Visual Question Answering on Path-VQA (test)
2.69Commonsense ScoreLlama-3.2-11B-Vision-Instruct
Evaluation results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Llama-3.2-11B-Vision-InstructPrompting Strategy=CoD2025.05 | 2.69 | 2.45 | 2.42 | 2.57 | 2.43 | 2.44 | 2.43 | 9.09 | 9.13 | 2.43 | 3.79 | |
| Patho-R1-7BPrompting Strategy=CoD2025.05 | 2.38 | 1.77 | 1.71 | 1.77 | 1.99 | 1.93 | 1.77 | 8.05 | 8.77 | 1.89 | 3.2 | |
| Patho-R1-7BPrompting Strategy=CoT2025.05 | 2.37 | 1.82 | 1.77 | 1.83 | 2.02 | 1.96 | 1.82 | 8.2 | 8.79 | 1.94 | 3.25 | |
| InternVL3-8BPrompting Strategy=CoD2025.05 | 2.25 | 1.7 | 1.66 | 1.8 | 1.84 | 1.86 | 1.69 | 8.62 | 8.93 | 1.79 | 3.21 | |
| Patho-R1-3BPrompting Strategy=CoT2025.05 | 2.19 | 1.66 | 1.62 | 1.66 | 1.84 | 1.79 | 1.66 | 8.31 | 8.81 | 1.77 | 3.13 | |
| Patho-R1-3BPrompting Strategy=CoD2025.05 | 2.15 | 1.65 | 1.61 | 1.65 | 1.83 | 1.78 | 1.65 | 8.34 | 8.84 | 1.76 | 3.12 | |
| InternVL2.5-8BPrompting Strategy=CoD2025.05 | 2.05 | 1.46 | 1.43 | 1.59 | 1.6 | 1.58 | 1.46 | 8.44 | 9 | 1.55 | 3.01 | |
| Llama-3.2V-11B-cotPrompting Strategy=CoD2025.05 | 1.93 | 1.49 | 1.46 | 1.62 | 1.59 | 1.61 | 1.49 | 8.72 | 8.99 | 1.55 | 3.04 | |
| Llama-3.2V-11B-cotPrompting Strategy=CoT2025.05 | 1.66 | 1.43 | 1.42 | 1.48 | 1.49 | 1.5 | 1.43 | 8.76 | 8.98 | 1.48 | 2.96 | |
| InternVL2-8BPrompting Strategy=CoT2025.05 | 1.65 | 1.33 | 1.32 | 1.37 | 1.43 | 1.41 | 1.33 | 8.63 | 8.93 | 1.4 | 2.88 | |
| Llava-Onevision-7BPrompting Strategy=CoT2025.05 | 1.62 | 1.43 | 1.42 | 1.45 | 1.49 | 1.48 | 1.43 | 8.8 | 8.97 | 1.47 | 2.95 | |
| InternVL2-8BPrompting Strategy=CoD2025.05 | 1.58 | 1.31 | 1.3 | 1.39 | 1.36 | 1.37 | 1.31 | 8.86 | 9.01 | 1.34 | 2.87 | |
| InternVL3-8BPrompting Strategy=CoT2025.05 | 1.57 | 1.44 | 1.43 | 1.46 | 1.48 | 1.48 | 1.44 | 8.9 | 8.98 | 1.47 | 2.97 | |
| Llama-3.2-11B-Vision-InstructPrompting Strategy=CoT2025.05 | 1.43 | 1.42 | 1.42 | 1.42 | 1.42 | 1.42 | 1.41 | 9.04 | 9.04 | 1.42 | 2.94 | |
| InternVL2.5-8BPrompting Strategy=CoT2025.05 | 1.36 | 1.36 | 1.36 | 1.36 | 1.36 | 1.36 | 1.36 | 9.04 | 9.04 | 1.36 | 2.9 | |
| Llava-Onevision-7BPrompting Strategy=CoD2025.05 | 1.28 | 1.15 | 1.15 | 1.18 | 1.16 | 1.17 | 1.15 | 8.96 | 9 | 1.16 | 2.73 |