QSTRBench: leaderboard
Metric: Overall Accuracy (%). Source: benchmarklist.com. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 | 85.3 |
| 2 | DeepSeek V3.2 | 72.1 |
| 3 | Grok 4.1 Fast | 68.4 |
| 4 | GPT-5.1 | 67.2 |
| 5 | DeepSeek V3.1 | 65.8 |
Interactive version: theaggregate.ai/benchmark?slug=qstrbench · How It Works · Data refreshed daily, snapshot 2026-09-19.