# Medical Knowledge Evaluation on MMedbench English subset (val) Source: [Medical Knowledge Evaluation on MMedbench English subset (val)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:29:59.761Z Evaluation of model performance on the English subset (validation split) of the MMedbench dataset for assessing medical knowledge, typically measured by accuracy. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Medical Knowledge Evaluation | | Dataset (including any stated split) | MMedbench English subset (val) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 36 of 36 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | LLaMA3-8B | 60.33 | Not recorded | 68fa75401e209131cea66d49 | | TAIA | 60.02 | Not recorded | 68fa75401e209131cea66d49 | | TAIA | 59.07 | Not recorded | 68fa75401e209131cea66d49 | | TAIA | 58.68 | Not recorded | 68fa75401e209131cea66d49 | | TAIA | 58.68 | Not recorded | 68fa75401e209131cea66d49 | | MOLORA | 58.44 | Not recorded | 68fa75401e209131cea66d49 | | MOLORA | 57.97 | Not recorded | 68fa75401e209131cea66d49 | | LoRA | 57.5 | Not recorded | 68fa75401e209131cea66d49 | | LoRA | 55.3 | Not recorded | 68fa75401e209131cea66d49 | | TAIA | 46.9 | Not recorded | 68fa75401e209131cea66d49 | | TAIA | 46.74 | Not recorded | 68fa75401e209131cea66d49 | | TAIA | 46.58 | Not recorded | 68fa75401e209131cea66d49 | | TAIA | 46.03 | Not recorded | 68fa75401e209131cea66d49 | | MOLORA | 45.56 | Not recorded | 68fa75401e209131cea66d49 | | Qwen1.5-7B | 45.09 | Not recorded | 68fa75401e209131cea66d49 | | LoRA | 44.85 | Not recorded | 68fa75401e209131cea66d49 | | LoRA | 38.73 | Not recorded | 68fa75401e209131cea66d49 | | TAIA | 38.33 | Not recorded | 68fa75401e209131cea66d49 | | TAIA | 38.1 | Not recorded | 68fa75401e209131cea66d49 | | LoRA | 38.02 | Not recorded | 68fa75401e209131cea66d49 | | MOLORA | 37.86 | Not recorded | 68fa75401e209131cea66d49 | | TAIA | 37.55 | Not recorded | 68fa75401e209131cea66d49 | | MOLORA | 37.23 | Not recorded | 68fa75401e209131cea66d49 | | TAIA | 36.68 | Not recorded | 68fa75401e209131cea66d49 | | TAIA | 36.53 | Not recorded | 68fa75401e209131cea66d49 | | TAIA | 34.64 | Not recorded | 68fa75401e209131cea66d49 | | MOLORA | 34.33 | Not recorded | 68fa75401e209131cea66d49 | | TAIA | 34.33 | Not recorded | 68fa75401e209131cea66d49 | | Qwen1.5-1.8B | 33.78 | Not recorded | 68fa75401e209131cea66d49 | | LLaMA2-7B | 32.21 | Not recorded | 68fa75401e209131cea66d49 | | TAIA | 29.9 | Not recorded | 68fa75401e209131cea66d49 | | LoRA | 27.65 | Not recorded | 68fa75401e209131cea66d49 | | MOLORA | 27.57 | Not recorded | 68fa75401e209131cea66d49 | | LoRA | 27.49 | Not recorded | 68fa75401e209131cea66d49 | | MOLORA | 27.42 | Not recorded | 68fa75401e209131cea66d49 | | LoRA | 22.1 | Not recorded | 68fa75401e209131cea66d49 | ### LLaMA3-8B Accuracy: 60.33. Result ID: 6993978c3a6c314849171984. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"Base Model","Model":"LLaMA3-8B"}. This record does not assert independent reproduction. ### TAIA Accuracy: 60.02. Result ID: 6993978c3a6c3148491719a4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"CoT-Collection","Model":"LLaMA3-8B","FT Method":"MOLORA","Infer Mode":"TAIA"}. This record does not assert independent reproduction. ### TAIA Accuracy: 59.07. Result ID: 6993978c3a6c314849171994. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"Alpaca-GPT4","Model":"LLaMA3-8B","FT Method":"MOLORA","Infer Mode":"TAIA"}. This record does not assert independent reproduction. ### TAIA Accuracy: 58.68. Result ID: 6993978c3a6c314849171992. