SaaS-Bench: leaderboard
Computer-Using Agents (CUAs) are rapidly extending large language models (LLMs) beyond text-based reasoning toward action execution in more complex environments, such as web browsers and graphical user interfaces (GUIs). However, existing web and GUI agent benchmarks often rely on simplified settings, isolated tasks, or short-horizon interactions, making it difficult to assess capabilities of agen
Metric: Overall (self-reported). Source: benchmarklist.com. Saturation forecast: Around September 2027. 17 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.7 | 43.9 | #49 |
| 2 | GPT-5.5 (High) | 43.8 | #31 (GPT-5.5) |
| 3 | Claude Opus 4.6 | 43.2 | #63 |
| 4 | GPT-5.4 (High) | 37 | #79 (GPT-5.4) |
| 5 | Kimi K2.6 | 34.1 | #104 |
| 6 | Qwen 3.6 Plus | 29.9 | #120 |
| 7 | Kimi K2.5 | 27.7 | #144 |
| 8 | Gemini 3.1 Pro (Preview) | 27.1 | #58 |
| 9 | Seed 2.0 Pro | 27.1 | #118 |
| 10 | Step 3.7 Flash | 25.1 | #236 |
| 11 | Claude Sonnet 4.6 | 23.3 | #90 |
| 12 | Gemini 3.5 Flash (High) | 23.3 | #60 (Gemini 3.5 Flash) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=saas-bench · How It Works · Data refreshed daily, snapshot 2026-10-20.