SaaS-Bench - Business Operations and Finance: 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 business operations and finance domain; higher is better.

Metric: Checkpoint score (%) on the business operations and finance 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 June 2027. 14 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-5.5High36.4#54
2Claude Opus 4.633.2#113
3Claude Opus 4.731.8#85
4Kimi K2.630#192
5Gemini 3.5 FlashHigh22.7#106
6GPT-5.4High20.6#135
7Claude Sonnet 4.620.5#173
8Qwen 3.6 Plus15.3#238
9DeepSeek V4 Pro13.6#196
10Kimi K2.513.2#266
11Gemini 3.1 Pro (Preview)11.2#99
12GLM-5.110.9#198
13Seed 2.0 Pro10.8#222
14MiniMax-M2.76.9#539

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-business-operations-and-finance · How It Works · Data refreshed daily, snapshot 2026-11-21.