LogicScore - 2WikiMultiHopQA Completeness: leaderboard

Metric: Completeness (%; answers whose extracted propositions link the gold answer back to a question entity; 2,177 2WikiMultiHopQA items). Source: arxiv.org. Saturation forecast: Estimated already saturated. 21 models tracked.

Top models

#ModelScore
1Qwen 3 235B A22B86
2Gemini 3 Pro85.78
3DeepSeek R184.16
4Qwen 3 30B A3B82.73
5O382.37
6Qwen 3 4B81.53
7Qwen 3 8B81.33
8Qwen 3 14B81.2
9GPT-5.181
10GPT-4o80.19
11DeepSeek V3.279.49
12Qwen 3 1.7B71.64
13Qwen 3 0.6B49.78

Interactive version: theaggregate.ai/benchmark?slug=logicscore-2wikimultihopqa-completeness · How It Works · Data refreshed daily, snapshot 2026-09-26.