STQA - Human-Authored Questions - Forecast Reasoning Accuracy: leaderboard
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Around December 2026. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-OSS-120B | 52.5 |
| 2 | Gemma 4 31B | 50 |
| 3 | Qwen 3 30B A3B | 47.5 |
| 4 | GPT-OSS-20B | 46.67 |
Interactive version: theaggregate.ai/benchmark?slug=stqa-human-authored-questions-forecast-reasoning-accuracy · How It Works · Data refreshed daily, snapshot 2026-09-24.