RCM-Bench-1

Revenue cycle tasks: claims, billing, insurance updates and eligibility checks, checked on the resulting system state.

More about this boardLess

Ninety-seven revenue cycle management scenarios across claim submission, encounter and patient billing, insurance updates, eligibility checks and RCM knowledge, checked on tool calls, arguments, responses and resulting system state.

Published by Commure, released Oct 2026. 97 revenue cycle scenarios in six workflows. Score % (avg@3), higher better.

Run by: Commure runs it; Fireworks publishes the provider's results
Headline metric: Score (avg@3)
Task count: 97
Board last updated: 22 Oct 2026

Publisher: Commure
Rows: 20
Models: 20 on the board
Released: Oct 2026
Measured to: Oct 2026
Unit: 97 RCM tasks
Documents cited: 1

Every result on RCM-Bench, on the board's own scale

20 results, one column each, highest first. Score % (avg@3), 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

20 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 5Anthropic · Score92.68Board publisherOct 2026[1]

Claude Opus 5 92.6789 (Score (avg@3)), rank 1

As printed: 92.68
Where: https://fireworks.ai/specialized-intelligence-index/benchmarks/healthcare/rcm-benchmark-1 (feed: benchmarks[id=healthcare/rcm-benchmark-1].results)
Setting: Score (avg@3), provider-default reasoning
Reported by: official leaderboard
Document: [1] RCM-Bench-1 on the Fireworks Specialized Intelligence Index

2Gemini 4 ArgonGoogle · Score91.49Board publisherOct 2026[1]

Gemini 4 Argon 91.4878 (Score (avg@3)), rank 2

As printed: 91.49
Where: https://fireworks.ai/specialized-intelligence-index/benchmarks/healthcare/rcm-benchmark-1 (feed: benchmarks[id=healthcare/rcm-benchmark-1].results)
Setting: Score (avg@3), medium reasoning
Reported by: official leaderboard
Document: [1] RCM-Bench-1 on the Fireworks Specialized Intelligence Index

3Claude Sonnet 5Anthropic · Score91.24Board publisherOct 2026[1]

Claude Sonnet 5 91.2437 (Score (avg@3)), rank 3

As printed: 91.24
Where: https://fireworks.ai/specialized-intelligence-index/benchmarks/healthcare/rcm-benchmark-1 (feed: benchmarks[id=healthcare/rcm-benchmark-1].results)
Setting: Score (avg@3), provider-default reasoning
Reported by: official leaderboard
Document: [1] RCM-Bench-1 on the Fireworks Specialized Intelligence Index

4GPT-5.6 SolOpenAI · Score91.21Board publisherOct 2026[1]

GPT-5.6 Sol 91.2121 (Score (avg@3)), rank 4

As printed: 91.21
Where: https://fireworks.ai/specialized-intelligence-index/benchmarks/healthcare/rcm-benchmark-1 (feed: benchmarks[id=healthcare/rcm-benchmark-1].results)
Setting: Score (avg@3), medium reasoning
Reported by: official leaderboard
Document: [1] RCM-Bench-1 on the Fireworks Specialized Intelligence Index

5Claude Sonnet 5.5Anthropic · Score91.05Board publisherOct 2026[1]

Claude Sonnet 5.5 91.0501 (Score (avg@3)), rank 5

As printed: 91.05
Where: https://fireworks.ai/specialized-intelligence-index/benchmarks/healthcare/rcm-benchmark-1 (feed: benchmarks[id=healthcare/rcm-benchmark-1].results)
Setting: Score (avg@3), provider-default reasoning
Reported by: official leaderboard
Document: [1] RCM-Bench-1 on the Fireworks Specialized Intelligence Index

6Gemini 3.8 FlashGoogle · Score90.23Board publisherOct 2026[1]

Gemini 3.8 Flash 90.2336 (Score (avg@3)), rank 6

As printed: 90.23
Where: https://fireworks.ai/specialized-intelligence-index/benchmarks/healthcare/rcm-benchmark-1 (feed: benchmarks[id=healthcare/rcm-benchmark-1].results)
Setting: Score (avg@3), medium reasoning
Reported by: official leaderboard
Document: [1] RCM-Bench-1 on the Fireworks Specialized Intelligence Index

