All benchmarks

QwenWorldBench

Progress Over Time

Interactive timeline showing model performance evolution on QwenWorldBench

State-of-the-art frontier
Open
Proprietary

QwenWorldBench Leaderboard

2 models
ContextCostLicense
1
Alibaba Cloud / Qwen Team
Qwen3.7-Plus
Alibaba Cloud / Qwen Team
—1.0M$0.32 / $1.28
2
Alibaba Cloud / Qwen Team
Qwen3.7 Max
Alibaba Cloud / Qwen Team
—1.0M$1.25 / $3.75
Notice missing or incorrect data?
About this benchmark

What is QwenWorldBench?

QwenWorldBench is Qwen's internal benchmark for evaluating LLMs as world models that simulate agentic environments across Terminal, SWE, MCP, Search, OS, Android, and Web domains.

QwenWorldBench is a text benchmark evaluating models on reasoning, simulation, and agents tasks. LLM Stats tracks 2 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 reasoning, best AI for simulation and best AI for agents leaderboards.

Current leaders

Qwen3.7-Plus from Alibaba Cloud / Qwen Team currently leads the QwenWorldBench leaderboard with a score of 0.621 across 2 evaluated AI models.

1Qwen3.7-PlusAlibaba Cloud / Qwen Team62.1%
2Qwen3.7 MaxAlibaba Cloud / Qwen Team57.3%

FAQ

Common questions about the QwenWorldBench benchmark and leaderboard.

What is the QwenWorldBench benchmark?

QwenWorldBench is Qwen's internal benchmark for evaluating LLMs as world models that simulate agentic environments across Terminal, SWE, MCP, Search, OS, Android, and Web domains.

What is the QwenWorldBench leaderboard?

The QwenWorldBench leaderboard ranks 2 AI models based on their performance on this benchmark. Currently, Qwen3.7-Plus by Alibaba Cloud / Qwen Team leads with a score of 0.621. The average score across all models is 0.597.

What is the highest QwenWorldBench score?

The highest QwenWorldBench score is 0.621, achieved by Qwen3.7-Plus from Alibaba Cloud / Qwen Team.

How many models are evaluated on QwenWorldBench?

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

What categories does QwenWorldBench cover?

QwenWorldBench is categorized under reasoning, simulation, and agents. The benchmark evaluates text models.

Which model offers the best value on QwenWorldBench?

Among models scoring within 10% of the leader, Qwen3.7-Plus from Alibaba Cloud / Qwen Team is the cheapest, at $0.32 per million input tokens with a score of 0.621.

How recent are the QwenWorldBench leaderboard results?

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