Pilot Task Results
This is the final results of pilot tasks.
Tort Prediction
There are 11 valid official submissions out of 14 leaderboard submissions.
Rank | Model | Team | Affiliation | Accuracy |
---|---|---|---|---|
1 | JAIST-LJPJT25 | CAPTAIN | Japan Advanced Institute of Science and Technology | 76.5% |
2 | KIS5 | KIS | Shizuoka University | 71.3% |
2 | KIS6 | KIS | Shizuoka University | 71.3% |
4 | KIS4 | KIS | Shizuoka University | 69.7% |
5 | system2 | NOWJ | VNU University of Engineering and Technology | 67.1% |
6 | modernbert | omega | freelance | 66.6% |
7 | system1 | NOWJ | VNU University of Engineering and Technology | 63.8% |
8 | system3 | NOWJ | VNU University of Engineering and Technology | 59.7% |
9 | OVGU2 | OVGU | Otto von Guericke University Magdeburg | 55.3% |
10 | OVGU3 | OVGU | Otto von Guericke University Magdeburg | 53.2% |
11 | OVGU1 | OVGU | Otto von Guericke University Magdeburg | 51.5% |
Rationale Extraction
There are 11 valid official submissions out of 15 leaderboard submissions.
Rank | Model | Team | Affiliation | F1 (All) |
---|---|---|---|---|
1 | KIS5 | KIS | Shizuoka University | 71.2% |
2 | JAIST-LJPJT25 | CAPTAIN | Japan Advanced Institute of Science and Technology | 70.6% |
3 | system2 | NOWJ | VNU University of Engineering and Technology | 69.2% |
4 | modernbert | omega | freelance | 69.1% |
5 | KIS4 | KIS | Shizuoka University | 68.2% |
6 | system1 | NOWJ | VNU University of Engineering and Technology | 68.1% |
7 | KIS6 | KIS | Shizuoka University | 67.3% |
8 | OVGU1 | OVGU | Otto von Guericke University Magdeburg | 65.7% |
9 | system3 | NOWJ | VNU University of Engineering and Technology | 55.9% |
10 | OVGU2 | OVGU | Otto von Guericke University Magdeburg | 48.6% |
11 | OVGU3 | OVGU | Otto von Guericke University Magdeburg | 31.6% |
Online Leaderboards (including unofficial submissions): https://ljpjt25.coliee.org/ (opens in a new tab)
Last updated on