Audio-Visual Reasoning on Riva (StandUp)
81.7AccuracyQwen3-Omni
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen3-OmniReasoning=true, Model Size=30B, Zero-shot=true2026.04 | 81.7 | |
| v-SALMONN-o1Reasoning=true, Model Size=7B, Zero-shot=true2026.04 | 76.7 | |
| AVRTReasoning=true, Model Size=7B, Zero-shot=true2026.04 | 75.3 | |
| Qwen2.5 OmniReasoning=false, Model Size=7B, Zero-shot=true2026.04 | 74.9 | |
| Kimi-VL-ThinkingReasoning=true, Model Size=Teacher, Zero-shot=true2026.04 | 72.3 | |
| AVRTReasoning=true, Model Size=3B, Zero-shot=true2026.04 | 71.3 | |
| V-RTSReasoning=true, Model Size=7B, Zero-shot=true2026.04 | 70.3 | |
| AF3 (think)Reasoning=true, Model Size=Teacher, Zero-shot=true2026.04 | 65.5 | |
| Qwen2.5 OmniReasoning=false, Model Size=3B, Zero-shot=true2026.04 | 62.4 |