New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
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.