LLM Stats (EgoSchema): leaderboard
5,031 temporal reasoning questions over 3-minute egocentric videos requiring understanding of long-range activities and event sequences.
Metric: Score (%). Source: llm-stats.com. Saturation forecast: Estimated already saturated. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 VL 72B Instruct | 76.2 | #377 |
| 2 | GPT-4o | 72.2 | #343 |
| 3 | Nova Pro | 72.1 | #569 |
| 4 | Gemini 2.0 Flash | 71.5 | #342 |
| 5 | Nova Lite | 71.4 | #754 |
| 6 | Qwen2.5-Omni-7B | 68.6 | #624 |
| 7 | Gemini 2.0 Flash Lite | 67.2 | #450 |
| 8 | Gemini 1.0 Pro | 55.7 | #933 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-egoschema · How It Works · Data refreshed daily, snapshot 2026-10-20.