general-eval-card / data /developers /agentlans.json
GitHub Actions
chore: sync EEE pipeline output [2026-03-28 04:56 UTC]
2edd871
raw
history blame
4.13 kB
{
"developer": "agentlans",
"models": [
{
"id": "agentlans/Gemma2-9B-AdvancedFuse",
"name": "Gemma2-9B-AdvancedFuse",
"developer": "agentlans",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.1543,
"hfopenllm_v2/BBH": 0.5859,
"hfopenllm_v2/MATH Level 5": 0.1005,
"hfopenllm_v2/GPQA": 0.3347,
"hfopenllm_v2/MUSR": 0.4231,
"hfopenllm_v2/MMLU-PRO": 0.4
}
},
{
"id": "agentlans/Llama-3.2-1B-Instruct-CrashCourse12K",
"name": "Llama-3.2-1B-Instruct-CrashCourse12K",
"developer": "agentlans",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.5395,
"hfopenllm_v2/BBH": 0.3548,
"hfopenllm_v2/MATH Level 5": 0.071,
"hfopenllm_v2/GPQA": 0.2408,
"hfopenllm_v2/MUSR": 0.321,
"hfopenllm_v2/MMLU-PRO": 0.1809
}
},
{
"id": "agentlans/Llama3.1-8B-drill",
"name": "Llama3.1-8B-drill",
"developer": "agentlans",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.7652,
"hfopenllm_v2/BBH": 0.5016,
"hfopenllm_v2/MATH Level 5": 0.1715,
"hfopenllm_v2/GPQA": 0.2676,
"hfopenllm_v2/MUSR": 0.3672,
"hfopenllm_v2/MMLU-PRO": 0.3776
}
},
{
"id": "agentlans/Llama3.1-Daredevilish",
"name": "Llama3.1-Daredevilish",
"developer": "agentlans",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.6292,
"hfopenllm_v2/BBH": 0.5013,
"hfopenllm_v2/MATH Level 5": 0.1292,
"hfopenllm_v2/GPQA": 0.3012,
"hfopenllm_v2/MUSR": 0.4091,
"hfopenllm_v2/MMLU-PRO": 0.3697
}
},
{
"id": "agentlans/Llama3.1-Daredevilish-Instruct",
"name": "Llama3.1-Daredevilish-Instruct",
"developer": "agentlans",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.7926,
"hfopenllm_v2/BBH": 0.5235,
"hfopenllm_v2/MATH Level 5": 0.1722,
"hfopenllm_v2/GPQA": 0.307,
"hfopenllm_v2/MUSR": 0.3911,
"hfopenllm_v2/MMLU-PRO": 0.3877
}
},
{
"id": "agentlans/Llama3.1-LexiHermes-SuperStorm",
"name": "Llama3.1-LexiHermes-SuperStorm",
"developer": "agentlans",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.7835,
"hfopenllm_v2/BBH": 0.5266,
"hfopenllm_v2/MATH Level 5": 0.1616,
"hfopenllm_v2/GPQA": 0.323,
"hfopenllm_v2/MUSR": 0.3963,
"hfopenllm_v2/MMLU-PRO": 0.3844
}
},
{
"id": "agentlans/Llama3.1-SuperDeepFuse",
"name": "Llama3.1-SuperDeepFuse",
"developer": "agentlans",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.7762,
"hfopenllm_v2/BBH": 0.5049,
"hfopenllm_v2/MATH Level 5": 0.1828,
"hfopenllm_v2/GPQA": 0.2743,
"hfopenllm_v2/MUSR": 0.3699,
"hfopenllm_v2/MMLU-PRO": 0.3775
}
},
{
"id": "agentlans/Llama3.1-SuperDeepFuse-CrashCourse12K",
"name": "Llama3.1-SuperDeepFuse-CrashCourse12K",
"developer": "agentlans",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.7187,
"hfopenllm_v2/BBH": 0.5216,
"hfopenllm_v2/MATH Level 5": 0.1805,
"hfopenllm_v2/GPQA": 0.3129,
"hfopenllm_v2/MUSR": 0.4026,
"hfopenllm_v2/MMLU-PRO": 0.3631
}
},
{
"id": "agentlans/Qwen2.5-0.5B-Instruct-CrashCourse-dropout",
"name": "Qwen2.5-0.5B-Instruct-CrashCourse-dropout",
"developer": "agentlans",
"evaluator_relationship": null,
"benchmark_scores": {
"hfopenllm_v2/IFEval": 0.2949,
"hfopenllm_v2/BBH": 0.3312,
"hfopenllm_v2/MATH Level 5": 0.0423,
"hfopenllm_v2/GPQA": 0.2634,
"hfopenllm_v2/MUSR": 0.3342,
"hfopenllm_v2/MMLU-PRO": 0.1608
}
}
]
}