IntentGrasp - Gem Set - Teaching: leaderboard
Metric: Instance F1 (%) on the Teaching (T) domain of the 470-item Gem Set, mean of four option-order runs, zero-shot, API default settings; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 43 |
| 2 | Gemini 3 Flash (Preview) | 39.67 |
| 3 | Claude Opus 4.7 | 33.5 |
| 4 | Gemini 3.1 Flash Lite (Preview) | 26.08 |
| 5 | Claude Haiku 4.5 | 12.5 |
| 6 | GPT-5.4 | 10.5 |
| 7 | Claude Sonnet 4.6 | 9.33 |
| 8 | GPT-5.4 Nano | 5.83 |
| 9 | GPT-5.4 Mini | 2 |
Interactive version: theaggregate.ai/benchmark?slug=intentgrasp-gem-set-teaching · How It Works · Data refreshed daily, snapshot 2026-10-07.