Multiple-Choice Question Answering on LongQA MC
85.07Exact Match (EM)GPT-4.1
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4.1Memory=CoA, Ordering Strategy=CL-ORDER2026.03 | 85.07 | |
| GPT-4.1Memory=CoA, Ordering Strategy=DENSE2026.03 | 84.33 | |
| GPT-4.1Memory=CoA, Ordering Strategy=DEFAULT2026.03 | 82.84 | |
| GPT-4.1-MINIMemory=CoA, Ordering Strategy=CL-ORDER2026.03 | 70.29 | |
| GPT-4.1-MINIMemory=CoA, Ordering Strategy=DENSE2026.03 | 67.39 | |
| GPT-4.1-MINIMemory=CoA, Ordering Strategy=DEFAULT2026.03 | 65.22 | |
| QWEN-3-14BMemory=CoA, Ordering Strategy=CL-ORDER2026.03 | 30.26 | |
| QWEN-3-14BMemory=CoA, Ordering Strategy=DENSE2026.03 | 26.2 | |
| QWEN-3-14BMemory=CoA, Ordering Strategy=DEFAULT2026.03 | 24.89 |