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"Alpaca-GPT4","Model":"LLaMA3-8B","FT Method":"LoRA","Infer Mode":"TAIA"}. This record does not assert independent reproduction. ### TAIA Accuracy: 58.68. Result ID: 6993978c3a6c3148491719a2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"CoT-Collection","Model":"LLaMA3-8B","FT Method":"LoRA","Infer Mode":"TAIA"}. This record does not assert independent reproduction. ### MOLORA Accuracy: 58.44. Result ID: 6993978c3a6c3148491719a3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Dataset":"CoT-Collection","Model":"LLaMA3-8B","FT Method":"MOLORA","Infer Mode":"Vanilla"}. This record does not assert independent reproduction. ### MOLORA Accuracy: 57.97. Result ID: 6993978c3a6c314849171993. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Dataset":"Alpaca-GPT4","Model":"LLaMA3-8B","FT Method":"MOLORA","Infer Mode":"Vanilla"}. This record does not assert independent reproduction. ### LoRA Accuracy: 57.5. Result ID: 6993978c3a6c314849171991. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"Alpaca-GPT4","Model":"LLaMA3-8B","FT Method":"LoRA","Infer Mode":"Vanilla"}. This record does not assert independent reproduction. ### LoRA Accuracy: 55.3. Result ID: 6993978c3a6c3148491719a1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"CoT-Collection","Model":"LLaMA3-8B","FT Method":"LoRA","Infer Mode":"Vanilla"}. This record does not assert independent reproduction. ### TAIA Accuracy: 46.9. Result ID: 6993978c3a6c31484917198a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"Alpaca-GPT4","Model":"Qwen1.5-7B","FT Method":"LoRA","Infer Mode":"TAIA"}. This record does not assert independent reproduction. ### TAIA Accuracy: 46.74. Result ID: 6993978c3a6c31484917199a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"CoT-Collection","Model":"Qwen1.5-7B","FT Method":"LoRA","Infer Mode":"TAIA"}. This record does not assert independent reproduction. ### TAIA Accuracy: 46.58. Result ID: 6993978c3a6c31484917198c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"Alpaca-GPT4","Model":"Qwen1.5-7B","FT Method":"MOLORA","Infer Mode":"TAIA"}. This record does not assert independent reproduction. ### TAIA Accuracy: 46.03. Result ID: 6993978c3a6c31484917199c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"CoT-Collection","Model":"Qwen1.5-7B","FT Method":"MOLORA","Infer Mode":"TAIA"}. This record does not assert independent reproduction. ### MOLORA Accuracy: 45.56. Result ID: 6993978c3a6c31484917198b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Dataset":"Alpaca-GPT4","Model":"Qwen1.5-7B","FT Method":"MOLORA","Infer Mode":"Vanilla"}. This record does not assert independent reproduction. ### Qwen1.5-7B Accuracy: 45.09. Result ID: 6993978c3a6c314849171982. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Dataset":"Base Model","Model":"Qwen1.5-7B"}. This record does not assert independent reproduction. ### LoRA Accuracy: 44.85. Result ID: 6993978c3a6c314849171989. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"Alpaca-GPT4","Model":"Qwen1.5-7B","FT Method":"LoRA","Infer Mode":"Vanilla"}. This record does not assert independent reproduction. ### LoRA Accuracy: 38.73. Result ID: 6993978c3a6c31484917199d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"CoT-Collection","Model":"LLaMA2-7B","FT Method":"LoRA","Infer Mode":"Vanilla"}. This record does not assert independent reproduction. ### TAIA Accuracy: 38.33. Result ID: 6993978c3a6c31484917199e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"CoT-Collection","Model":"LLaMA2-7B","FT Method":"LoRA","Infer Mode":"TAIA"}. This record does not assert independent reproduction. ### TAIA Accuracy: 38.1. Result ID: 6993978c3a6c31484917198e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"Alpaca-GPT4","Model":"LLaMA2-7B","FT Method":"LoRA","Infer Mode":"TAIA"}. This record does not assert independent reproduction. ### LoRA Accuracy: 38.02. Result ID: 6993978c3a6c31484917198d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"Alpaca-GPT4","Model":"LLaMA2-7B","FT Method":"LoRA","Infer Mode":"Vanilla"}. This record does not assert independent reproduction. ### MOLORA Accuracy: 37.86. Result ID: 