IdeaAMBIG - Clarification Action Generation - Real-World: leaderboard
Metric: Macro Clarification Action Success Rate (%). Source: arxiv.org. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol | 80.6 |
| 2 | Claude Sonnet 5 | 76.8 |
| 3 | Qwen 3.5 397B A17B | 72 |
| 4 | Gemini 3.1 Pro (Preview) | 68.9 |
| 5 | DeepSeek R1 0528 | 68 |
| 6 | Gemma 4 31B (IT) | 67.7 |
| 7 | Qwen 3.5 9B | 64.6 |
| 8 | GLM-5.2 | 63.6 |
| 9 | DeepSeek V3.2 | 62.9 |
| 10 | Qwen 3 32B | 61.9 |
| 11 | Kimi K3 | 60.6 |
| 12 | Qwen 3 8B | 53.8 |
| 13 | GPT-OSS-120B | 53.4 |
Interactive version: theaggregate.ai/benchmark?slug=ideaambig-clarification-action-generation-real-world · How It Works · Data refreshed daily, snapshot 2026-09-19.