ClarifyCodeBench: leaderboard
Metric: Pass@1 (%) on the hidden LiveCodeBench v6 tests of the code written after interactive clarification of an ambiguous requirement (419 tasks with one to three deleted requirement details; a GPT-4o judge matches each question to the annotated key questions and the environment returns the deleted detail; at most 6 rounds, temperature 0). Source: arxiv.org. Saturation forecast: Around January 2028. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 41.1 |
| 2 | DeepSeek V3.2 (Non-reasoning) | 39.1 |
| 3 | Claude Sonnet 4.5 | 38.2 |
| 4 | Claude Sonnet 4.5 (Thinking) | 34.3 |
| 5 | Gemini 2.5 Flash (Non-reasoning) | 29.8 |
| 6 | Qwen 3 235B A22B (Non-reasoning) | 27.7 |
| 7 | GPT-4o | 27.2 |
Interactive version: theaggregate.ai/benchmark?slug=clarifycodebench · How It Works · Data refreshed daily, snapshot 2026-09-29.