IntentGrasp - Gem Set - Policy Making: leaderboard

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 March 2027. 9 models tracked.

Top models

#ModelScore
1Gemini 3 Flash (Preview)39.77
2Gemini 3.1 Flash Lite (Preview)26.44
3Claude Opus 4.720.42
4Gemini 3.1 Pro (Preview)20.08
5Claude Sonnet 4.617.23
6GPT-5.412.31
7GPT-5.4 Nano2.35
8GPT-5.4 Mini1.14
9Claude Haiku 4.50

Interactive version: theaggregate.ai/benchmark?slug=intentgrasp-gem-set-policy-making · How It Works · Data refreshed daily, snapshot 2026-10-07.