THPT-Ladder - Part III (Short Answer): leaderboard
Metric: Accuracy (%; x100 of the fraction of Part III short-answer items answered correctly; 632 items from 21 official 2025-2026 Vietnamese National High School Graduation Examination papers in 11 subjects, presented in Vietnamese one item at a time with text and figures, scored against the ministry keys; open-weight models at their publishers' recommended sampling (16,384-token cap), closed models at their default settings). Source: arxiv.org. Saturation forecast: Around December 2026. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 95 |
| 2 | Claude Opus 5 | 95 |
| 3 | Claude Opus 4.8 | 91.7 |
| 4 | Qwen 3.5 27B | 91.7 |
| 5 | Claude Sonnet 5 | 91.7 |
| 6 | Qwen 3.5 9B | 85 |
| 7 | Claude Haiku 4.5 | 56.7 |
Interactive version: theaggregate.ai/benchmark?slug=thpt-ladder-part-iii-short-answer · How It Works · Data refreshed daily, snapshot 2026-09-26.