Closed-ended Task T-3 on DanmakuTPP-QA
120.79RMSEQwen3-235B-A22B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-235B-A22BModel Category=LLMs2026.02 | 120.79 | |
| Qwen2.5-VL-72BModel Category=MLLMs2026.02 | 121.25 | |
| DeepSeek-V3Model Category=LLMs2026.02 | 121.3 | |
| Gemma3-27BModel Category=MLLMs2026.02 | 121.32 | |
| Llama-3.3-70B-InstructModel Category=LLMs2026.02 | 121.49 | |
| Qwen3-30B-A3BModel Category=LLMs2026.02 | 121.96 | |
| Qwen2.5-32B-InstructModel Category=LLMs2026.02 | 122.69 | |
| Qwen2.5-72B-InstructModel Category=LLMs2026.02 | 123.45 | |
| Qwen3-8BModel Category=LLMs2026.02 | 123.59 | |
| Qwen2.5-VL-32BModel Category=MLLMs2026.02 | 124.02 | |
| Qwen2.5-VL-7BModel Category=MLLMs2026.02 | 124.99 | |
| Qwen2.5-7B-InstructModel Category=LLMs2026.02 | 134.45 | |
| MM-TPPModel Category=Finetuned2026.02 | 190.45 | |
| Qwen2.5-VL-3BModel Category=Finetuned2026.02 | 220.43 |