Multiple-choice Question Answering on Text-only Adaptive Benchmark (ALL)
81Pass@1 AccQwen3-Omni
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Qwen3-OmniModel Category=Omni models2025.12 | 81 | 0 | |
| AdaptThinkModel Category=Expert models2025.12 | 76 | 87 | |
| DeepSeek-R1-7BModel Category=Expert models2025.12 | 74 | 89 | |
| Omni-AutoThinkModel Category=Omni models2025.12 | 66 | 48 | |
| Qwen2.5-OmniModel Category=Omni models2025.12 | 35 | 26 |