Event Sequencing on VECTOR L1 (Ne=4) 1.0 (test)
90EM ScoreHuman
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Human2025.12 | 90 | 92.5 | 92.5 | 92.5 | |
| Human2025.12 | 85 | 95 | 95 | 95 | |
| GPT-4o2025.12 | 83.33 | 85.33 | 85.5 | 85.5 | |
| Gemini 1.5 Pro2025.12 | 80.67 | 82.33 | 82.5 | 82.5 | |
| GPT-4o2025.12 | 80 | 93.25 | 94.42 | 94.5 | |
| Gemini 1.5 Pro2025.12 | 78 | 88.5 | 90.08 | 90.25 | |
| MECoTSize=7B2025.12 | 55.67 | 60.67 | 67.67 | 70.17 | |
| MECoTSize=7B2025.12 | 41.67 | 70.33 | 80.17 | 84 | |
| LV-OVSize=7B2025.12 | 40.33 | 49.17 | 53.83 | 56 | |
| NVILASize=8B2025.12 | 29 | 37.33 | 41.67 | 42.33 | |
| V-LM2Size=7B2025.12 | 24.67 | 30.33 | 36.17 | 36.33 | |
| LongVUSize=7B2025.12 | 24.33 | 31.83 | 36.33 | 36.83 | |
| LV-OVSize=7B2025.12 | 23 | 53 | 73.25 | 81.08 | |
| NVILASize=8B2025.12 | 20 | 52.5 | 71.58 | 78.5 | |
| LongVUSize=7B2025.12 | 12.67 | 51 | 67.25 | 73.08 | |
| LongVASize=7B2025.12 | 11.33 | 15.17 | 18.67 | 18.83 | |
| LongLVSize=7B2025.12 | 9.33 | 12.17 | 14.33 | 14.67 | |
| VILA-1.5Size=8B2025.12 | 4.67 | 7.33 | 9.5 | 9.5 | |
| Chance2025.12 | 2.94 | 5.56 | 8.24 | 8.33 | |
| V-LM2Size=7B2025.12 | 2.33 | 27.92 | 55.08 | 75.5 | |
| LongVASize=7B2025.12 | 1.33 | 32.92 | 54.42 | 63.25 | |
| OryxSize=7B2025.12 | 0.67 | 0.83 | 0.83 | 0.83 | |
| VILA-1.5Size=8B2025.12 | 0.33 | 9.92 | 27.67 | 32.5 | |
| Chance2025.12 | 0 | 5 | 17.18 | 20 | |
| OryxSize=7B2025.12 | 0 | 22.33 | 28.75 | 29.67 | |
| LongLVSize=7B2025.12 | 0 | 9.42 | 26.92 | 32.92 |