{"benchmark_id":"humaneval+","benchmark_name":"HumanEval+","benchmark_description":"Enhanced version of HumanEval that extends the original test cases by 80x using EvalPlus framework for rigorous evaluation of LLM-synthesized code functional correctness, detecting previously undetected wrong code","max_score":1.0,"categories":["reasoning"],"modality":"text","total_models":10,"entries":[{"rank":1,"model_id":"phi-4-reasoning","model_name":"Phi 4 Reasoning","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.929,"normalized_score":0.929,"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":"2025-04-30","announcement_date":"2025-04-30","multimodal":false,"param_count":14000000000,"is_new":false},{"rank":2,"model_id":"phi-4-reasoning-plus","model_name":"Phi 4 Reasoning Plus","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.923,"normalized_score":0.923,"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":"2025-04-30","announcement_date":"2025-04-30","multimodal":false,"param_count":14000000000,"is_new":false},{"rank":3,"model_id":"granite-3.3-8b-base","model_name":"Granite 3.3 8B Base","organization_name":"IBM","organization_id":"ibm","benchmark_score":0.8609,"normalized_score":0.8609,"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":"2025-04-16","announcement_date":"2025-04-16","multimodal":true,"param_count":8170000000,"is_new":false},{"rank":4,"model_id":"granite-3.3-8b-instruct","model_name":"Granite 3.3 8B Instruct","organization_name":"IBM","organization_id":"ibm","benchmark_score":0.8609,"normalized_score":0.8609,"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":"2025-04-16","announcement_date":"2025-04-16","multimodal":true,"param_count":8000000000,"is_new":false},{"rank":5,"model_id":"phi-4","model_name":"Phi 4","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.828,"normalized_score":0.828,"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":"2024-12-12","announcement_date":"2024-12-12","multimodal":false,"param_count":14700000000,"is_new":false},{"rank":6,"model_id":"granite-4.0-tiny-preview","model_name":"IBM Granite 4.0 Tiny Preview","organization_name":"IBM","organization_id":"ibm","benchmark_score":0.783,"normalized_score":0.783,"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":"2025-05-02","announcement_date":"2025-05-02","multimodal":false,"param_count":7000000000,"is_new":false},{"rank":7,"model_id":"mimo-v2.5-pro","model_name":"MiMo-V2.5-Pro","organization_name":"Xiaomi","organization_id":"xiaomi","benchmark_score":0.756,"normalized_score":0.756,"verified":false,"self_reported":true,"provider_id":"xiaomi","input_cost_per_million":0.435,"output_cost_per_million":0.87,"speed_rps":null,"context_window":1048576,"release_date":"2026-04-27","announcement_date":"2026-04-27","multimodal":false,"param_count":1023244718976,"is_new":false},{"rank":8,"model_id":"qwen-2.5-32b-instruct","model_name":"Qwen2.5 32B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.524,"normalized_score":0.524,"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":"2024-09-19","announcement_date":"2024-09-19","multimodal":false,"param_count":32500000000,"is_new":false},{"rank":9,"model_id":"qwen-2.5-14b-instruct","model_name":"Qwen2.5 14B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.512,"normalized_score":0.512,"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":"2024-09-19","announcement_date":"2024-09-19","multimodal":false,"param_count":14700000000,"is_new":false},{"rank":10,"model_id":"ernie-4.5","model_name":"ERNIE 4.5","organization_name":"Baidu","organization_id":"baidu","benchmark_score":0.25,"normalized_score":0.25,"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":"2025-06-25","announcement_date":"2025-06-25","multimodal":false,"param_count":21000000000,"is_new":false}]}