LogicScore - 2WikiMultiHopQA Essentiality: leaderboard
LogicScore (Yan et al., 2026) Essentiality on 2,177 chain-structured 2WikiMultiHopQA questions: the model writes a cited step-by-step answer and a short answer from the retrieved documents, and GPT-4o-mini splits the long answer into propositions and entity triples. Essentiality is the share of those propositions that lie on a recovered path from the gold answer back to a question entity, and 0 when no path is found. Percent, higher is better; single run.
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; 2,177 2WikiMultiHopQA items). Source: arxiv.org. Saturation forecast: Not forecast. 21 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DeepSeek R1 | 56.41 | #467 |
| 2 | Qwen 3 30B A3B | 55.99 | #1124 |
| 3 | Qwen 3 14B | 54.56 | #1235 |
| 4 | Gemini 3 Pro | 53.93 | #135 |
| 5 | Qwen 3 4B | 53.85 | #2297 |
| 6 | Qwen 3 235B A22B | 53.25 | #622 |
| 7 | Qwen 3 8B | 52.88 | #1838 |
| 8 | Qwen 3 1.7B | 52.06 | #5551 |
| 9 | O3 | 50 | #224 |
| 10 | GPT-4o | 46.55 | #741 |
| 11 | DeepSeek V3.2 | 44.32 | #403 |
| 12 | GPT-5.1 | 37.96 | #225 |
| 13 | Qwen 3 0.6B | 31.53 | #8392 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=logicscore-2wikimultihopqa-essentiality · How It Works · Data refreshed daily, snapshot 2026-11-12.