pecc-leaderboard / current_results.json
Patrick Haller
fix spelling
044c33e
raw
history blame
2.22 kB
[
{
"Model": "Mistral-7B-Instruct-v0.1",
"euler_original": 0.37,
"euler_story": 0.12,
"aoc_original": 3.0,
"aoc_leet": 3.0,
"instruction_only": true,
"link": "https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1"
},
{
"Model": "Mixtral-8x7B-Instruct-v0.1",
"euler_original": 2.86,
"euler_story": 2.23,
"aoc_original": 15.31,
"aoc_leet": 13.01,
"instruction_only": false,
"link": "https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1"
},
{
"Model": "chat_bison",
"euler_story": 0.62,
"euler_original": 2.44,
"aoc_leet": 13.78,
"aoc_original": 17.09,
"instruction_only": false
},
{
"Model": "codechat_bison",
"euler_story": 2.61,
"euler_original": 4.59,
"aoc_original": 21.17,
"aoc_leet": 17.6,
"instruction_only": false
},
{
"Model": "WizardCoder-Python-34B-V1.0",
"aoc_leet": 22.5,
"aoc_original": 24.0,
"euler_original": 2.61,
"euler_story": 2.48,
"instruction_only": true,
"link": "https://huggingface.co/WizardLM/WizardCoder-Python-34B-V1.0"
},
{
"Model": "gpt3.5-turbo",
"euler_original": 8.19,
"euler_story": 6.95,
"aoc_leet": 29.85,
"aoc_original": 50.0,
"instruction_only": false
},
{
"Model": "claude-haiku",
"euler_original": 7.07,
"euler_story": 6.08,
"aoc_original": 51.28,
"aoc_leet": 46.26,
"instruction_only": false
},
{
"Model": "Llama-3-8B-Instruct",
"euler_original": 4.47,
"euler_story": 0.0,
"aoc_leet": 6.38,
"aoc_original": 1.53,
"instruction_only": false,
"link": "https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct"
},
{
"Model": "Phi-3-mini-128k-instruct",
"euler_original": 3.35,
"euler_story": 2.23,
"aoc_original": 10.13,
"aoc_leet": 13.00,
"instruction_only": false,
"link": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct"
},
{
"Model": "WizardLM-2-7b",
"aoc_original": 5.87,
"aoc_leet": 6.89,
"euler_original": 1.24,
"euler_story": 0.87,
"instruction_only": false,
"link": "https://huggingface.co/collections/microsoft/wizardlm-661d403f71e6c8257dbd598a"
}
]