Clinical Benchmarks

NVIDIA

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

Models
3
Results
3
Boards
3 of 13

www.nvidia.com

Models

ModelKindReleasedBoards
Nemotron 3.5 LightningModel11 Aug 20261
Nemotron 3 UltraModel4 Jun 20261
NVIDIA Nemotron 3 Ultra 550B A55BModel4 Jun 20261

Results

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

Documentation and coding

  1. MedScribe (Vals AI)
    Nemotron 3.5 Lightning
    model ID fireworks/nemotron-lightning-3p5-30b-a3b; temperature=1; top_p=0.95; max_output_tokens=30000
    4.27
    Rank 105 of 105Leader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  2. MedCode (Vals AI)
    Nemotron 3 Ultra
    model ID nvidia/nemotron-3-ultra-550b-a55b; temperature=1; top_p=0.95; max_output_tokens=30000
    38.62
    Rank 67 of 103Leader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026

EHR and workflow agents

  1. CHI-Bench
    openai-agents + Nemotron 3 Ultra 256K
    All Domains pass@1; openai-agents; Tinker 256K
    0.0
    Rank 43 of 43 here, 45 models on the boardLeader erius + claude-opus-5 54.7
    Official leaderboard
    Measured Jul 2026