general-eval-card / data /developers /abacusresearch.json
GitHub Actions
chore: sync EEE pipeline output [2026-03-28 11:37 UTC]
aa3daac
raw
history blame
482 Bytes
{
"developer": "AbacusResearch",
"models": [
{
"id": "AbacusResearch/Jallabi-34B",
"name": "Jallabi-34B",
"developer": "AbacusResearch",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.3529,
"hfopenllm_v2/BBH": 0.6023,
"hfopenllm_v2/MATH Level 5": 0.0521,
"hfopenllm_v2/GPQA": 0.3389,
"hfopenllm_v2/MUSR": 0.4822,
"hfopenllm_v2/MMLU-PRO": 0.4682
}
}
]
}