IntentGrasp - Gem Set - E-Commerce: leaderboard

The E-Commerce 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 E-Commerce (EC) 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 2027. 9 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3.1 Pro (Preview)40#99
2GPT-5.4 Mini31#406
3Claude Opus 4.730#85
4GPT-5.429.5#135
5Claude Sonnet 4.624.5#173
6Gemini 3 Flash (Preview)23.82#152
7GPT-5.4 Nano19.75#651
8Claude Haiku 4.59.83#583
9Gemini 3.1 Flash Lite (Preview)6.83#417

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=intentgrasp-gem-set-e-commerce · How It Works · Data refreshed daily, snapshot 2026-11-21.