IntentGrasp - Gem Set - Coronavirus Pandemic: leaderboard

Metric: Instance F1 (%) on the Coronavirus Pandemic (CP) 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 December 2027. 9 models tracked.

Top models

#ModelScore
1Gemini 3 Flash (Preview)30
2Gemini 3.1 Pro (Preview)20
3Claude Opus 4.712.92
4GPT-5.410.83
5Gemini 3.1 Flash Lite (Preview)10
6GPT-5.4 Mini5.83
7GPT-5.4 Nano4.88
8Claude Sonnet 4.63.33
9Claude Haiku 4.50.83

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