SaaS-Bench - Multimodal: 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 tasks that use images, documents or media files; higher is better.
Metric: Checkpoint score (%) on the 32 multimodal tasks (images, documents and media files as inputs), 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 2029. 11 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 4.6 | 48.7 | #114 | |
| 2 | GPT-5.5 | High | 47.6 | #56 |
| 3 | Claude Opus 4.7 | 46.3 | #86 | |
| 4 | GPT-5.4 | High | 46.1 | #138 |
| 5 | Qwen 3.6 Plus | 45.5 | #245 | |
| 6 | Seed 2.0 Pro | 44.2 | #226 | |
| 7 | Kimi K2.6 | 43.5 | #197 | |
| 8 | Gemini 3.1 Pro (Preview) | 42.4 | #102 | |
| 9 | Kimi K2.5 | 37 | #272 | |
| 10 | Gemini 3.5 Flash | High | 36.5 | #110 |
| 11 | Claude Sonnet 4.6 | 33.9 | #179 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=saas-bench-multimodal · How It Works · Data refreshed daily, snapshot 2026-11-22.