open-lithuanian-llm-leaderboard / leaderboard_data.jsonl
artena's picture
Upload leaderboard_data.jsonl
4f2e33f verified
{"Model":"meta-llama/Llama-3.2-1B", "Precision": "bfloat16", "#Params (B)": 1.24, "MMLU": 25.85, "GSM8K": 1.82, "ARC Easy": 29.08, "Winogrande": 49.80, "TruthfulQA": 38.75, "Hellaswag": 28.53, "Belebele": 27.33, "Hub License": "llama3.2", "Model sha": "main", "model_name_for_query": "meta-llama/Llama-3.2-1B"}
{"Model":"neurotechnology/Lt-Llama-2-7b-hf ", "Precision": "bfloat16", "#Params (B)": 6.9, "MMLU": 26.01, "GSM8K": 0.0, "ARC Easy": 43.18, "Winogrande": 53.67, "TruthfulQA": 41.38, "Hellaswag": 33.17, "Belebele": 27.23, "Hub License": "llama2", "Model sha": "main", "model_name_for_query": "neurotechnology/Lt-Llama-2-7b-hf"}
{"Model":"neurotechnology/Lt-Llama-2-13b-hf ", "Precision": "bfloat16", "#Params (B)": 12.7, "MMLU": 26.44, "GSM8K": 0.45, "ARC Easy": 54.5, "Winogrande": 61.72, "TruthfulQA": 35.23, "Hellaswag": 40.61, "Belebele": 27.67, "Hub License": "llama2", "Model sha": "main", "model_name_for_query": "neurotechnology/Lt-Llama-2-13b-hf"}
{"Model":"meta-llama/Llama-3.2-3B", "Precision": "bfloat16", "#Params (B)": 3.21, "MMLU": 36.41, "GSM8K": 13.04, "ARC Easy": 39.39, "Winogrande": 51.85, "TruthfulQA": 38.87, "Hellaswag": 31.51, "Belebele": 46.22, "Hub License": "llama3.2", "Model sha": "main", "model_name_for_query": "meta-llama/Llama-3.2-3B"}
{"Model":"google/gemma-2-2b", "Precision": "bfloat16", "#Params (B)": 2.61, "MMLU": 35.84, "GSM8K": 3.64, "ARC Easy": 45.45, "Winogrande": 51.85, "TruthfulQA": 54.78, "Hellaswag": 34.80, "Belebele": 52.44, "Hub License": "gemma", "Model sha": "main", "model_name_for_query": "google/gemma-2-2b"}
{"Model":"meta-llama/Llama-3.1-8B", "Precision": "bfloat16", "#Params (B)": 8.03, "MMLU": 44.86, "GSM8K": 30.17, "ARC Easy": 48.65, "Winogrande": 54.22, "TruthfulQA": 37.61, "Hellaswag": 35.19, "Belebele": 67.56, "Hub License": "llama3.1", "Model sha": "main", "model_name_for_query": "meta-llama/Llama-3.1-8B"}
{"Model":"utter-project/EuroLLM-9B", "Precision": "bfloat16", "#Params (B)": 9.15, "MMLU": 51.95, "GSM8K": 31.16, "ARC Easy": 71.55, "Winogrande": 64.17, "TruthfulQA": 42.13, "Hellaswag": 46.32, "Belebele": 69.44, "Hub License": "eurollm", "Model sha": "main", "model_name_for_query": "utter-project/EuroLLM-9B"}
{"Model":"google/gemma-2-9b", "Precision": "bfloat16", "#Params (B)": 9.24, "MMLU": 60.09, "GSM8K": 25.78, "ARC Easy": 68.31, "Winogrande": 65.15, "TruthfulQA": 39.69, "Hellaswag": 45.32, "Belebele": 86.78, "Hub License": "gemma", "Model sha": "main", "model_name_for_query": "google/gemma-2-9b"}
{"Model":"meta-llama/Llama-3.1-70B", "Precision": "bfloat16", "#Params (B)": 70, "MMLU": 67.50, "GSM8K": 72.40, "ARC Easy": 70.92, "Winogrande": 64.01, "TruthfulQA": 43.59, "Hellaswag": 46.39, "Belebele": 90.02, "Hub License": "llama3.1", "Model sha": "main", "model_name_for_query": "meta-llama/Llama-3.1-70B"}
{"Model":"google/gemma-2-27b", "Precision": "bfloat16", "#Params (B)": 27.2, "MMLU": 64.82, "GSM8K": 68.69, "ARC Easy": 77.40, "Winogrande": 66.77, "TruthfulQA": 42.06, "Hellaswag": 50.82, "Belebele": 89.22, "Hub License": "gemma", "Model sha": "main", "model_name_for_query": "google/gemma-2-27b"}
{"Model":"meta-llama/Llama-3.3-70B-Instruct", "Precision": "bfloat16", "#Params (B)": 70, "MMLU": 71.46, "GSM8K": 80.97, "ARC Easy": 70.66, "Winogrande": 59.83, "TruthfulQA": 45.61, "Hellaswag": 46.05, "Belebele": 89.33, "Hub License": "llama3.3", "Model sha": "main", "model_name_for_query": "meta-llama/Llama-3.3-70B-Instruct"}