TIDE-Bench - Interaction: leaderboard
Metric: Average customer score (out of 5): mean of the customer-facing success, satisfaction and tool-call behaviour scores (each 0-5) a kimi-k2-0905-preview judge gives the full trajectory of a merchant service agent over up to ten turns with five user-defined e-commerce tools and an API-model customer, 100 scripted scenarios in five service categories (TIDE-Bench Interaction track); higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 32B | 4.53 |
| 2 | Qwen 3 8B | 4.08 |
| 3 | Qwen 3 4B | 3.79 |
| 4 | GPT-5.4 | 3.57 |
| 5 | GPT-5 | 2.77 |
| 6 | GPT-4o | 1.62 |
Interactive version: theaggregate.ai/benchmark?slug=tide-bench-interaction · How It Works · Data refreshed daily, snapshot 2026-10-07.