EduArt - Multiple Choice: leaderboard
Metric: Exact-match accuracy (%; the 370 single-answer multiple-choice items in Italian and English, answer-only condition, one run; higher is better). Source: arxiv.org. Saturation forecast: Estimated already saturated. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.5 Flash | 96.5 |
| 2 | Gemini 3.1 Pro (Preview) | 95.7 |
| 3 | GPT-5.5 | 95.1 |
| 4 | Claude Opus 4.6 | 94.6 |
| 5 | Claude Sonnet 4.6 | 94.3 |
| 6 | Gemini 3.1 Flash Lite (Preview) | 92.4 |
| 7 | Qwen 3 VL 235B A22B | 88.6 |
| 8 | Mistral Large 3 | 84.6 |
| 9 | Claude Haiku 4.5 | 84 |
| 10 | GPT-5.4 Mini | 82.7 |
| 11 | GPT-5.4 Nano | 62.7 |
| 12 | Pixtral Large | 28.6 |
Interactive version: theaggregate.ai/benchmark?slug=eduart-multiple-choice · How It Works · Data refreshed daily, snapshot 2026-09-29.