Medical Question Answering on MedConceptsQA
94.27AccuracyGPT-4
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| GPT-4Category=Original, Approach=None, Teacher=None, TA=None, Student=GPT-42025.12 | 94.27 | — | 84.32 | |
| BRIDGECategory=Blackbox, Teacher=GPT-4, TA=None, Student=Qwen2.5-7B-Instr.2025.12 | 86.12 | — | 74.22 | |
| Qwen2.5-7B-Instr.Category=Original, Approach=None, Teacher=None, TA=None, Student=Qwen2.5-7B-Instr.2025.12 | 58 | — | 55.1 | |
| BRIDGECategory=Blackbox, Teacher=GPT-4, TA=None, Student=Mistral-7B-Instr.-v0.32025.12 | 56.66 | — | 57.94 | |
| Mistral-7B-Instr.-v0.3Category=Original, Approach=None, Teacher=None, TA=None, Student=Mistral-7B-Instr.-v0.32025.12 | 36.4 | — | 42.32 | |
| BRIDGECategory=Blackbox, Teacher=GPT-4, TA=Qwen2.5-7B-Instr., Student=Pythia-410M2025.12 | 35.6 | — | 33.1 | |
| BRIDGECategory=Blackbox, Teacher=GPT-4, TA=Qwen2.5-7B-Instr., Student=OPT-350M2025.12 | 33.2 | — | 33.82 | |
| BRIDGECategory=Blackbox, Teacher=GPT-4, TA=Qwen2.5-7B-Instr., Student=Bloomz-560M2025.12 | 31.2 | — | 32.66 | |
| BRIDGECategory=Blackbox, Teacher=GPT-4, TA=Mistral-7B-Instr.-v0.3, Student=Bloomz-560M2025.12 | 31.2 | — | 31.64 | |
| BRIDGECategory=Blackbox, Teacher=GPT-4, TA=Mistral-7B-Instr.-v0.3, Student=Pythia-410M2025.12 | 31.2 | — | 33.97 | |
| BRIDGECategory=Blackbox, Teacher=GPT-4, TA=Mistral-7B-Instr.-v0.3, Student=OPT-350M2025.12 | 30.8 | — | 31.14 | |
| BLKDCategory=Blackbox, Teacher=GPT-4, TA=None, Student=Pythia-410M2025.12 | 28 | — | 26.42 | |
| BLKDCategory=Blackbox, Teacher=GPT-4, TA=None, Student=Bloomz-560M2025.12 | 27 | — | 27.87 | |
| ULDCategory=Whitebox, Teacher=None, TA=Qwen2.5-7B-Instr., Student=Pythia-410M2025.12 | 26.5 | — | 27.98 | |
| BLKDCategory=Blackbox, Teacher=GPT-4, TA=None, Student=OPT-350M2025.12 | 26.2 | — | 26.77 | |
| ULDCategory=Whitebox, Teacher=None, TA=Qwen2.5-7B-Instr., Student=Bloomz-560M2025.12 | 25.8 | — | 24.74 | |
| Pythia-410MCategory=Original, Approach=None, Teacher=None, TA=None, Student=Pythia-410M2025.12 | 25.43 | — | 26.89 | |
| ULDCategory=Whitebox, Teacher=None, TA=Mistral-7B-Instr.-v0.3, Student=Pythia-410M2025.12 | 25.4 | — | 27.26 | |
| LionCategory=Blackbox, Teacher=GPT-4, TA=None, Student=Bloomz-560M2025.12 | 25 | — | 24.2 | |
| ULDCategory=Whitebox, Teacher=None, TA=Qwen2.5-7B-Instr., Student=OPT-350M2025.12 | 24.9 | — | 24.75 | |
| Bloomz-560MCategory=Original, Approach=None, Teacher=None, TA=None, Student=Bloomz-560M2025.12 | 24.6 | — | 24.16 | |
| ULDCategory=Whitebox, Teacher=None, TA=Mistral-7B-Instr.-v0.3, Student=OPT-350M2025.12 | 24 | — | 24.9 | |
| OPT-350MCategory=Original, Approach=None, Teacher=None, TA=None, Student=OPT-350M2025.12 | 23.9 | — | 23.88 | |
| ULDCategory=Whitebox, Teacher=None, TA=Mistral-7B-Instr.-v0.3, Student=Bloomz-560M2025.12 | 23.5 | — | 24.8 | |
| LionCategory=Blackbox, Teacher=GPT-4, TA=None, Student=Pythia-410M2025.12 | 20.6 | — | 20.77 | |
| LionCategory=Blackbox, Teacher=GPT-4, TA=None, Student=OPT-350M2025.12 | 19.4 | — | 21.1 |