Score Prediction on Eval-Actions 1.0 (test)
0.84SRCCAutoEval-S
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| AutoEval-SEvaluation Protocol=Rank-Guided (RG)2026.01 | 0.84 | 3.49 | |
| QwenVL3-4BEvaluation Protocol=Rank-Guided (RG)2026.01 | 0.82 | 4.55 | |
| InternVL3.5-4BEvaluation Protocol=Rank-Guided (RG)2026.01 | 0.81 | 4.93 | |
| AutoEval-SEvaluation Protocol=Expert Grading (EG)2026.01 | 0.81 | 3.45 | |
| InternVL3.5-4BEvaluation Protocol=Expert Grading (EG)2026.01 | 0.8 | 3.84 | |
| QwenVL3-4BEvaluation Protocol=Expert Grading (EG)2026.01 | 0.78 | 4.69 | |
| AutoEval-PEvaluation Protocol=Chain-of-Thought (CoT)2026.01 | 0.7 | 4.45 | |
| QwenVL2.5-3BEvaluation Protocol=Rank-Guided (RG)2026.01 | 0.64 | 10.21 | |
| QwenVL3-4BEvaluation Protocol=Chain-of-Thought (CoT)2026.01 | 0.64 | 5.68 | |
| InternVL3.5-4BEvaluation Protocol=Chain-of-Thought (CoT)2026.01 | 0.63 | 5.68 | |
| QwenVL2.5-3BEvaluation Protocol=Expert Grading (EG)2026.01 | 0.62 | 7.91 | |
| QwenVL2.5-3BEvaluation Protocol=Chain-of-Thought (CoT)2026.01 | 0.46 | 9.25 | |
| SmolVLM2.2BEvaluation Protocol=Expert Grading (EG)2026.01 | 0.41 | 9.7 | |
| SmolVLM2.2BEvaluation Protocol=Rank-Guided (RG)2026.01 | 0.39 | 10.57 | |
| SmolVLM2.2BEvaluation Protocol=Chain-of-Thought (CoT)2026.01 | 0.31 | 12.17 | |
| InternVL3.5-4BEvaluation Protocol=Rank-Guided (RG), Supervised Fine-Tuning=No (Zero-Shot)2026.01 | 0.02 | 27.97 | |
| InternVL3.5-4BEvaluation Protocol=Expert Grading (EG), Supervised Fine-Tuning=No (Zero-Shot)2026.01 | 0.01 | 31.9 |