7Claude Opus 5.5Anthropic · Score90.14Board publisherOct 2026[1]

Claude Opus 5.5 90.1389 (Score (avg@3)), rank 7

As printed: 90.14
Where: https://fireworks.ai/specialized-intelligence-index/benchmarks/healthcare/rcm-benchmark-1 (feed: benchmarks[id=healthcare/rcm-benchmark-1].results)
Setting: Score (avg@3), provider-default reasoning
Reported by: official leaderboard
Document: [1] RCM-Bench-1 on the Fireworks Specialized Intelligence Index

8Claude Sonnet 4.6Anthropic · Score89.82Board publisherOct 2026[1]

Claude Sonnet 4.6 89.8232 (Score (avg@3)), rank 8

As printed: 89.82
Where: https://fireworks.ai/specialized-intelligence-index/benchmarks/healthcare/rcm-benchmark-1 (feed: benchmarks[id=healthcare/rcm-benchmark-1].results)
Setting: Score (avg@3), provider-default reasoning
Reported by: official leaderboard
Document: [1] RCM-Bench-1 on the Fireworks Specialized Intelligence Index

9DeepSeek V4.1 FlashDeepSeek · Score88.99Board publisherOct 2026[1]

DeepSeek V4.1 Flash 88.9857 (Score (avg@3)), rank 9

As printed: 88.99
Where: https://fireworks.ai/specialized-intelligence-index/benchmarks/healthcare/rcm-benchmark-1 (feed: benchmarks[id=healthcare/rcm-benchmark-1].results)
Setting: Score (avg@3), provider-default reasoning
Reported by: official leaderboard
Document: [1] RCM-Bench-1 on the Fireworks Specialized Intelligence Index

10Claude Haiku 5.5Anthropic · Score88.38Board publisherOct 2026[1]

Claude Haiku 5.5 88.3775 (Score (avg@3)), rank 10

As printed: 88.38
Where: https://fireworks.ai/specialized-intelligence-index/benchmarks/healthcare/rcm-benchmark-1 (feed: benchmarks[id=healthcare/rcm-benchmark-1].results)
Setting: Score (avg@3), provider-default reasoning
Reported by: official leaderboard
Document: [1] RCM-Bench-1 on the Fireworks Specialized Intelligence Index

11GLM 5.3Zhipu · Score88.30Board publisherOct 2026[1]

GLM 5.3 88.3039 (Score (avg@3)), rank 11

As printed: 88.30
Where: https://fireworks.ai/specialized-intelligence-index/benchmarks/healthcare/rcm-benchmark-1 (feed: benchmarks[id=healthcare/rcm-benchmark-1].results)
Setting: Score (avg@3), provider-default reasoning
Reported by: official leaderboard
Document: [1] RCM-Bench-1 on the Fireworks Specialized Intelligence Index

12Grok 4.7SpaceX AI · Score88.16Board publisherOct 2026[1]

Grok 4.7 88.1566 (Score (avg@3)), rank 12

As printed: 88.16
Where: https://fireworks.ai/specialized-intelligence-index/benchmarks/healthcare/rcm-benchmark-1 (feed: benchmarks[id=healthcare/rcm-benchmark-1].results)
Setting: Score (avg@3), provider-default reasoning
Reported by: official leaderboard
Document: [1] RCM-Bench-1 on the Fireworks Specialized Intelligence Index

13Claude Opus 4.6Anthropic · Score87.85Board publisherOct 2026[1]

Claude Opus 4.6 87.8472 (Score (avg@3)), rank 13

As printed: 87.85
Where: https://fireworks.ai/specialized-intelligence-index/benchmarks/healthcare/rcm-benchmark-1 (feed: benchmarks[id=healthcare/rcm-benchmark-1].results)
Setting: Score (avg@3), provider-default reasoning
Reported by: official leaderboard
Document: [1] RCM-Bench-1 on the Fireworks Specialized Intelligence Index

