LR2Bench / Acrostic.json
UltraRonin's picture
add
c5ebc43
[
{
"Model": "Llama-3.1-8B-Instruct",
"CR": "43.0",
"S-Acc": "5.6",
"EM": "0.0",
"PM-0.5": "0.0",
"Tokens": "3712"
},
{
"Model": "Llama-3.1-70B-Instruct",
"CR": "84.0",
"S-Acc": "35.8",
"EM": "0.0",
"PM-0.5": "21.0",
"Tokens": "3565"
},
{
"Model": "Llama-3.3-70B-Instruct",
"CR": "97.0",
"S-Acc": "40.8",
"EM": "0.0",
"PM-0.5": "28.0",
"Tokens": "3584"
},
{
"Model": "Mistral-7B-Instruct-v0.3",
"CR": "75.0",
"S-Acc": "7.9",
"EM": "0.0",
"PM-0.5": "0.0",
"Tokens": "4600"
},
{
"Model": "Mistral-Small-Instruct-2409",
"CR": "67.0",
"S-Acc": "5.5",
"EM": "0.0",
"PM-0.5": "0.0",
"Tokens": "4171"
},
{
"Model": "Mistral-Large-Instruct-2411",
"CR": "98.0",
"S-Acc": "39.4",
"EM": "0.0",
"PM-0.5": "20.0",
"Tokens": "4279"
},
{
"Model": "Qwen2.5-7B-Instruct",
"CR": "42.0",
"S-Acc": "3.6",
"EM": "0.0",
"PM-0.5": "0.0",
"Tokens": "4159"
},
{
"Model": "Qwen2.5-32B-Instruct",
"CR": "100.0",
"S-Acc": "31.8",
"EM": "0.0",
"PM-0.5": "2.0",
"Tokens": "4073"
},
{
"Model": "Qwen2.5-72B-Instruct",
"CR": "100.0",
"S-Acc": "39.3",
"EM": "0.0",
"PM-0.5": "18.0",
"Tokens": "4111"
},
{
"Model": "QwQ-32B-Preview",
"CR": "97.0",
"S-Acc": "31.6",
"EM": "0.0",
"PM-0.5": "6.0",
"Tokens": "4964"
},
{
"Model": "DeepSeek-R1",
"CR": "100.0",
"S-Acc": "62.2",
"EM": "0.0",
"PM-0.5": "83.0",
"Tokens": "10077"
},
{
"Model": "Gemini-2.0-flash",
"CR": "98.0",
"S-Acc": "48.0",
"EM": "0.0",
"PM-0.5": "48.0",
"Tokens": "4020"
},
{
"Model": "Gemini-2.0-flash-thinking",
"CR": "92.0",
"S-Acc": "40.7",
"EM": "0.0",
"PM-0.5": "27.0",
"Tokens": "4257"
},
{
"Model": "OpenAI-gpt-4o",
"CR": "100.0",
"S-Acc": "56.0",
"EM": "0.0",
"PM-0.5": "67.0",
"Tokens": "3229"
},
{
"Model": "OpenAI-o1-mini",
"CR": "97.0",
"S-Acc": "34.7",
"EM": "0.0",
"PM-0.5": "12.0",
"Tokens": "10952"
},
{
"Model": "OpenAI-o1-preview",
"CR": "100.0",
"S-Acc": "67.2",
"EM": "0.0",
"PM-0.5": "90.0",
"Tokens": "14847"
}
]