GitHub Actions
chore: sync EEE pipeline output [2026-03-28 11:37 UTC]
aa3daac
raw
history blame
890 Bytes
{
"developer": "AI-MO",
"models": [
{
"id": "AI-MO/NuminaMath-7B-CoT",
"name": "NuminaMath-7B-CoT",
"developer": "AI-MO",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.2689,
"hfopenllm_v2/BBH": 0.4314,
"hfopenllm_v2/MATH Level 5": 0.2696,
"hfopenllm_v2/GPQA": 0.2659,
"hfopenllm_v2/MUSR": 0.3303,
"hfopenllm_v2/MMLU-PRO": 0.2868
}
},
{
"id": "AI-MO/NuminaMath-7B-TIR",
"name": "NuminaMath-7B-TIR",
"developer": "AI-MO",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.2756,
"hfopenllm_v2/BBH": 0.4144,
"hfopenllm_v2/MATH Level 5": 0.1609,
"hfopenllm_v2/GPQA": 0.2584,
"hfopenllm_v2/MUSR": 0.3509,
"hfopenllm_v2/MMLU-PRO": 0.2733
}
}
]
}