{"benchmark_id":"global-mmlu-lite","name":"Global-MMLU-Lite","parent_benchmark":null,"categories":["reasoning","language","general"],"modality":"text","multilingual":true,"max_score":1.0,"language":"en","description":"A lightweight version of Global MMLU benchmark that evaluates language models across multiple languages while addressing cultural and linguistic biases in multilingual evaluation.","paper_link":"https://arxiv.org/abs/2412.03304","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:23.474704+00:00","updated_at":"2026-07-05T18:27:48.956657+00:00","statistics":{"total_models":14,"average_score":0.6963571428571428,"min_score":0.342,"max_score":0.892,"score_stddev":0.15425284295739755,"verified_count":0,"self_reported_count":14},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"gemini-2.5-pro-preview-06-05","model_name":"Gemini 2.5 Pro Preview 06-05","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.892,"normalized_score":0.892,"verified":false,"self_reported":true,"self_reported_source":"https://blog.google/products/gemini/gemini-2-5-pro-latest-preview/","analysis_method":"Multilingual performance","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-06-05","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":2,"model_id":"gemini-2.5-pro","model_name":"Gemini 2.5 Pro","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.886,"normalized_score":0.886,"verified":false,"self_reported":true,"self_reported_source":"https://deepmind.google/models/gemini/pro/","analysis_method":"Accuracy","verification_date":null,"provider_id":"google","input_cost_per_million":1.25,"output_cost_per_million":10.0,"context_window":1048576,"announcement_date":"2025-05-20","param_count":null,"is_open_source":false,"is_new":false,"best_latency":0.7,"latency_provider":"Google","best_throughput":85.0,"throughput_provider":"Google","context_provider":"Google"},{"rank":3,"model_id":"gemini-2.5-flash","model_name":"Gemini 2.5 Flash","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.884,"normalized_score":0.884,"verified":false,"self_reported":true,"self_reported_source":"https://developers.googleblog.com/en/start-building-with-gemini-25-flash/","analysis_method":"Accuracy","verification_date":null,"provider_id":"google","input_cost_per_million":0.3,"output_cost_per_million":2.5,"context_window":1048576,"announcement_date":"2025-05-20","param_count":null,"is_open_source":false,"is_new":false,"best_latency":0.7,"latency_provider":"Google","best_throughput":85.0,"throughput_provider":"Google","context_provider":"Google"},{"rank":4,"model_id":"gemini-2.5-flash-lite","model_name":"Gemini 2.5 Flash-Lite","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.811,"normalized_score":0.811,"verified":false,"self_reported":true,"self_reported_source":"https://deepmind.google/models/gemini/flash-lite/","analysis_method":"Multilingual performance","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-06-17","param_count":null,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":5,"model_id":"gemini-2.0-flash-lite","model_name":"Gemini 2.0 Flash-Lite","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.782,"normalized_score":0.782,"verified":false,"self_reported":true,"self_reported_source":"https://ai.google.dev/gemini-api/docs/models","analysis_method":"0-shot evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-02-05","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":6,"model_id":"gemma-3-27b-it","model_name":"Gemma 3 27B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.751,"normalized_score":0.751,"verified":false,"self_reported":true,"self_reported_source":"https://ai.google.dev/gemma/docs/core/model_card_3","analysis_method":"0-shot evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-03-12","param_count":27000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":7,"model_id":"gemma-3-12b-it","model_name":"Gemma 3 12B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.695,"normalized_score":0.695,"verified":false,"self_reported":true,"self_reported_source":"https://ai.google.dev/gemma/docs/core/model_card_3","analysis_method":"0-shot evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-03-12","param_count":12000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":8,"model_id":"gemini-diffusion","model_name":"Gemini Diffusion","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.691,"normalized_score":0.691,"verified":false,"self_reported":true,"self_reported_source":"https://deepmind.google/models/gemini-diffusion/","analysis_method":"pass @1","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-05-20","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":9,"model_id":"gemma-3n-e4b-it-litert-preview","model_name":"Gemma 3n E4B Instructed LiteRT Preview","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.645,"normalized_score":0.645,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/google/gemma-3n-E4B-it-litert-preview","analysis_method":"0-shot Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-05-20","param_count":1910000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":9,"model_id":"gemma-3n-e4b-it","model_name":"Gemma 3n E4B Instructed","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.645,"normalized_score":0.645,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/google/gemma-3n-E4B-it","analysis_method":"Accuracy. 0-shot.","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-06-26","param_count":8000000000,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":11,"model_id":"gemma-3n-e2b-it","model_name":"Gemma 3n E2B Instructed","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.59,"normalized_score":0.59,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/google/gemma-3n-E2B-it","analysis_method":"Accuracy. 0-shot.","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-06-26","param_count":8000000000,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":11,"model_id":"gemma-3n-e2b-it-litert-preview","model_name":"Gemma 3n E2B Instructed LiteRT (Preview)","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.59,"normalized_score":0.59,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/google/gemma-3n-E2B-it-litert-preview","analysis_method":"0-shot Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-05-20","param_count":1910000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":13,"model_id":"gemma-3-4b-it","model_name":"Gemma 3 4B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.545,"normalized_score":0.545,"verified":false,"self_reported":true,"self_reported_source":"https://ai.google.dev/gemma/docs/core/model_card_3","analysis_method":"0-shot evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-03-12","param_count":4000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":14,"model_id":"gemma-3-1b-it","model_name":"Gemma 3 1B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.342,"normalized_score":0.342,"verified":false,"self_reported":true,"self_reported_source":"https://ai.google.dev/gemma/docs/core/model_card_3","analysis_method":"0-shot evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-03-12","param_count":1000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}