LR2Bench / Overall.json
UltraRonin's picture
add
c5ebc43
raw
history blame
2.76 kB
[
{
"Model": "Llama-3.1-8B-Instruct",
"CR": "42.6",
"S-Acc": "9.9",
"EM": "0.0",
"PM-0.5": "3.8",
"Tokens": "2478"
},
{
"Model": "Llama-3.1-70B-Instruct",
"CR": "71.8",
"S-Acc": "27.4",
"EM": "0.5",
"PM-0.5": "21.9",
"Tokens": "2090"
},
{
"Model": "Llama-3.3-70B-Instruct",
"CR": "92.4",
"S-Acc": "33.1",
"EM": "1.3",
"PM-0.5": "25.8",
"Tokens": "1842"
},
{
"Model": "Mistral-7B-Instruct-v0.3",
"CR": "85.8",
"S-Acc": "12.1",
"EM": "0.0",
"PM-0.5": "2.3",
"Tokens": "2736"
},
{
"Model": "Mistral-Small-Instruct-2409",
"CR": "91.0",
"S-Acc": "23.1",
"EM": "0.2",
"PM-0.5": "13.3",
"Tokens": "2273"
},
{
"Model": "Mistral-Large-Instruct-2411",
"CR": "96.1",
"S-Acc": "36.4",
"EM": "2.5",
"PM-0.5": "30.0",
"Tokens": "2313"
},
{
"Model": "Qwen2.5-7B-Instruct",
"CR": "85.1",
"S-Acc": "17.7",
"EM": "0.3",
"PM-0.5": "5.1",
"Tokens": "2086"
},
{
"Model": "Qwen2.5-32B-Instruct",
"CR": "96.2",
"S-Acc": "29.9",
"EM": "0.6",
"PM-0.5": "14.8",
"Tokens": "1924"
},
{
"Model": "Qwen2.5-72B-Instruct",
"CR": "95.0",
"S-Acc": "33.9",
"EM": "0.9",
"PM-0.5": "20.8",
"Tokens": "2359"
},
{
"Model": "QwQ-32B-Preview",
"CR": "65.0",
"S-Acc": "26.6",
"EM": "8.5",
"PM-0.5": "19.3",
"Tokens": "6709"
},
{
"Model": "DeepSeek-R1",
"CR": "100.0",
"S-Acc": "58.4",
"EM": "20.0",
"PM-0.5": "62.0",
"Tokens": "9856"
},
{
"Model": "Gemini-2.0-flash",
"CR": "81.1",
"S-Acc": "37.0",
"EM": "2.4",
"PM-0.5": "34.5",
"Tokens": "2637"
},
{
"Model": "Gemini-2.0-flash-thinking",
"CR": "88.2",
"S-Acc": "39.4",
"EM": "4.3",
"PM-0.5": "35.0",
"Tokens": "3725"
},
{
"Model": "OpenAI-gpt-4o",
"CR": "99.8",
"S-Acc": "43.7",
"EM": "3.2",
"PM-0.5": "41.7",
"Tokens": "1486"
},
{
"Model": "OpenAI-o1-mini",
"CR": "97.7",
"S-Acc": "41.3",
"EM": "9.1",
"PM-0.5": "32.8",
"Tokens": "9576"
},
{
"Model": "OpenAI-o1-preview",
"CR": "96.3",
"S-Acc": "58.7",
"EM": "23.6",
"PM-0.5": "61.7",
"Tokens": "11436"
}
]