Video-Holmes — leaderboard

Complex video reasoning benchmark over suspense short films, requiring models to actively find and connect clues across video segments.

Metric: Overall (self-reported). Source: benchmarklist.com. Status: saturation imminent. 16 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro45
2Gemini 2.0 Flash (Thinking)43.1
3GPT-4o42
4Gemini 1.5 Pro41.2
5Claude 3.7 Sonnet41
6Claude 3.5 Sonnet39.3
7InternVL3-8B32.3
8Gemini 2.0 Flash30.6
9O4 Mini29.9
10Qwen2.5-Omni-7B16.4

Interactive version: theaggregate.ai/benchmark?slug=video-holmes · How the rankings work · Data refreshed daily, snapshot 2026-07-22.