# Multilingual Knowledge Evaluation on Global-MMLU High Source: [Multilingual Knowledge Evaluation on Global-MMLU High]() Collection index: [llms.txt]() Data updated: 2026-06-08T06:32:02.827Z Evaluation of model performance on the Global-MMLU High dataset, assessing multilingual knowledge capabilities. 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 | Multilingual knowledge evaluation | | Dataset (including any stated split) | Global-MMLU High | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 | | --- | --- | --- | --- | | GRPO | 68.35 | Not recorded | 6a264c8590966ade919be956 | | Baseline | 68.15 | Not recorded | 6a264c8590966ade919be956 | | CPT + GRPO | 65.2 | Not recorded | 6a264c8590966ade919be956 | | SFT | 64.45 | Not recorded | 6a264c8590966ade919be956 | | CPT + SFT | 64.2 | Not recorded | 6a264c8590966ade919be956 | | CPT | 63.95 | Not recorded | 6a264c8590966ade919be956 | | GRPO | 39.22 | Not recorded | 6a264c8590966ade919be956 | | Baseline | 38.72 | Not recorded | 6a264c8590966ade919be956 | | CPT | 37.41 | Not recorded | 6a264c8590966ade919be956 | | CPT + GRPO | 36.34 | Not recorded | 6a264c8590966ade919be956 | | CPT + SFT | 36.15 | Not recorded | 6a264c8590966ade919be956 | | SFT | 35.4 | Not recorded | 6a264c8590966ade919be956 | ### GRPO Accuracy: 68.35. Result ID: 6a266179fbc373592c226c66. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-2.5-7B"}. This record does not assert independent reproduction. ### Baseline Accuracy: 68.15. Result ID: 6a266179fbc373592c226c62. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen-2.5-7B"}. This record does not assert independent reproduction. ### CPT + GRPO Accuracy: 65.2. Result ID: 6a266179fbc373592c226c67. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-2.5-7B"}. This record does not assert independent reproduction. ### SFT Accuracy: 64.45. Result ID: 6a266179fbc373592c226c64. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen-2.5-7B"}. This record does not assert independent reproduction. ### CPT + SFT Accuracy: 64.2. Result ID: 6a266179fbc373592c226c65. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen-2.5-7B"}. This record does not assert independent reproduction. ### CPT Accuracy: 63.95. Result ID: 6a266179fbc373592c226c63. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen-2.5-7B"}. This record does not assert independent reproduction. ### GRPO Accuracy: 39.22. Result ID: 6a266179fbc373592c226c60. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"OLMo-2-1124-7B"}. This record does not assert independent reproduction. ### Baseline Accuracy: 38.72. Result ID: 6a266179fbc373592c226c5c. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"OLMo-2-1124-7B"}. This record does not assert independent reproduction. ### CPT Accuracy: 37.41. Result ID: 6a266179fbc373592c226c5d. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"OLMo-2-1124-7B"}. This record does not assert independent reproduction. ### CPT + GRPO Accuracy: 36.34. Result ID: 6a266179fbc373592c226c61. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"OLMo-2-1124-7B"}. This record does not assert independent reproduction. ### CPT + SFT Accuracy: 36.15. Result ID: 6a266179fbc373592c226c5f. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"OLMo-2-1124-7B"}. This record does not assert independent reproduction. ### SFT Accuracy: 35.4. Result ID: 6a266179fbc373592c226c5e. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"OLMo-2-1124-7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.