SARFTokenizer / bench_results.json
almaghrabima's picture
Promote v0.3.1 to main (4-domain SOTA at 100k vocab)
f6c72b6 verified
Raw
History Blame Contribute Delete
12.5 kB
{
"eval": "/tmp/v03_eval/eval.parquet",
"results": [
{
"name": "SARFTokenizer v0.3.1",
"vocab": 100000,
"by_label": {
"arabic": {
"chars": 479808,
"words": 82964,
"tokens": 119828,
"cpt": 4.004139266281671,
"tpw": 1.4443373029265705
},
"english": {
"chars": 69308,
"words": 9805,
"tokens": 18568,
"cpt": 3.73265833692374,
"tpw": 1.8937276899541051
},
"math": {
"chars": 518667,
"words": 91001,
"tokens": 122248,
"cpt": 4.242744257574766,
"tpw": 1.3433698530785376
},
"code": {
"chars": 600000,
"words": 115473,
"tokens": 142865,
"cpt": 4.1997690127043015,
"tpw": 1.237215626163692
}
}
},
{
"name": "SARFTokenizer v0.3",
"vocab": 80000,
"by_label": {
"arabic": {
"chars": 479808,
"words": 82964,
"tokens": 150332,
"cpt": 3.191655801825293,
"tpw": 1.8120148498143773
},
"english": {
"chars": 69308,
"words": 9805,
"tokens": 19088,
"cpt": 3.6309723386420787,
"tpw": 1.9467618561958184
},
"math": {
"chars": 518667,
"words": 91001,
"tokens": 121769,
"cpt": 4.259433846052772,
"tpw": 1.3381061746574214
},
"code": {
"chars": 600000,
"words": 115473,
"tokens": 142051,
"cpt": 4.223835101477638,
"tpw": 1.2301663592354923
}
}
},
{
"name": "SARFTokenizer v0.2",
"vocab": 65000,
"by_label": {
"arabic": {
"chars": 479808,
"words": 82964,
"tokens": 130289,
"cpt": 3.6826439684086916,
"tpw": 1.570428137505424
},
"english": {
"chars": 69308,
"words": 9805,
"tokens": 19681,
"cpt": 3.5215690259641277,
"tpw": 2.0072412034676184
},
"math": {
"chars": 518667,
"words": 91001,
"tokens": 132253,
"cpt": 3.921778712014094,
"tpw": 1.4533136998494522
},
"code": {
"chars": 600000,
"words": 115473,
"tokens": 153321,
"cpt": 3.913358248380848,
"tpw": 1.3277649320620404
}
}
},
{
"name": "Qwen3.6-35B-A3B",
"vocab": 248077,
"by_label": {
"arabic": {
"chars": 479808,
"words": 82964,
"tokens": 153331,
"cpt": 3.129230227416504,
"tpw": 1.8481630586760522
},
"english": {
"chars": 69308,
"words": 9805,
"tokens": 23217,
"cpt": 2.985226342766077,
"tpw": 2.3678735339112698
},
"math": {
"chars": 518667,
"words": 91001,
"tokens": 160453,
"cpt": 3.2325166871295643,
"tpw": 1.7632004043911604
},
"code": {
"chars": 600000,
"words": 115473,
"tokens": 174818,
"cpt": 3.4321408550606916,
"tpw": 1.5139296632113135
}
}
},
{
"name": "GPT-4o (o200k_base)",
"vocab": 200019,
"by_label": {
"arabic": {
"chars": 479808,
"words": 82964,
"tokens": 155409,
"cpt": 3.0873887612686524,
"tpw": 1.8732100670170195
},
"english": {
"chars": 69308,
"words": 9805,
"tokens": 20332,
"cpt": 3.4088136927011607,
"tpw": 2.0736359000509945
},
"math": {
"chars": 518667,
"words": 91001,
"tokens": 147972,
"cpt": 3.505169897007542,
"tpw": 1.6260480654058747
},
"code": {
"chars": 600000,
"words": 115473,
"tokens": 165658,
"cpt": 3.621919858986587,
"tpw": 1.434603760186364
}
}
},
{
"name": "ALLaM-7B-Instruct",
"vocab": 64000,
"by_label": {
"arabic": {
"chars": 479808,
"words": 82964,
"tokens": 168111,
"cpt": 2.854114245944644,
"tpw": 2.0263126175208526
},
"english": {
"chars": 69308,
"words": 9805,
"tokens": 27522,
"cpt": 2.5182762880604606,
"tpw": 2.8069352371239162
},
"math": {
"chars": 518667,
"words": 91001,
"tokens": 172904,
"cpt": 2.9997397399713135,
"tpw": 1.9000230766694872
},
"code": {
"chars": 600000,
