Polish-SLM-Benchmark / results.json
Aleksander22's picture
Update results.json
a75f05d verified
Raw History Blame Contribute Delete
10.4 kB
{
"updated": "2026-09-09",
"scoring": "primary_composite_v1.0.1",
"models": [
{
"model": "OrisTeam/Koliber-1.2",
"author": "OrisTeam",
"group": "75M–150M",
"params": "126M",
"type": "Base",
"hf": "",
"average": 33.71,
"polemo_in": 37.26,
"polemo_out": 44.94,
"tags8": 36.37,
"belebele": 22.67,
"cbd": 14.82,
"dyk": 28.70,
"klej_ner": 23.71,
"polqa": 52.97,
"ppc": 33.10,
"psc": 42.52,
"checkpoint": "update_00045529.pt"
},
{
"model": "OrisTeam/Trillium-2.137M",
"author": "OrisTeam",
"group": "<75M",
"params": "2.137M",
"type": "Base",
"hf": "https://huggingface.co/OrisTeam/Trillium-2.137M",
"average": 27.59,
"polemo_in": 35.87,
"polemo_out": 42.51,
"tags8": 15.58,
"belebele": 22.89,
"cbd": 5.08,
"dyk": 14.68,
"klej_ner": 16.03,
"polqa": 53.36,
"ppc": 43.40,
"psc": 26.54,
"checkpoint": "update_00009020.pt",
"tokens_in": 138547200
},
{
"model": "LiquidAI/LFM2.5-230M",
"author": "LiquidAI",
"group": "150M–350M",
"params": "230M",
"type": "Base",
"hf": "https://huggingface.co/LiquidAI/LFM2.5-230M",
"average": 25.58,
"polemo_in": 20.64,
"polemo_out": 30.77,
"tags8": 15.48,
"belebele": 24.11,
"cbd": 2.90,
"dyk": 25.55,
"klej_ner": 17.93,
"polqa": 47.23,
"ppc": 32.30,
"psc": 38.88
},
{
"model": "LiquidAI/LFM2.5-350M",
"author": "LiquidAI",
"group": "150M–350M",
"params": "350M",
"type": "Base",
"hf": "https://huggingface.co/LiquidAI/LFM2.5-350M",
"average": 25.65,
"polemo_in": 37.53,
"polemo_out": 36.44,
"tags8": 14.18,
"belebele": 23.22,
"cbd": 8.46,
"dyk": 25.22,
"klej_ner": 21.62,
"polqa": 50.17,
"ppc": 28.50,
"psc": 11.17
},
{
"model": "SlayerLab/gollem-v4-250m-pl-ckpt16k",
"author": "SlayerLab",
"group": "150M–350M",
"params": "247.95M",
"type": "Base",
"hf": "https://huggingface.co/SlayerLab/gollem-v4-250m-pl",
"average": 30.93,
"polemo_in": 40.86,
"polemo_out": 35.63,
"tags8": 52.33,
"belebele": 24.11,
"cbd": 9.02,
"dyk": 26.07,
"klej_ner": 21.62,
"polqa": 49.3,
"ppc": 32.2,
"psc": 18.18,
"checkpoint": "ckpt_16000.safetensors"
},
{
"model": "SlayerLab/gollem-v4-250m-pl",
"author": "SlayerLab",
"group": "150M–350M",
"params": "247.95M",
"type": "Base",
"hf": "https://huggingface.co/SlayerLab/gollem-v4-250m-pl",
"average": 26.19,
"polemo_in": 39.75,
"polemo_out": 13.56,
"tags8": 46.43,
"belebele": 23.78,
"cbd": 10.88,
"dyk": 25.31,
"klej_ner": 22.3,
"polqa": 48.23,
"ppc": 26.9,
"psc": 4.75,
"checkpoint": "ckpt_48828.safetensors"
},
{
"model": "OrisTeam/Koliber-v1.2-old-ckpt46k",
"author": "OrisTeam",
"group": "150M–350M",
"params": "~175M",
"type": "Base",
"average": 30.96,
"polemo_in": 23.82,
"polemo_out": 32.39,
