LIBRA - ruSciPassageCount — leaderboard

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

Top models

#ModelScore
1GPT-4o35
2Mistral Nemo12.83
3Mistral 7B8.17
4GLM-4 9B Chat7.5
5Llama 3 8B6.5
6Llama 3.1 8B5.58
7T-lite-instruct-0.15.08
8LongChat-7B-v1.5-32k4.83
9Llama 2 7B4.75
10ChatGLM2 6B3.67
11Mistral-7B-v0.11.33
12Mistral-7B-v0.30

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