IntentGrasp - Gem Set - News: leaderboard

The News 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 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 October 2028. 9 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Claude Opus 4.738.75#86
2Claude Haiku 4.538.7#587
3Claude Sonnet 4.630.99#179
4Gemini 3.1 Pro (Preview)22.5#102
5Gemini 3 Flash (Preview)17.81#156
6GPT-5.417.6#138
7Gemini 3.1 Flash Lite (Preview)15.21#419
8GPT-5.4 Nano11.46#653
9GPT-5.4 Mini10.94#409

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-news · How It Works · Data refreshed daily, snapshot 2026-11-22.