Sentiment Analysis on MOSEI (held-out)
72.4F1 ScoreOMNISAPIENS-7B SFT
Evaluation results
| Method | Links | |
|---|---|---|
| OMNISAPIENS-7B SFTfine-tuning epochs=1, training mode=SFT2025.10 | 72.4 | |
| HumanOmniV2-7Bfine-tuning epochs=0, training mode=pre-trained2025.10 | 63.3 | |
| Gemma-3-4Bfine-tuning epochs=0, training mode=pre-trained2025.10 | 61.7 | |
| Qwen 2.5-Omni-7B SFTfine-tuning epochs=1, training mode=SFT2025.10 | 61.2 | |
| Qwen 2.5-Omni-7Bfine-tuning epochs=0, training mode=pre-trained2025.10 | 60.2 | |
| Qwen-2.5-VL-7Bfine-tuning epochs=0, training mode=pre-trained2025.10 | 31.7 | |
| OMNISAPIENS-7B RLzero-shot=true2025.10 | 24.7 | |
| Qwen 2.5-Omni-7Bzero-shot=true2025.10 | 20.1 |