LR2Bench / Sudoku.json
UltraRonin's picture
add
59ca3b6
raw
history blame
2.76 kB
[
{
"Model": "Llama-3.1-8B-Instruct",
"CR": "7.5",
"S-Acc": "1.2",
"EM": "0.0",
"PM-0.5": "0.0",
"Tokens": "2782"
},
{
"Model": "Llama-3.1-70B-Instruct",
"CR": "69.5",
"S-Acc": "24.2",
"EM": "1.0",
"PM-0.5": "17.5",
"Tokens": "1939"
},
{
"Model": "Llama-3.3-70B-Instruct",
"CR": "93.5",
"S-Acc": "34.8",
"EM": "7.0",
"PM-0.5": "22.5",
"Tokens": "1061"
},
{
"Model": "Mistral-7B-Instruct-v0.3",
"CR": "84.0",
"S-Acc": "11.9",
"EM": "0.0",
"PM-0.5": "1.5",
"Tokens": "3108"
},
{
"Model": "Mistral-Small-Instruct-2409",
"CR": "89.0",
"S-Acc": "20.5",
"EM": "0.5",
"PM-0.5": "7.5",
"Tokens": "1968"
},
{
"Model": "Mistral-Large-Instruct-2411",
"CR": "85.5",
"S-Acc": "39.5",
"EM": "10.0",
"PM-0.5": "33.5",
"Tokens": "1955"
},
{
"Model": "Qwen2.5-7B-Instruct",
"CR": "94.5",
"S-Acc": "30.2",
"EM": "1.5",
"PM-0.5": "15.0",
"Tokens": "1486"
},
{
"Model": "Qwen2.5-32B-Instruct",
"CR": "100.0",
"S-Acc": "42.8",
"EM": "3.5",
"PM-0.5": "30.5",
"Tokens": "1201"
},
{
"Model": "Qwen2.5-72B-Instruct",
"CR": "97.5",
"S-Acc": "43.0",
"EM": "5.5",
"PM-0.5": "34.0",
"Tokens": "2013"
},
{
"Model": "QwQ-32B-Preview",
"CR": "54.5",
"S-Acc": "40.1",
"EM": "31.5",
"PM-0.5": "35.5",
"Tokens": "8381"
},
{
"Model": "DeepSeek-R1",
"CR": "100.0",
"S-Acc": "70.3",
"EM": "50.0",
"PM-0.5": "64.0",
"Tokens": "8276"
},
{
"Model": "Gemini-2.0-exp",
"CR": "93.0",
"S-Acc": "45.3",
"EM": "12.5",
"PM-0.5": "37.5",
"Tokens": "2842"
},
{
"Model": "Gemini-2.0-thinking",
"CR": "79.5",
"S-Acc": "46.5",
"EM": "16.5",
"PM-0.5": "41.0",
"Tokens": "3852"
},
{
"Model": "OpenAI-gpt-4o",
"CR": "100.0",
"S-Acc": "52.2",
"EM": "14.5",
"PM-0.5": "48.0",
"Tokens": "1103"
},
{
"Model": "OpenAI-o1-mini",
"CR": "99.0",
"S-Acc": "53.4",
"EM": "27.0",
"PM-0.5": "43.0",
"Tokens": "3960"
},
{
"Model": "OpenAI-o1-preview",
"CR": "91.5",
"S-Acc": "65.1",
"EM": "50.0",
"PM-0.5": "55.5",
"Tokens": "8061"
}
]