DIAGENS Debuts CT Model for 509 Targets as iMed-6.0 Tops MedBench Evaluation

DIAGENS announced benchmark results for iMed-6.0, its medical imaging foundation model, and introduced a CT model designed to analyze 509 diseases and imaging findings, the company said on November 12, 2026. The Hong Kong-listed company (HKEX: 2526) disclosed the results in a PR Newswire release.

How the iMed-6.0 Models Scored on MedBench

In MedBench's multimodal API evaluation, iMed-6.0 Thoth and Aegis took first and second place overall and in all three core categories, according to the company. Thoth and Aegis earned overall scores of 64.4 and 61.7. In medical visual perception and text extraction, they scored 88.8 and 84.9, which the company said were 20.3% and 15.0% higher than the highest score of 73.8 among the other evaluated models. MedBench is developed by Shanghai AI Laboratory and forms part of the OpenCompass evaluation ecosystem.

On the MMMU Test, a multimodal academic benchmark spanning six broad domains and 30 subjects, Thoth achieved 66.2% overall accuracy, exceeding the previously published best result of 65.9%. In the Health & Medicine category, Thoth and Aegis achieved 74.9% and 71.1% accuracy, placing first and second.

What the 509-Target CT Model Does

The CT model, developed using iMed-6.0 Aegis, is designed for non-contrast and contrast-enhanced CT examinations of the chest and abdomen. It supports automated identification of 509 distinct diseases and imaging findings: 263 chest targets and 391 abdominal targets, with overlapping targets counted once. In an internal validation using nearly 40,000 CT examination-report pairs from multiple hospitals, the model achieved a macro-averaged AUC of 0.855 for zero-shot classification across all 509 targets. For a subset of 249 key targets represented in internationally available public benchmarks, it achieved a macro-averaged AUC of 0.930.

"We want clinicians and hospitals to build AI around the clinical challenges they know best. With a medical imaging foundation model and zero-code tools, they can train specialty models, adapt them to their workflows, and use them as copilots to support clinical decisions," said Dr. Ning Song, Chairman and CEO of DIAGENS.

iMed-6.0 processes 3D imaging data, whole-slide pathology images and temporal imaging data, and supports image interpretation, analysis of anatomy and lesions, and report drafting and review. DIAGENS pairs these capabilities with iMedLoop, its development platform, and iMedMaaS, a zero-code interface that lets clinicians and hospitals train, deploy and scale custom models. As of June 30, 2026, DIAGENS had undertaken 158 model projects and established R&D partnerships with 99 hospitals, with its products and services reaching more than 400 healthcare institutions.

DIAGENS Funding and Revenue Records

According to akta.pro company records, DIAGENS reported 2025 revenue of RMB 164 million, up 134% year-over-year, including technology licensing revenue of RMB 84.3 million, up 331.7%. The same records list four funding rounds, including a Series C of $14.1 million in December 2023 led by Meihong Investment and a Series C of $14.5 million in April 2023 led by Grand Flight Investment.

Earlier DIAGENS Platform Rollouts

In August 2026, Diagens Tech announced interim results for the first half of 2026 showing a 21.0% revenue increase driven primarily by a 101.1% surge in model-as-a-service revenue, FinanzNachrichten.de reported. At the 2026 Festival of Medical AI on September 25, Chairman Ning Song backed a fragmented market and aimed to let radiologists train customized AI copilots on iMedImage, with iMedLoop as the core asset, The future of trading reported. In October 2026, Diagens Tech showcased its medical AI platform at the Global Digital Trade Expo, and its karyotype-assisted diagnostic software received Class III NMPA approval, FinanzNachrichten.de reported.