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
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4 | 61.5 |
| 2 | GPT-4.1 | 59 |
| 3 | GPT-4.1 Mini | 55.1 |
| 4 | DeepSeek V3 (0324) | 53.5 |
| 5 | Llama 3.1 8B | 7.2 |
Interactive version: theaggregate.ai/benchmark?slug=has-bench-retail-task-score · How It Works · Data refreshed daily, snapshot 2026-09-29.