general-eval-card / data /developers /abacusai.json
GitHub Actions
chore: sync EEE pipeline output [2026-03-28 11:49 UTC]
d91b463
raw
history blame
4.36 kB
{
"developer": "abacusai",
"models": [
{
"id": "abacusai/bigstral-12b-32k",
"name": "bigstral-12b-32k",
"developer": "abacusai",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.4194,
"hfopenllm_v2/BBH": 0.47,
"hfopenllm_v2/MATH Level 5": 0.0151,
"hfopenllm_v2/GPQA": 0.2928,
"hfopenllm_v2/MUSR": 0.456,
"hfopenllm_v2/MMLU-PRO": 0.2641
}
},
{
"id": "abacusai/bigyi-15b",
"name": "bigyi-15b",
"developer": "abacusai",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.2094,
"hfopenllm_v2/BBH": 0.4345,
"hfopenllm_v2/MATH Level 5": 0.0295,
"hfopenllm_v2/GPQA": 0.3096,
"hfopenllm_v2/MUSR": 0.3538,
"hfopenllm_v2/MMLU-PRO": 0.3003
}
},
{
"id": "abacusai/Dracarys-72B-Instruct",
"name": "Dracarys-72B-Instruct",
"developer": "abacusai",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.7856,
"hfopenllm_v2/BBH": 0.6944,
"hfopenllm_v2/MATH Level 5": 0.3965,
"hfopenllm_v2/GPQA": 0.3909,
"hfopenllm_v2/MUSR": 0.4558,
"hfopenllm_v2/MMLU-PRO": 0.5456
}
},
{
"id": "abacusai/Liberated-Qwen1.5-14B",
"name": "Liberated-Qwen1.5-14B",
"developer": "abacusai",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.3631,
"hfopenllm_v2/BBH": 0.4948,
"hfopenllm_v2/MATH Level 5": 0.1601,
"hfopenllm_v2/GPQA": 0.2836,
"hfopenllm_v2/MUSR": 0.4175,
"hfopenllm_v2/MMLU-PRO": 0.3512
}
},
{
"id": "abacusai/Llama-3-Smaug-8B",
"name": "Llama-3-Smaug-8B",
"developer": "abacusai",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.4867,
"hfopenllm_v2/BBH": 0.4931,
"hfopenllm_v2/MATH Level 5": 0.0853,
"hfopenllm_v2/GPQA": 0.2483,
"hfopenllm_v2/MUSR": 0.3622,
"hfopenllm_v2/MMLU-PRO": 0.3185
}
},
{
"id": "abacusai/Smaug-34B-v0.1",
"name": "Smaug-34B-v0.1",
"developer": "abacusai",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.5016,
"hfopenllm_v2/BBH": 0.5358,
"hfopenllm_v2/MATH Level 5": 0.0718,
"hfopenllm_v2/GPQA": 0.3297,
"hfopenllm_v2/MUSR": 0.3979,
"hfopenllm_v2/MMLU-PRO": 0.4543
}
},
{
"id": "abacusai/Smaug-72B-v0.1",
"name": "Smaug-72B-v0.1",
"developer": "abacusai",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.5167,
"hfopenllm_v2/BBH": 0.5996,
"hfopenllm_v2/MATH Level 5": 0.1911,
"hfopenllm_v2/GPQA": 0.3238,
"hfopenllm_v2/MUSR": 0.4473,
"hfopenllm_v2/MMLU-PRO": 0.4624
}
},
{
"id": "abacusai/Smaug-Llama-3-70B-Instruct-32K",
"name": "Smaug-Llama-3-70B-Instruct-32K",
"developer": "abacusai",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.7761,
"hfopenllm_v2/BBH": 0.6493,
"hfopenllm_v2/MATH Level 5": 0.2749,
"hfopenllm_v2/GPQA": 0.2961,
"hfopenllm_v2/MUSR": 0.4208,
"hfopenllm_v2/MMLU-PRO": 0.4765
}
},
{
"id": "abacusai/Smaug-Mixtral-v0.1",
"name": "Smaug-Mixtral-v0.1",
"developer": "abacusai",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.5554,
"hfopenllm_v2/BBH": 0.5162,
"hfopenllm_v2/MATH Level 5": 0.0952,
"hfopenllm_v2/GPQA": 0.3012,
"hfopenllm_v2/MUSR": 0.4298,
"hfopenllm_v2/MMLU-PRO": 0.3352
}
},
{
"id": "abacusai/Smaug-Qwen2-72B-Instruct",
"name": "Smaug-Qwen2-72B-Instruct",
"developer": "abacusai",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.7825,
"hfopenllm_v2/BBH": 0.691,
"hfopenllm_v2/MATH Level 5": 0.4131,
"hfopenllm_v2/GPQA": 0.3616,
"hfopenllm_v2/MUSR": 0.4401,
"hfopenllm_v2/MMLU-PRO": 0.519
}
}
]
}