IntentGrasp - Gem Set - General: leaderboard
Metric: Instance F1 (%) on the General (G) 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 June 2027. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 43.33 |
| 2 | Gemini 3 Flash (Preview) | 29.27 |
| 3 | Claude Opus 4.7 | 23.44 |
| 4 | Claude Sonnet 4.6 | 18.75 |
| 5 | GPT-5.4 Nano | 12.5 |
| 6 | GPT-5.4 | 10.42 |
| 7 | Claude Haiku 4.5 | 10.42 |
| 8 | Gemini 3.1 Flash Lite (Preview) | 8.85 |
| 9 | GPT-5.4 Mini | 6.25 |
Interactive version: theaggregate.ai/benchmark?slug=intentgrasp-gem-set-general · How It Works · Data refreshed daily, snapshot 2026-10-07.