EIBench (Emotion Management) - Human Arena: leaderboard
Metric: Elo rating from more than 4,000 human pairwise judgments: annotators converse with two anonymized models under the same EIBench scenario profile and pick the one that handles it better; higher is better. Source: arxiv.org. Saturation forecast: Around June 2027. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 1616 |
| 2 | Gemini 3 Flash | 1606 |
| 3 | GPT-5.4 | 1593 |
| 4 | Claude Sonnet 4.6 | 1548 |
| 5 | Seed 2.0 Pro | 1536 |
| 6 | Qwen 3.6 Max Preview | 1519 |
| 7 | GLM-5.1 | 1504 |
| 8 | Qwen 3 Max | 1487 |
| 9 | DeepSeek V4 Pro | 1484 |
| 10 | Kimi K2.6 | 1478 |
| 11 | Grok 4.20 | 1476 |
| 12 | MiniMax-M2.5 | 1471 |
| 13 | Grok 4.20 (Reasoning) | 1458 |
| 14 | Qwen 3 32B | 1405 |
| 15 | Qwen 3 8B | 1316 |
Interactive version: theaggregate.ai/benchmark?slug=eibench-emotion-management-human-arena · How It Works · Data refreshed daily, snapshot 2026-09-29.