LIBRA - ruTREC — leaderboard
Metric: Dataset Total Score (%). Source: huggingface.co. 17 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 75 |
| 2 | GLM-4 9B Chat | 69.91 |
| 3 | Llama 3.1 8B | 59.86 |
| 4 | Mistral Nemo | 58.4 |
| 5 | Mistral 7B | 42.46 |
| 6 | T-lite-instruct-0.1 | 30.72 |
| 7 | Llama 3 8B | 27.36 |
| 8 | Llama 2 7B | 23.8 |
| 9 | LongChat-7B-v1.5-32k | 7.41 |
| 10 | Mistral-7B-v0.3 | 5.35 |
| 11 | ChatGLM2 6B | 4.47 |
| 12 | Mistral-7B-v0.1 | 4 |
Interactive version: theaggregate.ai/benchmark?slug=libra-rutrec · How the rankings work · Data refreshed daily, snapshot 2026-07-22.