IntentGrasp - Smart Assistant: leaderboard

The Smart Assistant 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 Smart Assistant (SA) 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
1Gemma 4 31B (IT) [4bit]43.33#1803
2Olmo-3.1-32B-Instruct [4bit]36.63
3gemma-4-E4B-it35.78#1539
4Llama 3.3 70B Instruct [4bit]33.05#1257
5Qwen3-32B [4bit]31.3#1273
6Qwen 3 4B30.63#2348
7Gemma 4 E2B (IT)28.22#2451
8Qwen 3 8B27.92#1873
9Llama 3.1 8B Instruct20.9#4600
10Llama 3.2 3B Instruct19.92#7241
11OLMo 3 7B Instruct17.9#6953

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

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