# Comprehensive Examination on GAOKAO (test) Source: [Comprehensive Examination on GAOKAO (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:29:33.819Z Evaluation of model performance on the Comprehensive Examination task using the test split of the GAOKAO dataset, 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 | Comprehensive Examination | | Dataset (including any stated split) | GAOKAO (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 27 of 27 | | 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 | | --- | --- | --- | --- | | Qwen-14B-Chat | 76.3 | Not recorded | 68fa72b31e209131cea57feb | | Qwen-14B | 62.5 | Not recorded | 68fa72b31e209131cea57feb | | Qwen-7B-Chat | 62.1 | Not recorded | 68fa72b31e209131cea57feb | | ChatGLM3-6B-Base | 59.4 | Not recorded | 68fa72b31e209131cea57feb | | InternLM2-Chat-20B-SFT | 58.6 | Not recorded | 68fa72b31e209131cea57feb | | InternLM2-7B | 58.6 | Not recorded | 68fa72b31e209131cea57feb | | InternLM2-Chat-20B | 58.3 | Not recorded | 68fa72b31e209131cea57feb | | InternLM2-Chat-7B | 58 | Not recorded | 68fa72b31e209131cea57feb | | InternLM2-Chat-7B-SFT | 57.3 | Not recorded | 68fa72b31e209131cea57feb | | InternLM2-20B | 57.1 | Not recorded | 68fa72b31e209131cea57feb | | ChatGLM3-6B | 56.3 | Not recorded | 68fa72b31e209131cea57feb | | Qwen-7B | 52.8 | Not recorded | 68fa72b31e209131cea57feb | | GPT-3.5 | 51.1 | Not recorded | 68fa72b31e209131cea57feb | | Baichuan2-13B-Chat | 45.8 | Not recorded | 68fa72b31e209131cea57feb | | Baichuan2-13B-Base | 45.6 | Not recorded | 68fa72b31e209131cea57feb | | Mixtral-8x7B-Instruct-v0.1 | 42.6 | Not recorded | 68fa72b31e209131cea57feb | | InternLM2-7B-Base | 40.7 | Not recorded | 68fa72b31e209131cea57feb | | InternLM2-20B-Base | 40.7 | Not recorded | 68fa72b31e209131cea57feb | | Baichuan2-7B-Chat | 37.5 | Not recorded | 68fa72b31e209131cea57feb | | Baichuan2-7B-Base | 34.7 | Not recorded | 68fa72b31e209131cea57feb | | Mixtral-8x7B-v0.1 | 32.3 | Not recorded | 68fa72b31e209131cea57feb | | Mistral-7B-v0.1 | 28.7 | Not recorded | 68fa72b31e209131cea57feb | | Mistral-7B-Instruct-v0.2 | 28.6 | Not recorded | 68fa72b31e209131cea57feb | | Llama2-13B-Chat | 23.2 | Not recorded | 68fa72b31e209131cea57feb | | Llama2-7B-Chat | 19.8 | Not recorded | 68fa72b31e209131cea57feb | | Llama2-7B | 19 | Not recorded | 68fa72b31e209131cea57feb | | Llama2-13B | 18.4 | Not recorded | 68fa72b31e209131cea57feb | ### Qwen-14B-Chat Accuracy: 76.3. Result ID: 69926f7f3a6c3148490eeb47. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameter size group":"13~20B Models","Evaluation protocol":"0-shot"}. This record does not assert independent reproduction. ### Qwen-14B Accuracy: 62.5. Result ID: 69926f7f3a6c3148490eece5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Shots":"0-shot","Model Size Group":"13 ~ 20B Models"}. This record does not assert independent reproduction. ### Qwen-7B-Chat Accuracy: 62.1. Result ID: 69926f7f3a6c3148490eeb41. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameter size group":"\< 7B Models","Evaluation protocol":"0-shot"}. This record does not assert independent reproduction. ### ChatGLM3-6B-Base Accuracy: 59.4. Result ID: 69926f7f3a6c3148490eecde. [Reporting paper]() Recorded evaluation configuration: {"Shots":"0-shot","Model Size Group":"\<= 7B Models"}. This record does not assert independent reproduction. ### InternLM2-Chat-20B-SFT Accuracy: 58.6. Result ID: 69926f7f3a6c3148490eeb48. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameter size group":"13~20B Models","Evaluation protocol":"0-shot","Alignment":"SFT"}. This record does not assert independent reproduction. ### InternLM2-7B Accuracy: 58.6. Result ID: 69926f7f3a6c3148490eece1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Shots":"0-shot","Model Size Group":"\<= 7B Models"}. This record does not assert independent reproduction. ### InternLM2-Chat-20B Accuracy: 58.3. Result ID: 69926f7f3a6c3148490eeb49. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameter size group":"13~20B Models","Evaluation protocol":"0-shot"}. This record does not assert independent reproduction. ### InternLM2-Chat-7B Accuracy: 58. Result ID: 69926f7f3a6c3148490eeb43. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameter size group":"\< 7B Models","Evaluation protocol":"0-shot"}. This record does not assert independent reproduction. ### InternLM2-Chat-7B-SFT Accuracy: 57.3. Result ID: 69926f7f3a6c3148490eeb42. