STQA - Human-Authored Questions - Historical Query Accuracy: leaderboard
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Around December 2026. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-OSS-120B | 56.67 |
| 2 | Gemma 4 31B | 56.67 |
| 3 | GPT-OSS-20B | 53.33 |
| 4 | Qwen 3 30B A3B | 50 |
Interactive version: theaggregate.ai/benchmark?slug=stqa-human-authored-questions-historical-query-accuracy · How It Works · Data refreshed daily, snapshot 2026-09-24.