Baichuan
Baichuan Intelligence
Baichuan focuses on Chinese language excellence and specialized vertical models. Strong in finance and healthcare domains. Backed by Alibaba and Xiaomi.
Models
Baichuan-M2Plus
Unknown parameters
Medical domain specialized model. Significantly lower hallucination rate than general models - about 3x lower than DeepSeek.
- 3x lower hallucination rate
- Medical domain specialized
- Better than OpenEvidence
Baichuan4-Finance
Unknown parameters
Specialized financial model. 95%+ accuracy in banking, insurance, funds, and securities. Overall 93.62% on FLAME-Cer benchmark.
- FLAME-Cer: 93.62%
- Surpasses GPT-4o on financial tasks
- Domain-specific optimization
Baichuan4-Turbo
Unknown parameters
Cost-optimized version of Baichuan 4. Lowest deployment cost among similar models - runs on 2x RTX 4090.
- Runs on 2x RTX 4090
- Lowest cost in class
- Full Baichuan 4 capabilities
Benchmarks
ceval
80%
Baichuan 4
Unknown parameters
Fourth generation with 10%+ improvement in general capabilities. Math improved 14%, code improved 9%. Ranked #1 on SuperCLUE Chinese benchmark.
- SuperCLUE score: 80.64 (#1)
- Beats GPT-4-Turbo on Chinese tasks
- Strong multimodal capabilities
Benchmarks
ceval
82%
cmmlu
83%
Baichuan2-13B
13B parameters
Open-source bilingual model with strong Chinese capabilities. Good balance of performance and efficiency.
- Open source
- Strong Chinese performance
- Efficient 13B size
Benchmarks
mmlu
59%
ceval
58%
cmmlu
62%