When Seekers Are Hard to Help: leaderboard
Emotional Support Dialogue Systems (ESDSes) are increasingly evaluated and trained with LLM-simulated seekers. However, such simulated seekers often behave as cooperative, average-case users who disclose clearly, respond constructively, and accept support within a few turns. This can lead to overly optimistic evaluation and obscure whether ESDSes can handle difficult help-seeking interactions. In
Metric: DEU (Deep Emotional Understanding) (self-reported). Source: benchmarklist.com. Saturation forecast: Around April 2027. 17 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 | 2.92 | #79 |
| 2 | GPT-4o | 1.76 | #343 |
| 3 | Qwen 3 8B | 1.76 | #674 |
| 4 | Qwen 3 4B | 1.74 | #829 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=when-seekers-are-hard-to-help · How It Works · Data refreshed daily, snapshot 2026-10-20.