IntentGrasp - Gem Set - Smart Assistant: leaderboard

The Smart Assistant 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 Smart Assistant (SA) 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 March 2028. 9 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3 Flash (Preview)31.88#152
2GPT-5.419#135
3Gemini 3.1 Flash Lite (Preview)15.87#417
4Gemini 3.1 Pro (Preview)14.12#99
5Claude Sonnet 4.611.92#173
6Claude Opus 4.79.92#85
7GPT-5.4 Nano8.56#651
8GPT-5.4 Mini7.92#406
9Claude Haiku 4.53.2#583

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-smart-assistant · How It Works · Data refreshed daily, snapshot 2026-11-21.