Single-choice question answering on SCQ
65AccuracySFT with Hybrid data
Evaluation Results
| Method | Links | |
|---|---|---|
| SFT with Hybrid dataModel Configuration=SFT with Hybrid data, Backbone=Qwen2.5-Omni-7B2025.12 | 65 | |
| SFT with Human-only dataModel Configuration=SFT with Human-only data, Backbone=Qwen2.5-Omni-7B2025.12 | 60 | |
| GPT-4o-AudioModel Configuration=GPT-4o-Audio2025.12 | 58.3 | |
| Gemini-2.5-FlashModel Configuration=Gemini-2.5-Flash2025.12 | 45 | |
| Gemini-2.5-ProModel Configuration=Gemini-2.5-Pro2025.12 | 45 | |
| SFT with MLLM-only dataModel Configuration=SFT with MLLM-only data, Backbone=Qwen2.5-Omni-7B2025.12 | 37.5 | |
| GPT-4o-Mini-AudioModel Configuration=GPT-4o-Mini-Audio2025.12 | 36.8 | |
| Qwen2-Audio-7BModel Configuration=Qwen2-Audio-7B2025.12 | 32.5 | |
| Qwen2.5-Omni-7BModel Configuration=Qwen2.5-Omni-7B2025.12 | 20 |