// BENCHMARK

WebWalkerQA benchmark

AI model leaderboard for the WebWalkerQA benchmark. Compare how large language models score on WebWalkerQA, see the full ranking, and understand what this AI benchmark measures. Tongyi DeepResearch currently leads with 72.2. Agentic web-navigation QA — agent must traverse web pages to find answers to multi-hop questions.

Leaderboard

# Model Organization Score Variant Source
#1 Tongyi DeepResearch Alibaba-NLP 72.2 react-avg@3 official ↗
#2 o3 OpenAI 71.7 react-cited-tongyi official ↗
#3 GLM 4.5 Zhipu AI 65.6 react-cited-tongyi official ↗
#4 Kimi K2 Moonshot 63 react-cited-tongyi official ↗
#5 Claude Sonnet 4 Anthropic 61.7 react-cited-tongyi official ↗
#6 DeepSeek-V3.1 DeepSeek 61.2 react-cited-tongyi official ↗

Frequently asked questions about WebWalkerQA

What is the WebWalkerQA benchmark?

Agentic web-navigation QA — agent must traverse web pages to find answers to multi-hop questions.

How is the WebWalkerQA benchmark scored?

WebWalkerQA is scored using the accuracy metric, where a higher score is better. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.

Which AI model scores highest on WebWalkerQA?

As of the latest reported scores on GenAIList, Tongyi DeepResearch achieves the highest result on WebWalkerQA with a score of 72.2.

Is a higher WebWalkerQA score better?

Yes. On WebWalkerQA a higher score indicates better performance, so models near the top of the leaderboard are the strongest.