Baichuan-2-7B-Base: benchmark results
Provider: Baichuan. Released 2023-09-06. Access: Open.
Aggregate Rating 1250 ± 38, rank #9259 of 10916 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Epoch AI - Lambada | 73.3 | Score | 36 |
| Open Portuguese LLM - OAB Exams | 37.13 | Accuracy (%) | 35.1 |
| Open Portuguese LLM - ENEM | 49.27 | Accuracy (%) | 33.5 |
| Open Portuguese LLM - BLUEX | 40.06 | Accuracy (%) | 32.5 |
| Open Portuguese LLM - FaQuAD NLI | 45.39 | Macro F1 (%) | 27.9 |
| Big-Bench Hard | 41.6 | Average (%) | 27.1 |
| GSM8K | 24.6 | Accuracy (%) | 25.8 |
| MMLU | 54.16 | Accuracy (%) | 25.4 |
| Open Portuguese LLM - ASSIN2 RTE | 67.69 | Macro F1 (%) | 23.6 |
| HellaSwag | 68 | Accuracy (%) | 22.4 |
| InfiBench | 23.5 | Score (%) | 19 |
| Gaokao-Bench | 27.2 | Objective Overall (%) | 16.7 |
Interactive version: theaggregate.ai/model?slug=baichuan-2-7b-base · How It Works · Data refreshed daily, snapshot 2026-11-08.