Clinical Benchmarks

MedGuard

MedGuard models with results here, each placed on its own board.

Models
1
Results
1
Boards
1 of 13

github.com/actava-ai/leaderboard/tree/main/benchmarks/chi-bench/submissions/2026-07-06-cuilinke-hermes-medguard

Models

ModelKindReleasedBoards
MedGuardProductNot stated1

Results

One line per result. Dark tick: the board leader.

EHR and workflow agents

  1. CHI-Bench
    hermes + MedGuard
    All Domains pass@1; hermes harness; community submission
    22.7
    Rank 11 of 43 here, 45 models on the boardLeader erius + claude-opus-5 54.7
    Independent run
    Measured Jul 2026