All benchmarks

ActivityNet

PaperImplementation

Progress Over Time

Interactive timeline showing model performance evolution on ActivityNet

State-of-the-art frontier
Open
Proprietary

ActivityNet Leaderboard

1 models
ContextCostLicense
1
OpenAI
GPT-4o
OpenAI
—128K$2.50 / $10.00
Notice missing or incorrect data?
About this benchmark

What is ActivityNet?

A large-scale video benchmark for human activity understanding. Provides samples from 203 activity classes with an average of 137 untrimmed videos per class and 1.41 activity instances per video, for a total of 849 video hours. The benchmark covers a wide range of complex human activities that are of interest to people in their daily living and can be used to compare algorithms for three scenarios: untrimmed video classification, trimmed activity classification, and activity detection.

ActivityNet is a video benchmark evaluating models on video and vision tasks. LLM Stats tracks 1 models on this benchmark, scored on a 0–1 scale. The current average is 0.6, with the leader at 0.6.

Compare leaders on the best AI for video and best AI for vision leaderboards.

Current leaders

GPT-4o from OpenAI currently leads the ActivityNet leaderboard with a score of 0.619 across 1 evaluated AI models.

1GPT-4oOpenAI61.9%

FAQ

Common questions about the ActivityNet benchmark and leaderboard.

What is the ActivityNet benchmark?

A large-scale video benchmark for human activity understanding. Provides samples from 203 activity classes with an average of 137 untrimmed videos per class and 1.41 activity instances per video, for a total of 849 video hours. The benchmark covers a wide range of complex human activities that are of interest to people in their daily living and can be used to compare algorithms for three scenarios: untrimmed video classification, trimmed activity classification, and activity detection.

What is the ActivityNet leaderboard?

The ActivityNet leaderboard ranks 1 AI models based on their performance on this benchmark. Currently, GPT-4o by OpenAI leads with a score of 0.619. The average score across all models is 0.619.

What is the highest ActivityNet score?

The highest ActivityNet score is 0.619, achieved by GPT-4o from OpenAI.

How many models are evaluated on ActivityNet?

1 models have been evaluated on the ActivityNet benchmark, with 0 verified results and 1 self-reported results.

Where can I find the ActivityNet paper?

The ActivityNet paper is available at https://openaccess.thecvf.com/content_cvpr_2015/html/Heilbron_ActivityNet_A_Large-Scale_2015_CVPR_paper.html. The paper details the methodology, dataset construction, and evaluation criteria.

Where can I find the ActivityNet dataset?

The ActivityNet dataset is available at https://github.com/activitynet/ActivityNet.

What categories does ActivityNet cover?

ActivityNet is categorized under video and vision. The benchmark evaluates video models.

Which model offers the best value on ActivityNet?

Among models scoring within 10% of the leader, GPT-4o from OpenAI is the cheapest, at $2.50 per million input tokens with a score of 0.619.

How recent are the ActivityNet leaderboard results?

The ActivityNet leaderboard was last updated in July 2026 and currently includes 1 evaluated models.