IdeaAMBIG - Clarification Action Generation - Controlled Synthetic: leaderboard
Metric: Macro Clarification Action Success Rate (%). Source: arxiv.org. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol | 96.2 |
| 2 | Claude Sonnet 5 | 94.5 |
| 3 | DeepSeek V3.2 | 93 |
| 4 | Kimi K3 | 92.5 |
| 5 | Gemini 3.1 Pro (Preview) | 91.6 |
| 6 | Qwen 3.5 397B A17B | 89 |
| 7 | Qwen 3 8B | 82.6 |
| 8 | Qwen 3.5 9B | 81.2 |
| 9 | GLM-5.2 | 77 |
| 10 | Qwen 3 32B | 76.3 |
| 11 | Gemma 4 31B (IT) | 73 |
| 12 | DeepSeek R1 0528 | 68.5 |
| 13 | GPT-OSS-120B | 65.3 |
Interactive version: theaggregate.ai/benchmark?slug=ideaambig-clarification-action-generation-controlled-synthetic · How It Works · Data refreshed daily, snapshot 2026-09-19.