general-eval-card / data /developers /aevalone.json
GitHub Actions
chore: sync EEE pipeline output [2026-03-28 04:56 UTC]
2edd871
raw
history blame
471 Bytes
{
"developer": "aevalone",
"models": [
{
"id": "aevalone/distill_qw_test",
"name": "distill_qw_test",
"developer": "aevalone",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.7409,
"hfopenllm_v2/BBH": 0.5246,
"hfopenllm_v2/MATH Level 5": 0.4781,
"hfopenllm_v2/GPQA": 0.3003,
"hfopenllm_v2/MUSR": 0.386,
"hfopenllm_v2/MMLU-PRO": 0.4092
}
}
]
}