IdeaAMBIG - Clarification Action Generation - Controlled Synthetic: leaderboard

Metric: Macro Clarification Action Success Rate (%). Source: arxiv.org. 13 models tracked.

Top models

#ModelScore
1GPT-5.6 Sol96.2
2Claude Sonnet 594.5
3DeepSeek V3.293
4Kimi K392.5
5Gemini 3.1 Pro (Preview)91.6
6Qwen 3.5 397B A17B89
7Qwen 3 8B82.6
8Qwen 3.5 9B81.2
9GLM-5.277
10Qwen 3 32B76.3
11Gemma 4 31B (IT)73
12DeepSeek R1 052868.5
13GPT-OSS-120B65.3

Interactive version: theaggregate.ai/benchmark?slug=ideaambig-clarification-action-generation-controlled-synthetic · How It Works · Data refreshed daily, snapshot 2026-09-19.