HumanLikeness - Meaning-1 — leaderboard

Metric: Humanlike Score (%). Source: huggingface.co. 20 models tracked.

Top models

#ModelScore
1Llama 3.1 70B Instruct80.22
2Llama 3.1 8B Instruct79
3Phi-3 Mini 4K Instruct76.07
4Llama 2 13B Chat Base73.9
5GPT-3.5 Turbo71.44
6c4ai-command-r-plus65.64
7starchat2-15B-v0.162.24
8Yi 1.5 34B Chat60.87
9Llama 3 8B Instruct58.94
10CodeLlama-34B-Instruct-hf58.04
11Llama 3 70B Instruct56.57
12Mistral Nemo Instruct (2407)51.53
13Llama 2 7B Chat50.31
14Mistral 7B Instruct (v0.3)49.23
15GPT-4o47.21

Interactive version: theaggregate.ai/benchmark?slug=humanlikeness-meaning-1 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.