InteractiveBench Logic: leaderboard
Interactive proof domain on Situation Puzzle logic instances.
Metric: Situation Puzzle Accuracy (%). Source: www.interactivebench.org. Source: www.interactivebench.org. Saturation forecast: Around July 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash | 30.4 | #99 |
| 2 | GPT-5 Mini | 17.4 | #186 |
| 3 | DeepSeek V3.2 | 15.2 | #204 |
| 4 | Grok 4.1 Fast | 15.2 | #217 |
| 5 | Kimi K2 (Thinking) | 6.5 | #243 (Kimi K2) |
| 6 | Qwen 3 Max | 4.3 | #209 |
No result here: #4 Claude Opus 5.5, #6 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=interactivebench-logic · How It Works · Data refreshed daily, snapshot 2026-10-21.