CSTutorBench - Hint Not Solution: leaderboard
The hint-not-solution criterion of CSTutorBench (2026): whether a tutoring response guides the student toward the fix without giving it away, as a percent of the points on the 8 debugging questions. Higher is better.
Metric: Hint-not-solution criterion (%; guides the student toward the fix without giving it away, on the 8 debugging questions; points earned out of the maximum on 17 scenario-based VEX VR block-programming tutoring questions for middle-school students, each scored 0 to 2 per criterion by a Claude Sonnet judge with human review of every judgment; revised system prompt (Trial 2); higher is better). Source: arxiv.org. Saturation forecast: Around February 2027. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 4 31B (IT) | 81 | #342 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=cstutorbench-hint-not-solution · How It Works · Data refreshed daily, snapshot 2026-11-13.