Model
Qwen3-Omni-30B-A3B-Thinking
Alibaba · open weights
Agentic / Tool Use
Agentic / Tool UseMultimodal
Multimodal| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| OmniHalluBench | 57.0 | f1 | sc | Independent | medium | arxiv.org |
| OmniReasoningBench | 87.5 | overall | N/A | Independent | medium | arxiv.org |
Reproduced by the community
Loading community runs…