FoundationalASSIST - Knowledge Tracing: leaderboard
Metric: Accuracy (%; whether the student answers the next question correctly, about 27,700 predictions from 500 students' histories; always predicting correct scores 51.3). Source: arxiv.org. Saturation forecast: Around December 2026. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-OSS-120B | 56.2 |
| 2 | Qwen 3 Next 80B A3B (Thinking) | 55.8 |
| 3 | Qwen 3 Next 80B A3B Instruct | 54 |
| 4 | Llama 3.3 70B Instruct | 52.3 |
Interactive version: theaggregate.ai/benchmark?slug=foundationalassist-knowledge-tracing · How It Works · Data refreshed daily, snapshot 2026-09-26.