TS-Skill (Free-Form): leaderboard
Metric: Native-form score (0-1; free-form answers parsed by GPT-5.4 and scored with answer-type comparators plus a GPT-5.4 rationale judge, mean over 3,000 questions). Source: arxiv.org. Saturation forecast: Around October 2026. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 0.67 |
| 2 | O3 Mini | 0.61 |
| 3 | Claude Sonnet 4.5 | 0.6 |
| 4 | Qwen 3 32B (Thinking) | 0.55 |
| 5 | Qwen 2.5 14B Instruct | 0.51 |
| 6 | Qwen 2.5 VL 7B | 0.5 |
Interactive version: theaggregate.ai/benchmark?slug=ts-skill-free-form · How It Works · Data refreshed daily, snapshot 2026-09-25.