LR2Bench / Cryptogram.json
UltraRonin's picture
add
59ca3b6
raw
history blame
2.74 kB
[
{
"Model": "Llama-3.1-8B-Instruct",
"CR": "43.0",
"S-Acc": "2.3",
"EM": "0.0",
"PM-0.5": "0.0",
"Tokens": "2067"
},
{
"Model": "Llama-3.1-70B-Instruct",
"CR": "62.0",
"S-Acc": "6.9",
"EM": "0.0",
"PM-0.5": "1.0",
"Tokens": "1297"
},
{
"Model": "Llama-3.3-70B-Instruct",
"CR": "99.0",
"S-Acc": "14.3",
"EM": "0.0",
"PM-0.5": "1.0",
"Tokens": "1137"
},
{
"Model": "Mistral-7B-Instruct-v0.3",
"CR": "99.0",
"S-Acc": "4.3",
"EM": "0.0",
"PM-0.5": "0.0",
"Tokens": "1095"
},
{
"Model": "Mistral-Small-Instruct-2409",
"CR": "95.0",
"S-Acc": "7.0",
"EM": "0.0",
"PM-0.5": "0.0",
"Tokens": "1233"
},
{
"Model": "Mistral-Large-Instruct-2411",
"CR": "96.0",
"S-Acc": "13.7",
"EM": "0.0",
"PM-0.5": "1.0",
"Tokens": "1204"
},
{
"Model": "Qwen2.5-7B-Instruct",
"CR": "81.0",
"S-Acc": "3.5",
"EM": "0.0",
"PM-0.5": "0.0",
"Tokens": "1181"
},
{
"Model": "Qwen2.5-32B-Instruct",
"CR": "89.0",
"S-Acc": "9.8",
"EM": "0.0",
"PM-0.5": "0.0",
"Tokens": "1303"
},
{
"Model": "Qwen2.5-72B-Instruct",
"CR": "85.0",
"S-Acc": "11.8",
"EM": "0.0",
"PM-0.5": "0.0",
"Tokens": "1726"
},
{
"Model": "QwQ-32B-Preview",
"CR": "47.0",
"S-Acc": "3.6",
"EM": "0.0",
"PM-0.5": "0.0",
"Tokens": "6491"
},
{
"Model": "DeepSeek-R1",
"CR": "100.0",
"S-Acc": "26.0",
"EM": "4.0",
"PM-0.5": "21.0",
"Tokens": "10344"
},
{
"Model": "Gemini-2.0-exp",
"CR": "47.0",
"S-Acc": "8.5",
"EM": "0.0",
"PM-0.5": "1.0",
"Tokens": "1585"
},
{
"Model": "Gemini-2.0-thinking",
"CR": "68.0",
"S-Acc": "11.2",
"EM": "0.0",
"PM-0.5": "2.0",
"Tokens": "4167"
},
{
"Model": "OpenAI-gpt-4o",
"CR": "100.0",
"S-Acc": "20.7",
"EM": "0.0",
"PM-0.5": "5.0",
"Tokens": "739"
},
{
"Model": "OpenAI-o1-mini",
"CR": "100.0",
"S-Acc": "22.7",
"EM": "1.0",
"PM-0.5": "13.0",
"Tokens": "11208"
},
{
"Model": "OpenAI-o1-preview",
"CR": "92.0",
"S-Acc": "34.8",
"EM": "13.0",
"PM-0.5": "29.0",
"Tokens": "12567"
}
]