Multiple-choice Question Answering on Text-only Adaptive Benchmark L3
88Pass@1 AccuracyQwen3-Omni
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Qwen3-OmniModel Category=Omni models2025.12 | 88 | 0 | |
| AdaptThinkModel Category=Expert models2025.12 | 87 | 90 | |
| DeepSeek-R1-7BModel Category=Expert models2025.12 | 84 | 94 | |
| Omni-AutoThinkModel Category=Omni models2025.12 | 67 | 52 | |
| Qwen2.5-OmniModel Category=Omni models2025.12 | 38 | 23 |