Labops
ORINN
Medical-grade alternative to generic LLMs

High Quality Data

Orinn is trained on high-quality medical data sourced from textbooks, research papers, and partner medical institutions. We don’t rely solely on web scraping.

Specialized Algorithm

No single algorithm is sufficient for every domain, so we designed a highly personalized one specifically for healthcare.

RL with Professionals

We trained and applied RL with a team of doctors, so the model learns to align closely with real medical expertise.

Affordable Intelligence

Our new model, Orinn 1.5, is far more affordable than others—hosting 8B model while delivering the same level of efficiency.

HealthBench

We evaluated Orinn 1.6 on OpenAI’s HealthBench benchmark to measure medical reasoning, reliability, and hallucination safety compared with leading frontier models.

Orinn 1.6 achieves the highest score across the benchmark, demonstrating stronger reliability and lower hallucination rates.

HealthBench
HealthBench Hard
Hallucination
Orinn-1.6MedGemma-27BGPT-5.1Opus-4.6Gemini-3-ProSonnet-4.6
Medical Knowledge & Reasoning
MedQA95.885.396.3895.4196.0392.06
MedMCQA96.570.2----
PubMedQA95.377.280.2---
MMLU92.586.286.3889.1190.187.34
Medscribe86.5-88.0986.1372.04-
Medcode48.52-52.7349.1352.2-
Orinn-1.6GPT-5.2Opus-4.6Gemini-3-ProQwen3.5-397B
Medical Multimodal Benchmarks
LongBench v263.654.564.468.260.2
OmniDocBench1.588.585.787.788.584.2
OCRBench89.580.785.890.486.2
SLAKE85.576.976.481.379.9
PMC-VQA64.458.966.369.460.5
MMedXpertQA-MM68.463.6767066

Every thought has a path.
Orinn follows it.

LLMs generate answers. Orinn maps the reasoning behind them — with context, clarity, and care.

Prompt
|

Orinn 1.6 is here

The next era of healthcare starts here.

Join us in scaling Orinn 1.6 — the AI health companion designed to serve billions, not just millions. We’re building a future where clinical-grade intelligence lives in every home.

Invest in trust. Invest in Orinn.