Know2Guess - Answer Accuracy: leaderboard

Metric: Answer accuracy (0-1 scaled to %) on the answer-expected zones A to C (questions with a unique supported answer, five domains); standard prompt on the 1,080-item test split, greedy decoding with at most 128 or 160 output tokens, no retrieval or tools; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.

Top models

#ModelScore
1Qwen 3.5 9B (Non-reasoning)48.33
2Mistral Small 3.244.18
3Llama 3 8B Instruct41.41
4Qwen 3 8B (Non-reasoning)34.26
5Qwen 2.5 3B Instruct27.68
6Qwen 2.5 1.5B Instruct8.19

Interactive version: theaggregate.ai/benchmark?slug=know2guess-answer-accuracy · How It Works · Data refreshed daily, snapshot 2026-09-29.