TS-Skill (MCQ) - SK2+SK3: leaderboard

Metric: MCQ macro-F1 (0-1; four-option multiple choice, letter-only answers, unparseable answers score 0, 342 questions). Source: arxiv.org. Saturation forecast: Around November 2026. 9 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.50.75
2GPT-4o0.71
3Qwen 3 32B (Thinking)0.57
4Qwen 2.5 14B Instruct0.46
5Qwen 2.5 VL 7B0.4

Interactive version: theaggregate.ai/benchmark?slug=ts-skill-mcq-sk2-plussk3 · How It Works · Data refreshed daily, snapshot 2026-09-25.