IntentGrasp - Gem Set - Writing: leaderboard
Metric: Instance F1 (%) on the Writing (W) 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 2029. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 20.17 |
| 2 | Gemini 3.1 Pro (Preview) | 12 |
| 3 | GPT-5.4 Mini | 5.83 |
| 4 | GPT-5.4 Nano | 5.17 |
| 5 | Gemini 3.1 Flash Lite (Preview) | 4.83 |
| 6 | GPT-5.4 | 4.5 |
| 7 | Claude Opus 4.7 | 3.83 |
| 8 | Claude Sonnet 4.6 | 3.5 |
| 9 | Claude Haiku 4.5 | 3.17 |
Interactive version: theaggregate.ai/benchmark?slug=intentgrasp-gem-set-writing · How It Works · Data refreshed daily, snapshot 2026-10-07.