LR2Bench / Drop_Quote.json
UltraRonin's picture
add
59ca3b6
raw
history blame
2.75 kB
[
{
"Model": "Llama-3.1-8B-Instruct",
"CR": "44.0",
"S-Acc": "11.2",
"EM": "0.0",
"PM-0.5": "1.0",
"Tokens": "2122"
},
{
"Model": "Llama-3.1-70B-Instruct",
"CR": "82.0",
"S-Acc": "27.7",
"EM": "0.0",
"PM-0.5": "12.0",
"Tokens": "1498"
},
{
"Model": "Llama-3.3-70B-Instruct",
"CR": "99.0",
"S-Acc": "29.0",
"EM": "0.0",
"PM-0.5": "13.0",
"Tokens": "918"
},
{
"Model": "Mistral-7B-Instruct-v0.3",
"CR": "66.0",
"S-Acc": "6.6",
"EM": "0.0",
"PM-0.5": "1.0",
"Tokens": "2336"
},
{
"Model": "Mistral-Small-Instruct-2409",
"CR": "97.0",
"S-Acc": "26.9",
"EM": "0.0",
"PM-0.5": "6.0",
"Tokens": "1614"
},
{
"Model": "Mistral-Large-Instruct-2411",
"CR": "98.0",
"S-Acc": "24.7",
"EM": "0.0",
"PM-0.5": "9.0",
"Tokens": "1565"
},
{
"Model": "Qwen2.5-7B-Instruct",
"CR": "98.0",
"S-Acc": "21.9",
"EM": "0.0",
"PM-0.5": "4.0",
"Tokens": "1851"
},
{
"Model": "Qwen2.5-32B-Instruct",
"CR": "95.0",
"S-Acc": "28.4",
"EM": "0.0",
"PM-0.5": "14.0",
"Tokens": "1197"
},
{
"Model": "Qwen2.5-72B-Instruct",
"CR": "94.0",
"S-Acc": "30.9",
"EM": "0.0",
"PM-0.5": "13.0",
"Tokens": "1756"
},
{
"Model": "QwQ-32B-Preview",
"CR": "33.0",
"S-Acc": "7.5",
"EM": "0.0",
"PM-0.5": "8.0",
"Tokens": "6078"
},
{
"Model": "DeepSeek-R1",
"CR": "100.0",
"S-Acc": "47.3",
"EM": "7.0",
"PM-0.5": "42.0",
"Tokens": "11422"
},
{
"Model": "Gemini-2.0-exp",
"CR": "92.0",
"S-Acc": "34.2",
"EM": "0.0",
"PM-0.5": "17.0",
"Tokens": "2717"
},
{
"Model": "Gemini-2.0-thinking",
"CR": "96.0",
"S-Acc": "34.4",
"EM": "0.0",
"PM-0.5": "23.0",
"Tokens": "3385"
},
{
"Model": "OpenAI-gpt-4o",
"CR": "99.0",
"S-Acc": "31.1",
"EM": "0.0",
"PM-0.5": "14.0",
"Tokens": "1165"
},
{
"Model": "OpenAI-o1-mini",
"CR": "96.0",
"S-Acc": "34.3",
"EM": "2.0",
"PM-0.5": "21.0",
"Tokens": "13255"
},
{
"Model": "OpenAI-o1-preview",
"CR": "97.0",
"S-Acc": "38.8",
"EM": "13.0",
"PM-0.5": "38.0",
"Tokens": "13595"
}
]