The InclusionMed Collaboration · Medical AI Benchmark
InclusionMed
InclusionMed is an open medical AI evaluation initiative that organises benchmarks across three healthcare roles and three AI capabilities in an Atlas, currently containing five benchmarks including a private diagnostic reasoning benchmark, InclusionMed-DxFiles. The authors evaluated frontier large language models and aggregated results into the InclusionMed Index, with overall scores ranging from 17.5 to 49.1 out of 100. They report that the ten top-ranked models all scored higher on patient communication than on clinical decision-making, and that models with similar Index scores differed substantially in estimated inference cost.
Open the source ↗Similar Research & Safety releases
- AscendGYM
SLAI-AITP (AI Training Platform Team) · Kernel Optimisation Benchmark · Week 48, 2026
- SWE-CoWork: Benchmarking Coding Agents as Digital Employees in Organizations
Xinping Lei et al. (Tokenwave.AI) · Org-level coding benchmark · Week 48, 2026
- Nemotron RL Litmus-Bench V2.0
NVIDIA · Science Post-Training Dataset · Week 48, 2026
- VibePrevisBench
Kling-Keye (Yuzhe Chen, Muxi Diao, Lele Yang, Wenbin Xu, Xuyang Liu, Qile Su, Changyi Liu, Jiankang Chen) · Agent Benchmark · Week 48, 2026
- NovaAtom-Lite
Geodesic Intelligence · All-atom structure prediction · Week 47, 2026
- XYBench
Ai2 (allenai), with researchers at Carnegie Mellon, NVIDIA and Johns Hopkins · XY problem benchmark · Week 47, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.