14GPT-6.1 SolOpenAI · Score87.37Board publisherOct 2026[1]

GPT-6.1 Sol 87.3737 (Score (avg@3)), rank 14

As printed: 87.37
Where: https://fireworks.ai/specialized-intelligence-index/benchmarks/healthcare/rcm-benchmark-1 (feed: benchmarks[id=healthcare/rcm-benchmark-1].results)
Setting: Score (avg@3), medium reasoning
Reported by: official leaderboard
Document: [1] RCM-Bench-1 on the Fireworks Specialized Intelligence Index

15GPT-5.6 TerraOpenAI · Score86.96Board publisherOct 2026[1]

GPT-5.6 Terra 86.9613 (Score (avg@3)), rank 15

As printed: 86.96
Where: https://fireworks.ai/specialized-intelligence-index/benchmarks/healthcare/rcm-benchmark-1 (feed: benchmarks[id=healthcare/rcm-benchmark-1].results)
Setting: Score (avg@3), medium reasoning
Reported by: official leaderboard
Document: [1] RCM-Bench-1 on the Fireworks Specialized Intelligence Index

16GPT-6 LunaOpenAI · Score85.81Board publisherOct 2026[1]

GPT-6 Luna 85.8081 (Score (avg@3)), rank 16

As printed: 85.81
Where: https://fireworks.ai/specialized-intelligence-index/benchmarks/healthcare/rcm-benchmark-1 (feed: benchmarks[id=healthcare/rcm-benchmark-1].results)
Setting: Score (avg@3), medium reasoning
Reported by: official leaderboard
Document: [1] RCM-Bench-1 on the Fireworks Specialized Intelligence Index

17GPT-5 miniOpenAI · Score84.28Board publisherOct 2026[1]

GPT-5 mini 84.2761 (Score (avg@3)), rank 17

As printed: 84.28
Where: https://fireworks.ai/specialized-intelligence-index/benchmarks/healthcare/rcm-benchmark-1 (feed: benchmarks[id=healthcare/rcm-benchmark-1].results)
Setting: Score (avg@3), provider-default reasoning
Reported by: official leaderboard
Document: [1] RCM-Bench-1 on the Fireworks Specialized Intelligence Index

18GPT-6 SolOpenAI · Score81.53Board publisherOct 2026[1]

GPT-6 Sol 81.5341 (Score (avg@3)), rank 18

As printed: 81.53
Where: https://fireworks.ai/specialized-intelligence-index/benchmarks/healthcare/rcm-benchmark-1 (feed: benchmarks[id=healthcare/rcm-benchmark-1].results)
Setting: Score (avg@3), medium reasoning
Reported by: official leaderboard
Document: [1] RCM-Bench-1 on the Fireworks Specialized Intelligence Index

19GPT-5.6 LunaOpenAI · Score71.48Board publisherOct 2026[1]

GPT-5.6 Luna 71.4815 (Score (avg@3)), rank 19

As printed: 71.48
Where: https://fireworks.ai/specialized-intelligence-index/benchmarks/healthcare/rcm-benchmark-1 (feed: benchmarks[id=healthcare/rcm-benchmark-1].results)
Setting: Score (avg@3), reasoning disabled for tool compatibility
Reported by: official leaderboard
Document: [1] RCM-Bench-1 on the Fireworks Specialized Intelligence Index

20Claude Haiku 4.5Anthropic · Score70.23Board publisherOct 2026[1]

Claude Haiku 4.5 70.2336 (Score (avg@3)), rank 20

As printed: 70.23
Where: https://fireworks.ai/specialized-intelligence-index/benchmarks/healthcare/rcm-benchmark-1 (feed: benchmarks[id=healthcare/rcm-benchmark-1].results)
Setting: Score (avg@3), provider-default reasoning
Reported by: official leaderboard
Document: [1] RCM-Bench-1 on the Fireworks Specialized Intelligence Index

References

1 document supports this board

1.RCM-Bench-1 on the Fireworks Specialized Intelligence Indexofficial leaderboard, Fireworks AI, 22 Oct 2026. Every result it supports