"tags8": 36.25,
"belebele": 23.22,
"cbd": 11.10,
"dyk": 25.15,
"klej_ner": 23.76,
"polqa": 52.79,
"ppc": 37.60,
"psc": 43.50,
"checkpoint": "update_00046000.pt",
"tokens_in": 2119898112
},
{
"model": "OrisTeam/Koliber-v1.0",
"author": "OrisTeam",
"group": "75M–150M",
"params": "126.04M",
"type": "Base",
"hf": "https://huggingface.co/OrisTeam/Koliber-v1.0",
"average": 30.72,
"polemo_in": 37.4,
"polemo_out": 26.11,
"tags8": 46.87,
"belebele": 22.44,
"cbd": 7.24,
"dyk": 24.48,
"klej_ner": 23.28,
"polqa": 52.81,
"ppc": 35.1,
"psc": 31.48,
"checkpoint": "update_00055000.pt",
"tokens_in": 2534400000
},
{
"model": "OrisTeam/Koliber-v1.1-Preview ",
"author": "OrisTeam",
"group": "75M–150M",
"params": "126.04M",
"type": "Base",
"hf": "https://huggingface.co/OrisTeam/Koliber-v1.1-Preview",
"average": 30.29,
"polemo_in": 38.09,
"polemo_out": 32.39,
"tags8": 44.97,
"belebele": 22.44,
"cbd": 5.92,
"dyk": 21.85,
"klej_ner": 23.32,
"polqa": 52.85,
"ppc": 34.7,
"psc": 26.35,
"checkpoint": "update_00004000.pt",
"tokens_in": 184320000
},
{
"model": "OrisTeam/Vyuhu-280M-Base-3012m *",
"author": "OrisTeam",
"group": "150M–350M",
"params": "282.68M",
"type": "Elastic",
"hf": "https://huggingface.co/OrisTeam/Vyuhu-280M-Base-3012m",
"average": 30.21,
"polemo_in": 22.44,
"polemo_out": 29.96,
"tags8": 50.91,
"belebele": 26.67,
"cbd": 11.04,
"dyk": 24.24,
"klej_ner": 15.6,
"polqa": 53.28,
"ppc": 37.2,
"psc": 30.72,
"profile": "Sankarshana"
},
{
"model": "Azurro/APT3-275M-Base",
"author": "Azurro",
"group": "150M–350M",
"params": "275M",
"type": "Base",
"hf": "https://huggingface.co/Azurro/APT3-275M-Base",
"average": 29.28,
"polemo_in": 16.62,
"polemo_out": 29.55,
"tags8": 33.71,
"belebele": 22.44,
"cbd": 5.25,
"dyk": 27.68,
"klej_ner": 23.37,
"polqa": 52.86,
"ppc": 45.0,
"psc": 36.28
},
{
"model": "dkleczek/papuGaPT2",
"author": "dkleczek",
"group": "75M–150M",
"params": "~124M",
"type": "Base",
"hf": "https://huggingface.co/dkleczek/papuGaPT2",
"average": 27.51,
"polemo_in": 18.14,
"polemo_out": 25.1,
"tags8": 48.24,
"belebele": 22.56,
"cbd": 6.81,
"dyk": 18.34,
"klej_ner": 18.9,
"polqa": 51.68,
"ppc": 22.0,
"psc": 43.36
},
{
"model": "Maggio33/GoLLeM-110M-PL-v3",
"author": "Maggio33",
"group": "75M–150M",
"params": "110.03M",
"type": "Base",
"hf": "https://huggingface.co/Maggio33/GoLLeM-110M-PL-v3",
"average": 26.56,
"polemo_in": 17.73,
"polemo_out": 8.1,
"tags8": 39.64,
"belebele": 24.33,
"cbd": 11.49,
"dyk": 26.94,
"klej_ner": 16.67,
"polqa": 52.14,
"ppc": 26.6,
"psc": 42.0
},
{
"model": "Maggio33/GoLLeM-110M-PL",
"author": "Maggio33",
"group": "75M–150M",
"params": "110.03M",
"type": "Base",
"hf": "https://huggingface.co/Maggio33/GoLLeM-110M-PL",
"average": 25.62,
