GitHub Actions
chore: sync EEE pipeline output [2026-03-28 11:37 UTC]
aa3daac
raw
history blame
1.32 kB
{
"developer": "AGI-0",
"models": [
{
"id": "AGI-0/Art-v0-3B",
"name": "Art-v0-3B",
"developer": "AGI-0",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.3192,
"hfopenllm_v2/BBH": 0.3401,
"hfopenllm_v2/MATH Level 5": 0.2462,
"hfopenllm_v2/GPQA": 0.2592,
"hfopenllm_v2/MUSR": 0.3768,
"hfopenllm_v2/MMLU-PRO": 0.1179
}
},
{
"id": "AGI-0/Artificium-llama3.1-8B-001",
"name": "Artificium-llama3.1-8B-001",
"developer": "AGI-0",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.5248,
"hfopenllm_v2/BBH": 0.4256,
"hfopenllm_v2/MATH Level 5": 0.136,
"hfopenllm_v2/GPQA": 0.2659,
"hfopenllm_v2/MUSR": 0.3795,
"hfopenllm_v2/MMLU-PRO": 0.3182
}
},
{
"id": "AGI-0/smartllama3.1-8B-001",
"name": "smartllama3.1-8B-001",
"developer": "AGI-0",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.3518,
"hfopenllm_v2/BBH": 0.467,
"hfopenllm_v2/MATH Level 5": 0.1299,
"hfopenllm_v2/GPQA": 0.3062,
"hfopenllm_v2/MUSR": 0.4386,
"hfopenllm_v2/MMLU-PRO": 0.3487
}
}
]
}