IntentGrasp - E-Commerce: leaderboard

The E-Commerce domain of the IntentGrasp (2026) All Set, intent-understanding items drawn from public intent datasets and posed as multiple choice with one or more correct intents. The score is instance F1 in percent, averaged over option-order shuffles; higher is better.

Metric: Instance F1 (%) on the E-Commerce (EC) domain of the 12,909-item All Set, mean over option-order shuffles, zero-shot at temperature 0; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Llama 3.3 70B Instruct [4bit]30.01#1275
2gemma-4-E4B-it29.58#1577
3Qwen3-32B [4bit]28.41#1296
4Gemma 4 E2B (IT)26.2#2532
5Gemma 4 31B (IT) [4bit]25.55#1824
6Olmo-3.1-32B-Instruct [4bit]23.94
7Qwen 3 4B23.53#2379
8Qwen 3 8B21.6#1890
9OLMo 3 7B Instruct17.78#6953
10Llama 3.1 8B Instruct13.62#4655
11Llama 3.2 3B Instruct11.25#7311

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=intentgrasp-e-commerce · How It Works · Data refreshed daily, snapshot 2026-11-22.