SearchAgent - HotpotQA: leaderboard
SearchAgent HotpotQA slice measures exact match for search agents on multi-hop QA.
Metric: Exact Match (%). Source: huggingface.co. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | ReSeek-Qwen2.5-7b-Instruct | 38.9 | |
| 2 | Search-R1-Qwen2.5-7b-Instruct | 37 | |
| 3 | ZeroSearch-Qwen2.5-7b-Instruct | 34.6 | |
| 4 | ReSeek-Qwen2.5-3b-Instruct | 32.8 | |
| 5 | Search-R1-Qwen2.5-3b-Instruct | 32.4 | |
| 6 | RAG-Qwen2.5-7b-Instruct | 29.9 | |
| 7 | ZeroSearch-Qwen2.5-3b-Instruct | 27.4 | |
| 8 | R1-Qwen2.5-7b-Instruct | 23.7 | |
| 9 | SFT-Qwen2.5-7b-Instruct | 21.7 | |
| 10 | Search-o1-Qwen2.5-7b-Instruct | 18.7 |
Interactive version: theaggregate.ai/benchmark?slug=searchagent-hotpotqa · How It Works · Data refreshed daily, snapshot 2026-10-20.