"polemo_in": 16.76,
"polemo_out": 13.56,
"tags8": 42.31,
"belebele": 23.33,
"cbd": 11.67,
"dyk": 26.92,
"klej_ner": 22.55,
"polqa": 50.11,
"ppc": 27.6,
"psc": 21.35
},
{
"model": "KateMajzel/GoLLeM-45M-PL",
"author": "KateMajzel",
"group": "<75M",
"params": "42.5M",
"type": "Base",
"hf": "https://huggingface.co/KateMajzel/GoLLeM-45M-PL",
"average": 25.47,
"polemo_in": 23.55,
"polemo_out": 16.4,
"tags8": 34.97,
"belebele": 22.56,
"cbd": 7.78,
"dyk": 27.74,
"klej_ner": 27.89,
"polqa": 53.43,
"ppc": 16.9,
"psc": 23.53
},
{
"model": "romanoza/gpt2-small-III",
"author": "romanoza",
"group": "75M–150M",
"params": "~125M",
"type": "Base",
"hf": "https://huggingface.co/romanoza/gpt2-small-III",
"average": 25.27,
"polemo_in": 14.68,
"polemo_out": 7.49,
"tags8": 34.84,
"belebele": 23.0,
"cbd": 8.61,
"dyk": 29.04,
"klej_ner": 20.31,
"polqa": 51.84,
"ppc": 27.0,
"psc": 35.94
},
{
"model": "Maggio33/GoLLeM-110M-PL-v2",
"author": "Maggio33",
"group": "75M–150M",
"params": "~110M",
"type": "Base",
"hf": "https://huggingface.co/Maggio33/GoLLeM-110M-PL-v2",
"average": 24.9,
"polemo_in": 16.62,
"polemo_out": 2.63,
"tags8": 39.57,
"belebele": 23.11,
"cbd": 17.54,
"dyk": 24.73,
"klej_ner": 16.86,
"polqa": 53.36,
"ppc": 19.8,
"psc": 34.76
},
{
"model": "radlab/polish-gpt2-small *",
"author": "RADLAB",
"group": "75M–150M",
"params": "~125M",
"type": "Base",
"hf": "https://huggingface.co/radlab/polish-gpt2-small",
"average": 24.78,
"polemo_in": 17.73,
"polemo_out": 1.62,
"tags8": 25.85,
"belebele": 23.11,
"cbd": 13.14,
"dyk": 29.14,
"klej_ner": 12.39,
"polqa": 52.45,
"ppc": 41.9,
"psc": 30.48
},
{
"model": "radlab/polish-gpt2-small-v2",
"author": "RADLAB",
"group": "75M–150M",
"params": "~126M",
"type": "Base",
"hf": "https://huggingface.co/radlab/polish-gpt2-small-v2",
"average": 24.71,
"polemo_in": 19.67,
"polemo_out": 29.15,
"tags8": 45.97,
"belebele": 24.11,
"cbd": 5.78,
"dyk": 23.86,
"klej_ner": 16.72,
"polqa": 47.24,
"ppc": 33.4,
"psc": 1.2
},
{
"model": "mbien/gpt-neo-pl-125m *",
"author": "mbien",
"group": "75M–150M",
"params": "~125M",
"type": "Base",
"hf": "https://huggingface.co/mbien/gpt-neo-pl-125m",
"average": 23.41,
"polemo_in": 17.73,
"polemo_out": 2.83,
"tags8": 18.71,
"belebele": 25.44,
"cbd": 1.92,
"dyk": 18.97,
"klej_ner": 12.97,
"polqa": 53.32,
"ppc": 41.3,
"psc": 40.86
},
{
"model": "rakoo/distilgpt2-pl *",
"author": "rakoo",
"group": "75M–150M",
"params": "81.9M",
"type": "CPT",
"hf": "https://huggingface.co/rakoo/distilgpt2-pl",
"average": 21.4,
"polemo_in": 15.65,
"polemo_out": 1.01,
"tags8": 31.98,
"belebele": 23.0,
"cbd": 3.17,
"dyk": 15.67,
"klej_ner": 14.67,
"polqa": 53.42,
"ppc": 38.1,
"psc": 17.38
}
],
"note": "* = not recomputed with scorer v1.0.1"
}