SaaS-Bench - Healthcare Administration: leaderboard

SaaS-Bench (2026) evaluates computer-use agents on long professional workflows across 23 self-hosted SaaS systems, scoring weighted verification checkpoints on the final application state. This board is the checkpoint score in percent on the healthcare administration domain; higher is better.

Metric: Checkpoint score (%) on the healthcare administration domain, weighted-checkpoint score over the final application states, browser-use agent loop over live self-hosted SaaS apps (DOM and screenshot observations, restricted browser actions, no JavaScript or backend access), same step budget, timeout and failure cap for every model; higher is better. Source: arxiv.org. Saturation forecast: Around 2028. 14 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-5.5High30.9#54
2Claude Opus 4.729.7#85
3Claude Opus 4.627.2#113
4GPT-5.4High26.8#135
5Kimi K2.626.2#192
6GLM-5.124#198
7Kimi K2.520.2#266
8Gemini 3.1 Pro (Preview)20#99
9Qwen 3.6 Plus18.9#238
10MiniMax-M2.717.7#539
11DeepSeek V4 Pro17.1#196
12Gemini 3.5 FlashHigh14.5#106
13Seed 2.0 Pro13.6#222
14Claude Sonnet 4.69.5#173

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=saas-bench-healthcare-administration · How It Works · Data refreshed daily, snapshot 2026-11-21.