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

#ModelScore
1Gemini 3.1 Pro (Preview)43.33
2Gemini 3 Flash (Preview)29.27
3Claude Opus 4.723.44
4Claude Sonnet 4.618.75
5GPT-5.4 Nano12.5
6GPT-5.410.42
7Claude Haiku 4.510.42
8Gemini 3.1 Flash Lite (Preview)8.85
9GPT-5.4 Mini6.25

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