UR-FUNNY-Temporal - Laughter Detection: leaderboard

Laughter detection on UR-FUNNY-Temporal (2026), TED talk clips from UR-FUNNY-V2 with temporal laughter annotations: a zero-shot model is asked whether laughter occurs in a 5-second video clip and, if so, when it starts and ends. F1 of the laughter or no-laughter decision over all test clips, times 100; higher is better.

Metric: UR-FUNNY-Temporal laughter detection F1 (times 100, so 0-100) over all test segments: the model is prompted, zero-shot, to say whether laughter occurs in a 5-second video segment, on the UR-FUNNY-Temporal test split (TED talk clips of UR-FUNNY-V2); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 3 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3 Flash77.5#180
2Qwen2.5-Omni-7B77.3#1888
3MTLLFM Qwen2-Audio-7B (checkpoint unspecified)46.6

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=ur-funny-temporal-laughter-detection · How It Works · Data refreshed daily, snapshot 2026-11-22.