DAYJOB: Healthcare
Long agent assignments from healthcare professionals, from clinical decision support to pharmacy and payer work.
More about this boardLess
Fifty long-horizon assignments written by healthcare professionals across clinical decision support, pharmacy, payer and revenue-cycle work, and quality and compliance reviews; the agent works from charts, claims exports and policies to finish a brief request.
Published by Surge AI, released Sep 2026. 50 long-horizon healthcare assignments. Pass@1 at 95% (share of assignments passed), higher better.
- Run by
- Surge AI runs it; Fireworks imports the results Surge supplied
- Headline metric
- Score (pass@1 at 95%)
- Task count
- 50
- Board last updated
- 28 Oct 2026
- Publisher
- Surge AI
- Rows
- 15
- Models
- 15 on the board
- Released
- Sep 2026
- Measured to
- Oct 2026
- Unit
- 50 assignments
- Documents cited
- 1
Every result on DAYJOB Health, on the board's own scale
15 results, one column each, highest first. Pass@1 at 95% (share of assignments passed), higher better.
Column colour is the model's lab. The table below says who ran each result.
Every published result, ranked on this board alone
15 rows. Higher is better. Bars run from 0 to 100; whiskers show a published interval. Select a row for its quote, page and document.
1Claude Opus 5.5Anthropic · Score48.3Board publisherOct 2026[1]
Claude Opus 5.5 48.3 (Score (pass@1 at 95%)), rank 1
2Claude Sonnet 5.5Anthropic · Score34Board publisherOct 2026[1]
Claude Sonnet 5.5 34 (Score (pass@1 at 95%)), rank 2
3Claude Fable 5.1Anthropic · Score31.2Board publisherOct 2026[1]
Claude Fable 5.1 31.2 (Score (pass@1 at 95%)), rank 4
3Muse Wonder 1.0Meta · Score31.2Board publisherOct 2026[1]
Muse Wonder 1.0 31.2 (Score (pass@1 at 95%)), rank 3
5GPT-6 AstraOpenAI · Score28.4Board publisherOct 2026[1]
GPT-6 Astra 28.4 (Score (pass@1 at 95%)), rank 5
6Grok 4.7SpaceX AI · Score27.6Board publisherOct 2026[1]
Grok 4.7 27.6 (Score (pass@1 at 95%)), rank 6
7GPT-6.1 SolOpenAI · Score25.2Board publisherOct 2026[1]
GPT-6.1 Sol 25.2 (Score (pass@1 at 95%)), rank 7
8Gemini 4 ArgonGoogle · Score23.6Board publisherOct 2026[1]
Gemini 4 Argon 23.6 (Score (pass@1 at 95%)), rank 8
9Claude Opus 5Anthropic · Score22Board publisherOct 2026[1]
Claude Opus 5 22 (Score (pass@1 at 95%)), rank 9
9Muse Spark 1.3Meta · Score22Board publisherOct 2026[1]
Muse Spark 1.3 22 (Score (pass@1 at 95%)), rank 10
11Grok 4.6SpaceX AI · Score14.8Board publisherOct 2026[1]
Grok 4.6 14.8 (Score (pass@1 at 95%)), rank 11
12Claude Fable 5Anthropic · Score11.2Board publisherOct 2026[1]
Claude Fable 5 11.2 (Score (pass@1 at 95%)), rank 12
13Muse Spark 1.2Meta · Score8.8Board publisherOct 2026[1]
Muse Spark 1.2 8.8 (Score (pass@1 at 95%)), rank 13
14GPT-6 SolOpenAI · Score7.2Board publisherOct 2026[1]
GPT-6 Sol 7.2 (Score (pass@1 at 95%)), rank 14
15Hy4 PreviewTencent · Score6.4Board publisherOct 2026[1]
Hy4 Preview 6.4 (Score (pass@1 at 95%)), rank 15
1 document supports this board
- 1.DAYJOB: Healthcare on the Fireworks Specialized Intelligence Indexofficial leaderboard, Fireworks AI, 28 Oct 2026. Every result it supports