ExtremeWhenBench: leaderboard
Metric: Mean IoU x 100 (0-100) between the predicted and gold time intervals over the 2,273 queries on full hour-scale videos, each model at its best frame budget within its context limit (GPT-5.4: 64 frames as 8x8 grids; Gemini: raw video), parse failures scored 0; higher is better. Source: arxiv.org. Saturation forecast: Around 2031. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.5 Flash | 11.5 |
| 2 | Qwen 3.5 9B | 11 |
| 3 | Gemini 2.5 Flash | 5.3 |
| 4 | GPT-5.4 | 1.3 |
| 5 | InternVL3.5-8B | 0.3 |
Interactive version: theaggregate.ai/benchmark?slug=extremewhenbench · How It Works · Data refreshed daily, snapshot 2026-09-29.