LogicScore - HotpotQA Determinateness: leaderboard
Metric: Determinateness (%; answers whose own short answer o4-mini re-derives from the long-form answer alone; 1,939 HotpotQA distractor-setting items). Source: arxiv.org. Saturation forecast: Estimated already saturated. 21 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.1 | 99.15 |
| 2 | O3 | 98.92 |
| 3 | Qwen 3 235B A22B | 98.87 |
| 4 | DeepSeek R1 | 98.56 |
| 5 | Gemini 3 Pro | 98.56 |
| 6 | DeepSeek V3.2 | 97.96 |
| 7 | Qwen 3 30B A3B | 97.77 |
| 8 | Qwen 3 8B | 97.68 |
| 9 | GPT-4o | 97.36 |
| 10 | Qwen 3 14B | 97.31 |
| 11 | Qwen 3 4B | 96.87 |
| 12 | Qwen 3 1.7B | 92.9 |
| 13 | Qwen 3 0.6B | 81.52 |
Interactive version: theaggregate.ai/benchmark?slug=logicscore-hotpotqa-determinateness · How It Works · Data refreshed daily, snapshot 2026-09-26.