LogicScore - HotpotQA Completeness: leaderboard
Metric: Completeness (%; answers whose extracted propositions link the gold answer back to a question entity; 1,939 HotpotQA distractor-setting items). Source: arxiv.org. Saturation forecast: Around May 2027. 21 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 78.65 |
| 2 | Qwen 3 30B A3B | 77.09 |
| 3 | DeepSeek V3.2 | 76.34 |
| 4 | Qwen 3 4B | 75.58 |
| 5 | GPT-4o | 75.57 |
| 6 | Qwen 3 8B | 75.36 |
| 7 | DeepSeek R1 | 73.91 |
| 8 | Qwen 3 235B A22B | 73.8 |
| 9 | O3 | 73.24 |
| 10 | Qwen 3 14B | 73.18 |
| 11 | GPT-5.1 | 72.61 |
| 12 | Qwen 3 1.7B | 66.17 |
| 13 | Qwen 3 0.6B | 52.16 |
Interactive version: theaggregate.ai/benchmark?slug=logicscore-hotpotqa-completeness · How It Works · Data refreshed daily, snapshot 2026-09-26.