Cross-distribution performance on SAIR (hard2)
99Accuracy98_hard200
Evaluation Results
| Method | Links | |
|---|---|---|
| 98_hard200Participant=Betka2026.04 | 99 | |
| hard98_derivate_2Participant=Pandey2026.04 | 97 | |
| traditional_mlParticipant=Reza Jamei2026.04 | 89 | |
| combo_jackParticipant=Reza Jamei2026.04 | 86 | |
| bank_lookup_v8Participant=Arjun Garg2026.04 | 83 | |
| distilled-r-12Participant=Heath2026.04 | 80 | |
| Test 8Participant=Debtirtha Saha2026.04 | 60 | |
| Stage 1 PromptParticipant=SimonRJ2026.04 | 58 | |
| bank_lookup_v5Participant=Garg2026.04 | 51.5 | |
| hard3_overfittedParticipant=Woon Siang Yi2026.04 | 51 | |
| chat_v32Participant=Devanshu Dixit2026.04 | 49.5 | |
| AN45cParticipant=Cazares2026.04 | 48 | |
| AN38Participant=Cazares2026.04 | 41 |