{"benchmark_id":"facts-grounding","benchmark_name":"FACTS Grounding","benchmark_description":"A benchmark evaluating language models' ability to generate factually accurate and well-grounded responses based on long-form input context, comprising 1,719 examples with documents up to 32k tokens requiring detailed responses that are fully grounded in provided documents","max_score":1.0,"categories":["reasoning","factuality","grounding"],"modality":"text","total_models":13,"entries":[{"rank":1,"model_id":"gemini-2.5-pro-preview-06-05","model_name":"Gemini 2.5 Pro Preview 06-05","organization_name":"Google","organization_id":"google","benchmark_score":0.878,"normalized_score":0.878,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2025-06-05","announcement_date":"2025-06-05","multimodal":true,"param_count":null,"is_new":false},{"rank":2,"model_id":"gemini-2.5-flash","model_name":"Gemini 2.5 Flash","organization_name":"Google","organization_id":"google","benchmark_score":0.853,"normalized_score":0.853,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2025-05-20","announcement_date":"2025-05-20","multimodal":true,"param_count":null,"is_new":false},{"rank":3,"model_id":"gemini-2.5-flash-lite","model_name":"Gemini 2.5 Flash-Lite","organization_name":"Google","organization_id":"google","benchmark_score":0.841,"normalized_score":0.841,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2025-06-17","announcement_date":"2025-06-17","multimodal":true,"param_count":null,"is_new":false},{"rank":4,"model_id":"gemini-2.0-flash-lite","model_name":"Gemini 2.0 Flash-Lite","organization_name":"Google","organization_id":"google","benchmark_score":0.836,"normalized_score":0.836,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2025-02-05","announcement_date":"2025-02-05","multimodal":true,"param_count":null,"is_new":false},{"rank":5,"model_id":"gemini-2.0-flash","model_name":"Gemini 2.0 Flash","organization_name":"Google","organization_id":"google","benchmark_score":0.836,"normalized_score":0.836,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2024-12-01","announcement_date":"2024-12-01","multimodal":true,"param_count":null,"is_new":false},{"rank":6,"model_id":"gemma-3-12b-it","model_name":"Gemma 3 12B","organization_name":"Google","organization_id":"google","benchmark_score":0.758,"normalized_score":0.758,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2025-03-12","announcement_date":"2025-03-12","multimodal":true,"param_count":12000000000,"is_new":false},{"rank":7,"model_id":"gemma-3-27b-it","model_name":"Gemma 3 27B","organization_name":"Google","organization_id":"google","benchmark_score":0.749,"normalized_score":0.749,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2025-03-12","announcement_date":"2025-03-12","multimodal":true,"param_count":27000000000,"is_new":false},{"rank":8,"model_id":"gemini-3-pro-preview","model_name":"Gemini 3 Pro","organization_name":"Google","organization_id":"google","benchmark_score":0.705,"normalized_score":0.705,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2025-11-18","announcement_date":"2025-11-18","multimodal":true,"param_count":null,"is_new":false},{"rank":9,"model_id":"gemma-3-4b-it","model_name":"Gemma 3 4B","organization_name":"Google","organization_id":"google","benchmark_score":0.701,"normalized_score":0.701,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2025-03-12","announcement_date":"2025-03-12","multimodal":true,"param_count":4000000000,"is_new":false},{"rank":10,"model_id":"gemini-3-flash-preview","model_name":"Gemini 3 Flash","organization_name":"Google","organization_id":"google","benchmark_score":0.619,"normalized_score":0.619,"verified":false,"self_reported":true,"provider_id":"google","input_cost_per_million":0.5,"output_cost_per_million":3.0,"speed_rps":null,"context_window":1000000,"release_date":"2025-12-17","announcement_date":"2025-12-17","multimodal":true,"param_count":null,"is_new":false},{"rank":11,"model_id":"glm-5v-turbo","model_name":"GLM-5V-Turbo","organization_name":"Zhipu AI","organization_id":"zai-org","benchmark_score":0.586,"normalized_score":0.586,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2026-04-02","announcement_date":"2026-04-02","multimodal":true,"param_count":null,"is_new":false},{"rank":12,"model_id":"gemini-3.1-flash-lite-preview","model_name":"Gemini 3.1 Flash-Lite","organization_name":"Google","organization_id":"google","benchmark_score":0.406,"normalized_score":0.406,"verified":false,"self_reported":true,"provider_id":"google","input_cost_per_million":0.25,"output_cost_per_million":1.5,"speed_rps":null,"context_window":1000000,"release_date":"2026-03-03","announcement_date":"2026-03-03","multimodal":true,"param_count":null,"is_new":false},{"rank":13,"model_id":"gemma-3-1b-it","model_name":"Gemma 3 1B","organization_name":"Google","organization_id":"google","benchmark_score":0.364,"normalized_score":0.364,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2025-03-12","announcement_date":"2025-03-12","multimodal":false,"param_count":1000000000,"is_new":false}]}