HealthBench Professional

Updates

Every change to the leaderboard, dated: models added, sources located or replaced, methodology corrections, and price corrections. Each entry keeps a stable anchor.

Change history

DateChange
Sourcing correction. The site previously described its scores as produced by Arcophos under a run protocol. That was wrong: Arcophos does not run HealthBench Professional. The scores are compiled from published documents and now come from the Arcophos benchmark results database. Every row carries a source field, links to its document on the sources page, and is marked source pending until a published document is matched to it. 0 of 43 rows are source pending as of this entry. The methodology page was rewritten to match. The JSON download gained a source object per row and the CSV gained source_name and source_url columns.
Initial release. 43 models listed on the 525-task set: GPT-6 Astra (Anthropic run), Claude Sonnet 5.5, Claude Fable 5, Claude Opus 5.5, GPT-6 Luna (Anthropic run), Claude Haiku 5.5, GPT-6 Astra, GPT-6.1 Sol, Claude Fable 5 (September card), GPT-6.1 Terra, Muse Wonder Full, Claude Fable 5.1, GPT-6 Luna, GPT-6 Sol, GPT-5.6 Sol, Muse Wonder, Claude Opus 5, Muse Spark 1.1, Claude Sonnet 5, GPT-5.6 Terra, Claude Opus 4.8 (Opus 4.8 grader), Grok 4.7, Claude Opus 4.8, GPT-5.6 Luna, Gemini 4 Argon, Muse Spark, GPT-5.6 Sol (August), Kimi K3, GLM 5.3, Claude Opus 4.7, GPT-5.5, Gemini 3.8 Flash, DeepSeek V4.1 Flash, Grok 4.6, GPT-5.4, GPT-5, GPT-5.2, Claude Sonnet 4.6, GPT-5.6 Luna (August), GPT-5.1, GPT-5.5 Instant, MAI-Thinking-1, Claude Haiku 4.5. List prices verified against vendor price sheets on this date.

The current table is on the leaderboard; versioned downloads are on the data page.