SaaS-Bench - Artisan Agri-Food Supply Chain: leaderboard

Metric: Checkpoint score (%) on the artisan agri-food supply chain domain (multimodal), 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: Not forecast. 11 models tracked.

Top models

#ModelScore
1GPT-5.4 (High)53.4
2Qwen 3.6 Plus52.6
3GPT-5.5 (High)51.7
4Kimi K2.551.3
5Kimi K2.650.1
6Seed 2.0 Pro46.4
7Claude Opus 4.746.3
8Claude Opus 4.642
9Gemini 3.1 Pro (Preview)38.5
10Gemini 3.5 Flash (High)35.9
11Claude Sonnet 4.634.1

Interactive version: theaggregate.ai/benchmark?slug=saas-bench-artisan-agri-food-supply-chain · How It Works · Data refreshed daily, snapshot 2026-10-07.