LIBRA - MatreshkaNames — leaderboard

Metric: Dataset Total Score (%). Source: huggingface.co. 17 models tracked.

Top models

#ModelScore
1GPT-4o51.67
2GLM-4 9B Chat47.33
3Llama 3.1 8B39.78
4Mistral Nemo32.22
5Llama 3 8B16.56
6Mistral 7B16.33
7T-lite-instruct-0.114
8Mistral-7B-v0.310
9Mistral-7B-v0.18.11
10LongChat-7B-v1.5-32k5.89
11Llama 2 7B3.44
12ChatGLM2 6B1.33

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