tabedini commited on
Commit
c46b820
·
verified ·
1 Parent(s): cc6b025

Update leaderboard_data.jsonl

Browse files
Files changed (1) hide show
  1. leaderboard_data.jsonl +5 -1
leaderboard_data.jsonl CHANGED
@@ -22,4 +22,8 @@
22
  {"Model":"O1-OPEN/OpenO1-LLama-8B-v0.1", "Precision": "bfloat16", "#Params (B)": 8.03, "Part Multiple Choice": 34.66, "ARC Easy": 77.87, "ARC Challenge": 63.08, "MMLU Pro": 21.24, "AUT Multiple Choice Persian": 54.24, "Hub License": "None", "Model sha": "main", "model_name_for_query": "O1-OPEN/OpenO1-LLama-8B-v0.1"}
23
  {"Model":"PrincetonPLI/Llama-3-8B-Instruct-SkillMix", "Precision": "bfloat16", "#Params (B)": 8.03, "Part Multiple Choice": 34.67, "ARC Easy": 72.98, "ARC Challenge": 60.40, "MMLU Pro": 23.38, "AUT Multiple Choice Persian": 54.04, "Hub License": "llama3", "Model sha": "main", "model_name_for_query": "PrincetonPLI/Llama-3-8B-Instruct-SkillMix"}
24
  {"Model":"Qwen/QwQ-32B-Preview", "Precision": "bfloat16", "#Params (B)": 32.8, "Part Multiple Choice": 46.64, "ARC Easy": 91.95, "ARC Challenge": 87.24, "MMLU Pro": 37.94, "AUT Multiple Choice Persian": 60.15, "Hub License": "apache-2.0", "Model sha": "main", "model_name_for_query": "Qwen/QwQ-32B-Preview"}
25
- {"Model":"NousResearch/Hermes-3-Llama-3.1-8B", "Precision": "bfloat16", "#Params (B)": 8.03, "Part Multiple Choice": 35.01, "ARC Easy": 77.01, "ARC Challenge": 58.39, "MMLU Pro": 21.00, "AUT Multiple Choice Persian": 52.46, "Hub License": "llama3", "Model sha": "main", "model_name_for_query": "NousResearch/Hermes-3-Llama-3.1-8B"}
 
 
 
 
 
22
  {"Model":"O1-OPEN/OpenO1-LLama-8B-v0.1", "Precision": "bfloat16", "#Params (B)": 8.03, "Part Multiple Choice": 34.66, "ARC Easy": 77.87, "ARC Challenge": 63.08, "MMLU Pro": 21.24, "AUT Multiple Choice Persian": 54.24, "Hub License": "None", "Model sha": "main", "model_name_for_query": "O1-OPEN/OpenO1-LLama-8B-v0.1"}
23
  {"Model":"PrincetonPLI/Llama-3-8B-Instruct-SkillMix", "Precision": "bfloat16", "#Params (B)": 8.03, "Part Multiple Choice": 34.67, "ARC Easy": 72.98, "ARC Challenge": 60.40, "MMLU Pro": 23.38, "AUT Multiple Choice Persian": 54.04, "Hub License": "llama3", "Model sha": "main", "model_name_for_query": "PrincetonPLI/Llama-3-8B-Instruct-SkillMix"}
24
  {"Model":"Qwen/QwQ-32B-Preview", "Precision": "bfloat16", "#Params (B)": 32.8, "Part Multiple Choice": 46.64, "ARC Easy": 91.95, "ARC Challenge": 87.24, "MMLU Pro": 37.94, "AUT Multiple Choice Persian": 60.15, "Hub License": "apache-2.0", "Model sha": "main", "model_name_for_query": "Qwen/QwQ-32B-Preview"}
25
+ {"Model":"NousResearch/Hermes-3-Llama-3.1-8B", "Precision": "bfloat16", "#Params (B)": 8.03, "Part Multiple Choice": 35.01, "ARC Easy": 77.01, "ARC Challenge": 58.39, "MMLU Pro": 21.00, "AUT Multiple Choice Persian": 52.46, "Hub License": "llama3", "Model sha": "main", "model_name_for_query": "NousResearch/Hermes-3-Llama-3.1-8B"}
26
+ {"Model":"google/gemma-3-1b-it", "Precision": "bfloat16", "#Params (B)": 1, "Part Multiple Choice": 27.15, "ARC Easy": 41.67, "ARC Challenge": 31.54, "MMLU Pro": 16.23, "AUT Multiple Choice Persian": 36.88, "Hub License": "gemma", "Model sha": "main", "model_name_for_query": "google/gemma-3-1b-it"}
27
+ {"Model":"google/gemma-3-4b-it", "Precision": "bfloat16", "#Params (B)": 4.3, "Part Multiple Choice": 34.40, "ARC Easy": 77.01, "ARC Challenge": 63.76, "MMLU Pro": 19.81, "AUT Multiple Choice Persian": 50.30, "Hub License": "gemma", "Model sha": "main", "model_name_for_query": "google/gemma-3-4b-it"}
28
+ {"Model":"google/gemma-3-12b-it", "Precision": "bfloat16", "#Params (B)": 12.2, "Part Multiple Choice": 43.52, "ARC Easy": 93.39, "ARC Challenge": 81.21, "MMLU Pro": 29.36, "AUT Multiple Choice Persian": 57.00, "Hub License": "gemma", "Model sha": "main", "model_name_for_query": "google/gemma-3-12b-it"}
29
+ {"Model":"google/gemma-3-27b-it", "Precision": "bfloat16", "#Params (B)": 27.4, "Part Multiple Choice": 48.56, "ARC Easy": 95.69, "ARC Challenge": 90.60, "MMLU Pro": 40.10, "AUT Multiple Choice Persian": 64.30, "Hub License": "gemma", "Model sha": "main", "model_name_for_query": "google/gemma-3-27b-it"}