IntentGrasp - Gem Set - Daily Life: leaderboard

Metric: Instance F1 (%) on the Daily Life (DL) 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 November 2027. 9 models tracked.

Top models

#ModelScore
1Gemini 3.1 Pro (Preview)36.33
2Gemini 3 Flash (Preview)28.05
3Claude Opus 4.724.17
4Gemini 3.1 Flash Lite (Preview)17.72
5GPT-5.4 Nano16.48
6GPT-5.414.17
7Claude Sonnet 4.610.5
8GPT-5.4 Mini6.25
9Claude Haiku 4.54.2

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