The AI arena is free today

Open Superagent

WebArena-Verified

Implementation

Progress Over Time

Interactive timeline showing model performance evolution on WebArena-Verified

State-of-the-art frontier
Open
Proprietary

WebArena-Verified Leaderboard

1 models
ContextCostLicense
1
Alibaba Cloud / Qwen Team
Alibaba Cloud / Qwen Team
28B
Notice missing or incorrect data?
About this benchmark

What is WebArena-Verified?

WebArena-Verified evaluates browser agents on realistic web tasks using a verified task set and execution-based grading.

WebArena-Verified is a multimodal benchmark evaluating models on multimodal, agents, 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 multimodal, best AI for agents and best AI for vision leaderboards.

Current leaders

Qwen3.8-27B from Alibaba Cloud / Qwen Team currently leads the WebArena-Verified leaderboard with a score of 0.648 across 1 evaluated AI models.

1Qwen3.8-27BAlibaba Cloud / Qwen Team64.8%

FAQ

Common questions about the WebArena-Verified benchmark and leaderboard.

What is the WebArena-Verified benchmark?

WebArena-Verified evaluates browser agents on realistic web tasks using a verified task set and execution-based grading.

What is the WebArena-Verified leaderboard?

The WebArena-Verified leaderboard ranks 1 AI models based on their performance on this benchmark. Currently, Qwen3.8-27B by Alibaba Cloud / Qwen Team leads with a score of 0.648. The average score across all models is 0.648.

What is the highest WebArena-Verified score?

The highest WebArena-Verified score is 0.648, achieved by Qwen3.8-27B from Alibaba Cloud / Qwen Team.

How many models are evaluated on WebArena-Verified?

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

Where can I find the WebArena-Verified dataset?

The WebArena-Verified dataset is available at https://github.com/ServiceNow/webarena-verified.

What categories does WebArena-Verified cover?

WebArena-Verified is categorized under multimodal, agents, and vision. The benchmark evaluates multimodal models.

What is the best open-source model on WebArena-Verified?

Qwen3.8-27B by Alibaba Cloud / Qwen Team is the top-ranked open-source model on WebArena-Verified, with a score of 0.648 (rank #1).

How recent are the WebArena-Verified leaderboard results?

The WebArena-Verified leaderboard was last updated in August 2026 and currently includes 1 evaluated models.