HAS-Bench - Retail Task Score: leaderboard

Metric: Task score (%; mean partial credit over the task dimensions of the 94 retail tasks) under Equal Partnership (A3) human participation: the agent may ask a GPT-4.1-simulated human for clarification, feedback and control, temperature 0, one rollout per task; GPT-4.1 judge; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 5 models tracked.

Top models

#ModelScore
1Claude Sonnet 461.5
2GPT-4.159
3GPT-4.1 Mini55.1
4DeepSeek V3 (0324)53.5
5Llama 3.1 8B7.2

Interactive version: theaggregate.ai/benchmark?slug=has-bench-retail-task-score · How It Works · Data refreshed daily, snapshot 2026-09-29.