AgentWebBench (Centralized Retrieval) - Web Search: leaderboard
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 2030. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 53.77 |
| 2 | GPT-5 Mini | 52.09 |
| 3 | Qwen 3 30B A3B 2507 (Thinking) | 49.9 |
| 4 | DeepSeek V3.2 (Thinking) | 49.37 |
| 5 | Qwen 3 Next 80B A3B (Thinking) | 48.78 |
| 6 | Qwen 3 4B 2507 (Thinking) | 47.65 |
| 7 | Qwen 3 14B | 47.59 |
Interactive version: theaggregate.ai/benchmark?slug=agentwebbench-centralized-retrieval-web-search · How It Works · Data refreshed daily, snapshot 2026-10-07.