AgentWebBench (Multi-Agent Coordination) - 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 multi-agent coordination, the user agent exchanging messages with content agents that search their own sites; 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 multi-agent coordination (the user agent plans multi-turn exchanges with website content agents, which retrieve within their own site and answer in natural language), thinking mode on; higher is better. Source: arxiv.org. Saturation forecast: Around October 2027. 7 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 47.08 | #152 | |
| 2 | GPT-5 Mini | 42.3 | #364 | |
| 3 | DeepSeek V3.2 | Thinking | 34.23 | #419 |
| 4 | Qwen 3 Next 80B A3B (Thinking) | 34.04 | #594 | |
| 5 | Qwen 3 30B A3B 2507 (Thinking) | 29.72 | #764 | |
| 6 | Qwen 3 14B | 27.9 | #1269 | |
| 7 | Qwen 3 4B 2507 (Thinking) | 27.04 | #1433 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=agentwebbench-multi-agent-coordination-web-search · How It Works · Data refreshed daily, snapshot 2026-11-21.