Emotional Intelligence Evaluation on EIBench (test)
43.8CHARM ScoreClaude-Sonnet-4.6
Evaluation results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude-Sonnet-4.62026.06 | 43.8 | 14.6 | 17.9 | 56.5 | 23 | 1 | 24 | 1 | 1,548 | 4 | |
| GPT-5.42026.06 | 41.5 | 9.5 | 14.5 | 49 | 21.4 | 2 | 22.7 | 3 | 1,593 | 3 | |
| Qwen3.6-Max-Preview2026.06 | 39.1 | 14.3 | 14.7 | 42.7 | 17.9 | 7 | 19.9 | 6 | 1,519 | 6 | |
| GLM-5.12026.06 | 37.9 | 15.2 | 19.3 | 44.8 | 19.1 | 6 | 19.4 | 7 | 1,504 | 7 | |
| Kimi-K2.62026.06 | 37.3 | 8.8 | 17.6 | 42.1 | 19.8 | 5 | 21.9 | 4 | 1,478 | 10 | |
| Gemini-3-Flash2026.06 | 37 | 11.1 | 18.1 | 34 | 17.2 | 8 | 16.5 | 10 | 1,606 | 2 | |
| Qwen3-Max2026.06 | 32 | 2.4 | 14.1 | 45.7 | 20.6 | 3 | 14.8 | 11 | 1,487 | 8 | |
| Doubao-Seed-2.0-Pro2026.06 | 31.9 | 14.2 | 10.7 | 39.8 | 14.8 | 9 | 17 | 9 | 1,536 | 5 | |
| Gemini-3.1-Pro2026.06 | 31.3 | 2.5 | 18.6 | 39.3 | 20 | 4 | 21.5 | 5 | 1,616 | 1 | |
| Grok-4.202026.06 | 31 | 13.5 | 5.1 | 38.4 | 13.1 | 12 | 13 | 12 | 1,476 | 11 | |
| DeepSeek-V4-Pro2026.06 | 28 | 7.8 | 12.2 | 32.4 | 14.4 | 10 | 23.3 | 2 | 1,484 | 9 | |
| Grok-4.20-Reasoning2026.06 | 28 | 19 | 12.2 | 40.9 | 13.1 | 11 | 10.6 | 13 | 1,458 | 13 | |
| Qwen3-32B2026.06 | 23.7 | 14.3 | 6.8 | 3.9 | 3.4 | 14 | 5.8 | 14 | 1,405 | 14 | |
| MiniMax-M2.52026.06 | 21.6 | 16.7 | 5.2 | 31.4 | 8.4 | 13 | 17.6 | 8 | 1,471 | 12 | |
| Qwen3-8B2026.06 | 14.6 | 21.4 | 35.9 | 43.3 | 22.4 | 15 | 23.7 | 15 | 1,316 | 15 |