Product Launchllmhealthcarefractalbenchmarks
Vaidya 2.0 Beats GPT-5 on HealthBench
8.2
Fractal launched Vaidya 2.0 at the India AI Impact Summit 2026, reporting a 50.1 score on OpenAI’s HealthBench (hard) on Feb. 19, 2026, surpassing GPT-5 and Google’s Gemini Pro 3. The post-trained healthcare reasoning model targets workflows like emergency triage, symptom checking, and doctor/administrator assist, and is positioned as part of Fractal’s contribution to India’s ₹10,300+ crore India AI Mission.
Key Points
- 1Achieves 50.1 on HealthBench (hard), first model to exceed a 50 score on the benchmark
- 2Positions Vaidya 2.0 ahead of GPT-5 and Gemini Pro 3 on medical reasoning benchmarks
- 3Enables healthcare workflows like triage, symptom checking, and doctor assist for scalable deployments
Scoring Rationale
Strong benchmark novelty and practical launch, limited by single-source company claims and lack of independent third-party verification.
Sources
Public references used for this report.
Practice with real Health & Insurance data
90 SQL & Python problems · 15 industry datasets
Used by DS/ML engineers at top companies
250 free problems · No credit card
See all Health & Insurance problems
