Clarify-Then-Search (3 Questions): leaderboard
Metric: Nugget restoration score (0-100): mean restore_score_100, weighted nugget recall with partial credit against the static gold; three clarifying questions (k=3); 518 underspecified Baidu search queries; the evaluated model asks clarifying questions, a closed-book user answerer and a rewriter (ERNIE-4.5-Turbo-128K) build the rewritten query, WebDancer searches, and ERNIE-4.5-Turbo-128K judges coverage of weighted evidence-grounded gold nuggets. Source: arxiv.org. Saturation forecast: Around 2029. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 27.13 |
| 2 | Claude Sonnet 4.5 | 27.03 |
| 3 | Kimi K2 | 26.57 |
| 4 | DeepSeek V3.2 | 26.49 |
| 5 | GPT-5.2 | 26.3 |
| 6 | Qwen 3 235B A22B Instruct | 26.24 |
Interactive version: theaggregate.ai/benchmark?slug=clarify-then-search-3-questions · How It Works · Data refreshed daily, snapshot 2026-09-29.