IntentGrasp - Gem Set - Policy Making: leaderboard
The Policy Making domain of the IntentGrasp (2026) Gem Set, hard intent-understanding items that every open-weight model failed in its first run. The score is instance F1 in percent, averaged over four option orders; higher is better.
Metric: Instance F1 (%) on the Policy Making (PM) 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 February 2027. 9 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 39.77 | #156 |
| 2 | Gemini 3.1 Flash Lite (Preview) | 26.44 | #419 |
| 3 | Claude Opus 4.7 | 20.42 | #86 |
| 4 | Gemini 3.1 Pro (Preview) | 20.08 | #102 |
| 5 | Claude Sonnet 4.6 | 17.23 | #179 |
| 6 | GPT-5.4 | 12.31 | #138 |
| 7 | GPT-5.4 Nano | 2.35 | #653 |
| 8 | GPT-5.4 Mini | 1.14 | #409 |
| 9 | Claude Haiku 4.5 | 0 | #587 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=intentgrasp-gem-set-policy-making · How It Works · Data refreshed daily, snapshot 2026-11-22.