LR2Bench / Logic_Puzzle.json
UltraRonin's picture
add
59ca3b6
raw
history blame
2.76 kB
[
{
"Model": "Llama-3.1-8B-Instruct",
"CR": "57.0",
"S-Acc": "16.0",
"EM": "0.0",
"PM-0.5": "8.0",
"Tokens": "1292"
},
{
"Model": "Llama-3.1-70B-Instruct",
"CR": "56.0",
"S-Acc": "22.8",
"EM": "2.0",
"PM-0.5": "18.0",
"Tokens": "1164"
},
{
"Model": "Llama-3.3-70B-Instruct",
"CR": "80.5",
"S-Acc": "32.2",
"EM": "1.0",
"PM-0.5": "25.0",
"Tokens": "1738"
},
{
"Model": "Mistral-7B-Instruct-v0.3",
"CR": "97.0",
"S-Acc": "19.1",
"EM": "0.0",
"PM-0.5": "4.5",
"Tokens": "1617"
},
{
"Model": "Mistral-Small-Instruct-2409",
"CR": "99.5",
"S-Acc": "30.7",
"EM": "0.5",
"PM-0.5": "12.5",
"Tokens": "1514"
},
{
"Model": "Mistral-Large-Instruct-2411",
"CR": "100.0",
"S-Acc": "38.3",
"EM": "3.0",
"PM-0.5": "30.5",
"Tokens": "1636"
},
{
"Model": "Qwen2.5-7B-Instruct",
"CR": "96.5",
"S-Acc": "25.8",
"EM": "0.0",
"PM-0.5": "8.5",
"Tokens": "1395"
},
{
"Model": "Qwen2.5-32B-Instruct",
"CR": "93.0",
"S-Acc": "32.2",
"EM": "0.0",
"PM-0.5": "22.5",
"Tokens": "1207"
},
{
"Model": "Qwen2.5-72B-Instruct",
"CR": "93.5",
"S-Acc": "34.0",
"EM": "0.0",
"PM-0.5": "23.0",
"Tokens": "1809"
},
{
"Model": "QwQ-32B-Preview",
"CR": "78.5",
"S-Acc": "46.3",
"EM": "19.5",
"PM-0.5": "48.0",
"Tokens": "9523"
},
{
"Model": "DeepSeek-R1",
"CR": "100.0",
"S-Acc": "69.4",
"EM": "42.5",
"PM-0.5": "68.0",
"Tokens": "9204"
},
{
"Model": "Gemini-2.0-exp",
"CR": "58.0",
"S-Acc": "24.2",
"EM": "2.0",
"PM-0.5": "20.0",
"Tokens": "2103"
},
{
"Model": "Gemini-2.0-thinking",
"CR": "99.0",
"S-Acc": "45.9",
"EM": "8.0",
"PM-0.5": "37.5",
"Tokens": "4037"
},
{
"Model": "OpenAI-gpt-4o",
"CR": "100.0",
"S-Acc": "39.3",
"EM": "3.5",
"PM-0.5": "29.5",
"Tokens": "953"
},
{
"Model": "OpenAI-o1-mini",
"CR": "99.0",
"S-Acc": "57.2",
"EM": "23.5",
"PM-0.5": "53.5",
"Tokens": "10242"
},
{
"Model": "OpenAI-o1-preview",
"CR": "99.0",
"S-Acc": "68.8",
"EM": "41.0",
"PM-0.5": "68.5",
"Tokens": "9449"
}
]