Emotional Reasoning on Emotion6 In-domain
71.72AccuracyEMO-R3
Evaluation Results
| Method | Links | |
|---|---|---|
| EMO-R3Backbone=Qwen2.5-VL-3B-Instruct, Roll-out=8, Post-training=true2026.02 | 71.72 | |
| GRPOBackbone=Qwen2.5-VL-3B-Instruct, Roll-out=4, Post-training=true2026.02 | 70.88 | |
| EMO-R3Backbone=Qwen2.5-VL-3B-Instruct, Roll-out=4, Post-training=true2026.02 | 70.71 | |
| GRPOBackbone=Qwen2.5-VL-3B-Instruct, Roll-out=8, Post-training=true2026.02 | 69.87 | |
| SFTBackbone=Qwen2.5-VL-3B-Instruct, Roll-out=-, Post-training=true2026.02 | 69.53 | |
| DAPOBackbone=Qwen2.5-VL-3B-Instruct, Roll-out=4, Post-training=true2026.02 | 68.56 | |
| DAPOBackbone=Qwen2.5-VL-3B-Instruct, Roll-out=8, Post-training=true2026.02 | 62.39 | |
| SEPM*Backbone=LLaVA1.5-7B, Roll-out=-, Post-training=false2026.02 | 54.21 | |
| Vanilla*Backbone=Qwen2.5-VL-3B-Instruct, Roll-out=-, Post-training=false2026.02 | 50 | |
| Vanilla*Backbone=LLaVA1.5-7B, Roll-out=-, Post-training=false2026.02 | 48.32 |