ChronosBench - Complex Scenes (Basic Prompt): leaderboard
Metric: Task Completion Rate (%; equal-weight mean of positive and negative branches, 54 complex cases, basic prompt only, thinking disabled). Source: arxiv.org. Saturation forecast: Around January 2027. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 32B (Non-reasoning) | 16.67 |
| 2 | Qwen 3 8B (Non-reasoning) | 11.11 |
| 3 | Llama 3.1 8B Instruct | 1.85 |
Interactive version: theaggregate.ai/benchmark?slug=chronosbench-complex-scenes-basic-prompt · How It Works · Data refreshed daily, snapshot 2026-09-25.