TIDE-Bench - ExpoDesign: leaderboard
Metric: Overall judge score (1-5): mean of the experimental-design, tool-success and result-conclusion consistency scores (each 1-5) a kimi-k2-0905-preview judge gives the structured experiment card the system builds, with search and Python tools, from a paper-agnostic research brief (TIDE-Bench ExpoDesign track, STEM and computer-science papers); higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 4.79 |
| 2 | GPT-5 | 4.68 |
| 3 | Qwen 3 32B | 3.03 |
| 4 | Qwen 3 8B | 2.98 |
| 5 | Qwen 3 4B | 2.83 |
| 6 | GPT-4o | 2.52 |
Interactive version: theaggregate.ai/benchmark?slug=tide-bench-expodesign · How It Works · Data refreshed daily, snapshot 2026-10-07.