StudentBench - Learning Gain: leaderboard
Metric: GRE learning gain after one hour of AI tutoring (percentage points, pretest-adjusted ANCOVA). Source: studentbench.org. Saturation forecast: Around March 2028. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.8 (xHigh) | 16 |
| 2 | Gemini 3.1 Pro (Preview) (High) | 15.4 |
| 3 | Gemini 3.5 Flash (Low) | 14.3 |
| 4 | Gemini 3.7 Flash (Medium) | 14.1 |
| 5 | Claude Opus 4.8 (Non-reasoning) | 13.6 |
| 6 | GPT-5.5 (High) | 13.5 |
| 7 | Gemma 4 31B (High) | 13.1 |
| 8 | GPT-5.4 Mini (Non-reasoning) | 13 |
| 9 | Claude Opus 5 (High) | 12.6 |
Interactive version: theaggregate.ai/benchmark?slug=studentbench-learning-gain · How It Works · Data refreshed daily, snapshot 2026-10-04.