6993978c3a6c31484917199f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Dataset":"CoT-Collection","Model":"LLaMA2-7B","FT Method":"MOLORA","Infer Mode":"Vanilla"}. This record does not assert independent reproduction. ### TAIA Accuracy: 37.55. Result ID: 6993978c3a6c3148491719a0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"CoT-Collection","Model":"LLaMA2-7B","FT Method":"MOLORA","Infer Mode":"TAIA"}. This record does not assert independent reproduction. ### MOLORA Accuracy: 37.23. Result ID: 6993978c3a6c31484917198f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Dataset":"Alpaca-GPT4","Model":"LLaMA2-7B","FT Method":"MOLORA","Infer Mode":"Vanilla"}. This record does not assert independent reproduction. ### TAIA Accuracy: 36.68. Result ID: 6993978c3a6c314849171998. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"CoT-Collection","Model":"Qwen1.5-1.8B","FT Method":"MOLORA","Infer Mode":"TAIA"}. This record does not assert independent reproduction. ### TAIA Accuracy: 36.53. Result ID: 6993978c3a6c314849171990. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"Alpaca-GPT4","Model":"LLaMA2-7B","FT Method":"MOLORA","Infer Mode":"TAIA"}. This record does not assert independent reproduction. ### TAIA Accuracy: 34.64. Result ID: 6993978c3a6c314849171996. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"CoT-Collection","Model":"Qwen1.5-1.8B","FT Method":"LoRA","Infer Mode":"TAIA"}. This record does not assert independent reproduction. ### MOLORA Accuracy: 34.33. Result ID: 6993978c3a6c314849171987. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Dataset":"Alpaca-GPT4","Model":"Qwen1.5-1.8B","FT Method":"MOLORA","Infer Mode":"Vanilla"}. This record does not assert independent reproduction. ### TAIA Accuracy: 34.33. Result ID: 6993978c3a6c314849171988. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"Alpaca-GPT4","Model":"Qwen1.5-1.8B","FT Method":"MOLORA","Infer Mode":"TAIA"}. This record does not assert independent reproduction. ### Qwen1.5-1.8B Accuracy: 33.78. Result ID: 6993978c3a6c314849171981. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Dataset":"Base Model","Model":"Qwen1.5-1.8B"}. This record does not assert independent reproduction. ### LLaMA2-7B Accuracy: 32.21. Result ID: 6993978c3a6c314849171983. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"Base Model","Model":"LLaMA2-7B"}. This record does not assert independent reproduction. ### TAIA Accuracy: 29.9. Result ID: 6993978c3a6c314849171986. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"Alpaca-GPT4","Model":"Qwen1.5-1.8B","FT Method":"LoRA","Infer Mode":"TAIA"}. This record does not assert independent reproduction. ### LoRA Accuracy: 27.65. Result ID: 6993978c3a6c314849171995. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"CoT-Collection","Model":"Qwen1.5-1.8B","FT Method":"LoRA","Infer Mode":"Vanilla"}. This record does not assert independent reproduction. ### MOLORA Accuracy: 27.57. Result ID: 6993978c3a6c31484917199b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Dataset":"CoT-Collection","Model":"Qwen1.5-7B","FT Method":"MOLORA","Infer Mode":"Vanilla"}. This record does not assert independent reproduction. ### LoRA Accuracy: 27.49. Result ID: 6993978c3a6c314849171999. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"CoT-Collection","Model":"Qwen1.5-7B","FT Method":"LoRA","Infer Mode":"Vanilla"}. This record does not assert independent reproduction. ### MOLORA Accuracy: 27.42. Result ID: 6993978c3a6c314849171997. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Dataset":"CoT-Collection","Model":"Qwen1.5-1.8B","FT Method":"MOLORA","Infer Mode":"Vanilla"}. This record does not assert independent reproduction. ### LoRA Accuracy: 22.1. Result ID: 6993978c3a6c314849171985. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"Alpaca-GPT4","Model":"Qwen1.5-1.8B","FT Method":"LoRA","Infer Mode":"Vanilla"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.