LIBRA - ruBABILongQA3 — leaderboard
Metric: Dataset Total Score (%). Source: huggingface.co. 17 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3.1 8B | 29.65 |
| 2 | GLM-4 9B Chat | 22.3 |
| 3 | GPT-4o | 21.44 |
| 4 | Llama 2 7B | 16.31 |
| 5 | Mistral Nemo | 16 |
| 6 | Mistral-7B-v0.3 | 15.67 |
| 7 | Llama 3 8B | 9.06 |
| 8 | Mistral-7B-v0.1 | 9 |
| 9 | T-lite-instruct-0.1 | 8.23 |
| 10 | Mistral 7B | 6 |
| 11 | LongChat-7B-v1.5-32k | 4 |
| 12 | ChatGLM2 6B | 2.5 |
Interactive version: theaggregate.ai/benchmark?slug=libra-rubabilongqa3 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.