SearchAgent - 2WikiMultihopQA: leaderboard
SearchAgent 2WikiMultihopQA slice measures exact match on two-hop Wikipedia questions.
Metric: Exact Match (%). Source: huggingface.co. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Search-R1-Qwen2.5-7b-Instruct | 41.4 | |
| 2 | ReSeek-Qwen2.5-7b-Instruct | 38.2 | |
| 3 | ZeroSearch-Qwen2.5-7b-Instruct | 35.2 | |
| 4 | Search-R1-Qwen2.5-3b-Instruct | 31.9 | |
| 5 | ZeroSearch-Qwen2.5-3b-Instruct | 30 | |
| 6 | ReSeek-Qwen2.5-3b-Instruct | 29.8 | |
| 7 | R1-Qwen2.5-7b-Instruct | 29.2 | |
| 8 | SFT-Qwen2.5-7b-Instruct | 25.9 | |
| 9 | Direct-Inference-Qwen2.5-7b-Instruct | 25 | |
| 10 | RAG-Qwen2.5-7b-Instruct | 23.5 |
Interactive version: theaggregate.ai/benchmark?slug=searchagent-2wikimultihopqa · How It Works · Data refreshed daily, snapshot 2026-10-20.