{"model_id": "Gemini 2.5 Pro(Not on hub)", "benchmark": "MMLU", "subject": "ALL", "accuracy": 88.00, "sample_count": 1000, "timestamp": "2025-06-25T14:17:00.000000"} {"model_id": "ChatGPT 4.5(Not on hub)", "benchmark": "MMLU", "subject": "ALL", "accuracy": 86.50, "sample_count": 1000, "timestamp": "2025-06-25T14:17:01.000000"} {"model_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "benchmark": "MMLU", "subject": "ALL", "accuracy": 85.00, "sample_count": 1000, "timestamp": "2025-06-25T14:17:02.000000"} {"model_id": "Qwen/Qwen3-235B-A22B", "benchmark": "MMLU", "subject": "ALL", "accuracy": 87.20, "sample_count": 1000, "timestamp": "2025-06-25T14:17:03.000000"} {"model_id": "Mistralai/Mistral-Small-3.2-24B-Instruct-2506", "benchmark": "MMLU", "subject": "ALL", "accuracy": 84.80, "sample_count": 1000, "timestamp": "2025-06-25T14:17:04.000000"} {"model_id": "Claude 4 Opus(Not on hub)", "benchmark": "MMLU", "subject": "ALL", "accuracy": 89.10, "sample_count": 1000, "timestamp": "2025-06-25T14:17:05.000000"} {"model_id": "unsloth/gemma-3-1b-it", "benchmark": "MMLU", "subject": "ALL", "accuracy": 59.60, "sample_count": 1000, "timestamp": "2025-06-25T21:28:36.000000"}