GPT-5.6 Luna on HealthBench Professional

rank 7 of 9 · updated August 16, 2026

GPT-5.6 Luna scores 0.557 on HealthBench Professional, rank 7 of 9 evaluated models. The small, high-volume tier of the GPT-5.6 family, repriced to $0.20 per million input tokens on July 30, 2026. HealthBench Professional scores models on 525 tasks drawn from real clinician conversations, graded criterion by criterion against physician-written rubrics on a 0 to 1 scale.

Result and API facts

Position in the field

The gap to the leader, Claude Fable 5 at 0.660, is 0.103. Directly above sits Claude Opus 4.8 at 0.558. Directly below sits GPT-5.5 Instant at 0.384. Scores on this page come from the same evaluation run, so differences between models are differences on identical tasks, not across configurations.

Head to head

Pairings with a dedicated comparison page are linked; every other difference is in the score-difference matrix.

• GPT-5.6 Luna vs Claude Fable 5
  0.557 vs 0.660 · Claude Fable 5 by 0.103
• GPT-5.6 Luna vs GPT-5.6 Sol
  0.557 vs 0.605 · GPT-5.6 Sol by 0.048
• GPT-5.6 Luna vs Claude Opus 5
  0.557 vs 0.598 · Claude Opus 5 by 0.041
• GPT-5.6 Luna vs Claude Sonnet 5
  0.557 vs 0.578 · Claude Sonnet 5 by 0.021
• GPT-5.6 Luna vs GPT-5.6 Terra
  0.557 vs 0.577 · GPT-5.6 Terra by 0.020
• GPT-5.6 Luna vs Claude Opus 4.8
  0.557 vs 0.558 · Claude Opus 4.8 by 0.001
• GPT-5.6 Luna vs GPT-5.5 Instant
  0.557 vs 0.384 · GPT-5.6 Luna by 0.173
• GPT-5.6 Luna vs MAI-Thinking-1
  0.557 vs 0.350 · GPT-5.6 Luna by 0.207

How tasks are selected and graded is on the methodology page. The full ranking is on the leaderboard.