | Qwen 3 8B (Non-reasoning) | 16.67 |
| 4 | Llama 3.1 8B Instruct | 11.11 |
| 5 | Qwen 3 32B (Non-reasoning) | 11.11 |
Interactive version: theaggregate.ai/benchmark?slug=chronosbench-complex-scenes-guided-prompt · How It Works · Data refreshed daily, snapshot 2026-09-25.