EduGuardBench — leaderboard
Education-specific safety benchmark for teaching harm, adversarial safety, pedagogical fidelity, refusal, and safe tutoring behavior.
Metric: RFS (self-reported). Source: benchmarklist.com. Status: saturation imminent. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3 | 73 |
| 2 | Qwen 3 32B | 72 |
| 3 | GPT-4o | 69 |
| 4 | Qwen 3 235B A22B | 67 |
| 5 | Qwen 3 8B | 61 |
| 6 | Qwen 2.5 72B Instruct | 56 |
Interactive version: theaggregate.ai/benchmark?slug=eduguardbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.