5h ago

Anthropic Claude Code Opus Tops AI Leaderboard for Healthcare Tasks

——0——
Original post
Sanmi KoyejoSK#1085@SANMIKOYEJOOPWeiran YaoWYWeiran Yao|@ISCREAMNEARBY

4/🧵Leaderboard Results Best overall: Anthropic's Claude Code Opus 4.6 — 28% pass@1. Runner-up: OpenAI's Codex GPT-5.5 — 21%. By domain: utilization review 41%; care management 32%; prior-auth paperwork 29%.

9:25 AM · May 20, 2026 View on X
Reposted by
Sanmi KoyejoSK#1085|@SANMIKOYEJO

Sentiment

Pos100%
Neg0%

Users are praising Claude Code Opus 4.6 for topping the CHI-Bench healthcare AI leaderboard because it recognizes the team's valuable work and fills a much-needed gap in specialized benchmarks.

2 comments with sentiment.

3630343

Cluster engagement

23 snapshots