LogicScore - MuSiQue 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; 1,605 MuSiQue answerable items). Source: arxiv.org. Saturation forecast: Around 2031. 21 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 38.98 |
| 2 | O3 | 37.3 |
| 3 | Qwen 3 235B A22B | 35.25 |
| 4 | DeepSeek R1 | 34.33 |
| 5 | GPT-4o | 32.54 |
| 6 | Qwen 3 30B A3B | 32.41 |
| 7 | Qwen 3 14B | 31.78 |
| 8 | Qwen 3 8B | 31.33 |
| 9 | DeepSeek V3.2 | 30.34 |
| 10 | Qwen 3 4B | 29.83 |
| 11 | GPT-5.1 | 27.27 |
| 12 | Qwen 3 1.7B | 21.56 |
| 13 | Qwen 3 0.6B | 6.92 |
Interactive version: theaggregate.ai/benchmark?slug=logicscore-musique-essentiality · How It Works · Data refreshed daily, snapshot 2026-09-26.