IntentGrasp - Gem Set - News: leaderboard

Metric: Instance F1 (%) on the News (N) 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

#ModelScore
1Claude Opus 4.738.75
2Claude Haiku 4.538.7
3Claude Sonnet 4.630.99
4Gemini 3.1 Pro (Preview)22.5
5Gemini 3 Flash (Preview)17.81
6GPT-5.417.6
7Gemini 3.1 Flash Lite (Preview)15.21
8GPT-5.4 Nano11.46
9GPT-5.4 Mini10.94

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