WorldBench

Progress Over Time

Interactive timeline showing model performance evolution on WorldBench

State-of-the-art frontier
Open
Proprietary

WorldBench Leaderboard

2 models
ContextCostLicense
1
ByteDance
ByteDance
2
Notice missing or incorrect data?
About this benchmark

What is WorldBench?

WorldBench evaluates real-world visual knowledge and understanding across diverse everyday scenes.

WorldBench is a multimodal benchmark evaluating models on knowledge, multimodal, and vision tasks. LLM Stats tracks 2 models on this benchmark, scored on a 0–1 scale. The current average is 0.7, with the leader at 0.7.

Compare leaders on the best AI for knowledge, best AI for multimodal and best AI for vision leaderboards.

Current leaders

Seed 2.1 Pro from ByteDance currently leads the WorldBench leaderboard with a score of 0.676 across 2 evaluated AI models.

1Seed 2.1 ProByteDance67.6%
2Seed 2.1 TurboByteDance63.7%

FAQ

Common questions about the WorldBench benchmark and leaderboard.

What is the WorldBench benchmark?

WorldBench evaluates real-world visual knowledge and understanding across diverse everyday scenes.

What is the WorldBench leaderboard?

The WorldBench leaderboard ranks 2 AI models based on their performance on this benchmark. Currently, Seed 2.1 Pro by ByteDance leads with a score of 0.676. The average score across all models is 0.657.

What is the highest WorldBench score?

The highest WorldBench score is 0.676, achieved by Seed 2.1 Pro from ByteDance.

How many models are evaluated on WorldBench?

2 models have been evaluated on the WorldBench benchmark, with 0 verified results and 2 self-reported results.

What categories does WorldBench cover?

WorldBench is categorized under knowledge, multimodal, and vision. The benchmark evaluates multimodal models.

How recent are the WorldBench leaderboard results?

The WorldBench leaderboard was last updated in July 2026 and currently includes 2 evaluated models.