LogicScore - HotpotQA Essentiality: leaderboard
Metric: Essentiality (%; share of the answer's extracted propositions that lie on the recovered question-to-gold-answer path, 0 when no path is recovered; 1,939 HotpotQA distractor-setting items). Source: arxiv.org. Saturation forecast: Around 2031. 21 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 14B | 52.01 |
| 2 | Qwen 3 30B A3B | 50.97 |
| 3 | Qwen 3 4B | 50.39 |
| 4 | Qwen 3 1.7B | 50.07 |
| 5 | DeepSeek R1 | 49.6 |
| 6 | GPT-5.1 | 48.37 |
| 7 | Qwen 3 8B | 47.47 |
| 8 | O3 | 47.44 |
| 9 | Qwen 3 235B A22B | 45.62 |
| 10 | GPT-4o | 44.9 |
| 11 | DeepSeek V3.2 | 44.81 |
| 12 | Gemini 3 Pro | 39.69 |
| 13 | Qwen 3 0.6B | 33.11 |
Interactive version: theaggregate.ai/benchmark?slug=logicscore-hotpotqa-essentiality · How It Works · Data refreshed daily, snapshot 2026-09-26.