AgentWebBench (Centralized Retrieval) - Web Search: leaderboard

AgentWebBench (2026) models the Agentic Web: a user agent serves information needs over 100 ClueWeb22-B websites by coordinating with content agents or tools that each cover one website, with every LLM in thinking mode. This board is NDCG@5 in percent on MS MARCO web search queries whose relevant documents lie in the corpus, under centralized retrieval over one index of all websites, the reference without access constraints; higher is better.

Metric: NDCG@5 (%) on 354 MS MARCO Web Search queries whose relevant documents lie in the 100-website ClueWeb22-B corpus, LLM user agent under centralized retrieval (the agent retrieves from one index over all 100 websites, the no-access-constraint reference), thinking mode on; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 7 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1Gemini 3 Flash (Preview)53.77#152
2GPT-5 Mini52.09#364
3Qwen 3 30B A3B 2507 (Thinking)49.9#764
4DeepSeek V3.2Thinking49.37#419
5Qwen 3 Next 80B A3B (Thinking)48.78#594
6Qwen 3 4B 2507 (Thinking)47.65#1433
7Qwen 3 14B47.59#1269

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=agentwebbench-centralized-retrieval-web-search · How It Works · Data refreshed daily, snapshot 2026-11-21.