IntentGrasp - Teaching: leaderboard

The Teaching 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 Teaching (T) 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]25.8#1257
2Qwen 3 4B20.42#2348
3Qwen3-32B [4bit]18.66#1273
4Qwen 3 8B18.51#1873
5Olmo-3.1-32B-Instruct [4bit]13.5
6gemma-4-E4B-it13.1#1539
7OLMo 3 7B Instruct10.86#6953
8Gemma 4 31B (IT) [4bit]8.57#1803
9Llama 3.2 3B Instruct6.88#7241
10Gemma 4 E2B (IT)2.96#2451
11Llama 3.1 8B Instruct0.8#4600

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

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