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameter size group":"\< 7B Models","Evaluation protocol":"0-shot","Alignment":"SFT"}. This record does not assert independent reproduction. ### InternLM2-20B Accuracy: 57.1. Result ID: 69926f7f3a6c3148490eece7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Shots":"0-shot","Model Size Group":"13 ~ 20B Models"}. This record does not assert independent reproduction. ### ChatGLM3-6B Accuracy: 56.3. Result ID: 69926f7f3a6c3148490eeb40. [Reporting paper]() Recorded evaluation configuration: {"Parameter size group":"\< 7B Models","Evaluation protocol":"0-shot"}. This record does not assert independent reproduction. ### Qwen-7B Accuracy: 52.8. Result ID: 69926f7f3a6c3148490eecdf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Shots":"0-shot","Model Size Group":"\<= 7B Models"}. This record does not assert independent reproduction. ### GPT-3.5 Accuracy: 51.1. Result ID: 69926f7f3a6c3148490eeb3c. [Reporting paper]() Recorded evaluation configuration: {"Model type":"API Models","Evaluation protocol":"0-shot"}. This record does not assert independent reproduction. ### Baichuan2-13B-Chat Accuracy: 45.8. Result ID: 69926f7f3a6c3148490eeb46. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameter size group":"13~20B Models","Evaluation protocol":"0-shot"}. This record does not assert independent reproduction. ### Baichuan2-13B-Base Accuracy: 45.6. Result ID: 69926f7f3a6c3148490eece4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Shots":"0-shot","Model Size Group":"13 ~ 20B Models"}. This record does not assert independent reproduction. ### Mixtral-8x7B-Instruct-v0.1 Accuracy: 42.6. Result ID: 69926f7f3a6c3148490eeb45. [Reporting paper]() Recorded evaluation configuration: {"Parameter size group":"13~20B Models","Evaluation protocol":"0-shot","Alignment":"Instruct"}. This record does not assert independent reproduction. ### InternLM2-7B-Base Accuracy: 40.7. Result ID: 69926f7f3a6c3148490eece0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Shots":"0-shot","Model Size Group":"\<= 7B Models"}. This record does not assert independent reproduction. ### InternLM2-20B-Base Accuracy: 40.7. Result ID: 69926f7f3a6c3148490eece6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Shots":"0-shot","Model Size Group":"13 ~ 20B Models"}. This record does not assert independent reproduction. ### Baichuan2-7B-Chat Accuracy: 37.5. Result ID: 69926f7f3a6c3148490eeb3f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameter size group":"\< 7B Models","Evaluation protocol":"0-shot"}. This record does not assert independent reproduction. ### Baichuan2-7B-Base Accuracy: 34.7. Result ID: 69926f7f3a6c3148490eecdd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Shots":"0-shot","Model Size Group":"\<= 7B Models"}. This record does not assert independent reproduction. ### Mixtral-8x7B-v0.1 Accuracy: 32.3. Result ID: 69926f7f3a6c3148490eece3. [Reporting paper]() Recorded evaluation configuration: {"Shots":"0-shot","Model Size Group":"13 ~ 20B Models"}. This record does not assert independent reproduction. ### Mistral-7B-v0.1 Accuracy: 28.7. Result ID: 69926f7f3a6c3148490eecdc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Shots":"0-shot","Model Size Group":"\<= 7B Models"}. This record does not assert independent reproduction. ### Mistral-7B-Instruct-v0.2 Accuracy: 28.6. Result ID: 69926f7f3a6c3148490eeb3e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameter size group":"\< 7B Models","Evaluation protocol":"0-shot","Alignment":"Instruct"}. This record does not assert independent reproduction. ### Llama2-13B-Chat Accuracy: 23.2. Result ID: 69926f7f3a6c3148490eeb44. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameter size group":"13~20B Models","Evaluation protocol":"0-shot"}. This record does not assert independent reproduction. ### Llama2-7B-Chat Accuracy: 19.8. Result ID: 69926f7f3a6c3148490eeb3d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameter size group":"\< 7B Models","Evaluation protocol":"0-shot"}. This record does not assert independent reproduction. ### Llama2-7B Accuracy: 19. Result ID: 69926f7f3a6c3148490eecdb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Shots":"0-shot","Model Size Group":"\<= 7B Models"}. This record does not assert independent reproduction. ### Llama2-13B Accuracy: 18.4. Result ID: 69926f7f3a6c3148490eece2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Shots":"0-shot","Model Size Group":"13 ~ 20B Models"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.