Information Analysis and Processing on MARS Level 1 (test)
1.7Average Ranking (AI GPT-5)Ours
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| OursParam.=1800B2025.11 | 1.7 | 1.2 | |
| Qwen3-235B-AParam.=22B2025.11 | 3.4 | 2.9 | |
| Llama-3.2-11BParam.=11B2025.11 | 5.1 | 6.1 | |
| Llama-VisionParam.=11B2025.11 | 5.4 | 7.2 | |
| Qwen-VLParam.=7B2025.11 | 5.56 | 7.9 | |
| Llama-4-ScoutParam.=17B2025.11 | 5.9 | 6.89 | |
| GPT-ossParam.=20B2025.11 | 6.4 | 7.22 | |
| Llama-3.2-90BParam.=90B2025.11 | 6.8 | 4.8 | |
| Qwen2.5-VLParam.=72B2025.11 | 7.89 | 8 | |
| LLaVA-1.5Param.=7B2025.11 | 8.4 | 7 | |
| Qwen2-VLParam.=72B2025.11 | 8.56 | 6 |