"words": 115473,
"tokens": 184611,
"cpt": 3.2500771893332465,
"tpw": 1.5987373671767426
}
}
},
{
"name": "google/gemma-4-31B-it",
"vocab": 262144,
"by_label": {
"arabic": {
"chars": 479808,
"words": 82964,
"tokens": 169379,
"cpt": 2.8327478613051205,
"tpw": 2.041596355045562
},
"english": {
"chars": 69308,
"words": 9805,
"tokens": 22580,
"cpt": 3.0694419840566876,
"tpw": 2.302906680265171
},
"math": {
"chars": 518667,
"words": 91001,
"tokens": 160000,
"cpt": 3.24166875,
"tpw": 1.7582224371160757
},
"code": {
"chars": 600000,
"words": 115473,
"tokens": 177333,
"cpt": 3.38346500651317,
"tpw": 1.5357096464108493
}
}
},
{
"name": "google/gemma-3-1b-pt",
"vocab": 262145,
"by_label": {
"arabic": {
"chars": 479808,
"words": 82964,
"tokens": 169379,
"cpt": 2.8327478613051205,
"tpw": 2.041596355045562
},
"english": {
"chars": 69308,
"words": 9805,
"tokens": 22580,
"cpt": 3.0694419840566876,
"tpw": 2.302906680265171
},
"math": {
"chars": 518667,
"words": 91001,
"tokens": 160000,
"cpt": 3.24166875,
"tpw": 1.7582224371160757
},
"code": {
"chars": 600000,
"words": 115473,
"tokens": 177301,
"cpt": 3.384075667931935,
"tpw": 1.535432525352247
}
}
},
{
"name": "google/gemma-2-2b",
"vocab": 256000,
"by_label": {
"arabic": {
"chars": 479808,
"words": 82964,
"tokens": 172625,
"cpt": 2.7794815351194786,
"tpw": 2.0807217588351574
},
"english": {
"chars": 69308,
"words": 9805,
"tokens": 22237,
"cpt": 3.1167873364212797,
"tpw": 2.267924528301887
},
"math": {
"chars": 518667,
"words": 91001,
"tokens": 158685,
"cpt": 3.268531997353247,
"tpw": 1.7437720464610278
},
"code": {
"chars": 600000,
"words": 115473,
"tokens": 177356,
"cpt": 3.3830262297300346,
"tpw": 1.5359088271717198
}
}
},
{
"name": "QCRI/Fanar-1-9B",
"vocab": 128256,
"by_label": {
"arabic": {
"chars": 479808,
"words": 82964,
"tokens": 172741,
"cpt": 2.777615042172964,
"tpw": 2.0821199556434116
},
"english": {
"chars": 69308,
"words": 9805,
"tokens": 22743,
"cpt": 3.047443169326826,
"tpw": 2.319530851606323
},
"math": {
"chars": 518667,
"words": 91001,
"tokens": 161011,
"cpt": 3.2213140717093864,
"tpw": 1.7693322051406029
},
"code": {
"chars": 600000,
"words": 115473,
"tokens": 179306,
"cpt": 3.3462349280001784,
"tpw": 1.5527958916803062
}
}
},
{
"name": "Qwen2.5-0.5B",
"vocab": 151665,
"by_label": {
"arabic": {
"chars": 479808,
"words": 82964,
"tokens": 185741,
"cpt": 2.5832099536451296,
"tpw": 2.2388144255339664
},
"english": {
"chars": 69308,
"words": 9805,
"tokens": 23714,
"cpt": 2.922661718815889,
"tpw": 2.4185619581845996
},
"math": {
"chars": 518667,
"words": 91001,
"tokens": 157198,
"cpt": 3.299450374686701,
"tpw": 1.7274315666860804
},
"code": {
"chars": 600000,
"words": 115473,
"tokens": 170867,
"cpt": 3.5115030989014846,
"tpw": 1.479713872506993
}
}
},
{
"name": "Hala-350M",
"vocab": 64400,
"by_label": {
"arabic": {
"chars": 479808,
"words": 82964,
"tokens": 216262,
"cpt": 2.218642202513618,
"tpw": 2.6066968805747073
},
"english": {
"chars": 69308,
"words": 9805,
"tokens": 21525,
"cpt": 3.219883855981417,
"tpw": 2.195308516063233
},
"math": {
"chars": 518667,
"words": 91001,
"tokens": 154027,
"cpt": 3.367377148162335,
"tpw": 1.6925857957604862
},
"code": {
"chars": 600000,
"words": 115473,
"tokens": 172555,
"cpt": 3.477152212338095,
"tpw": 1.4943320083482718
}
}
},
{
"name": "Kimi-K2.6",
"vocab": 163840,
"by_label": {
"arabic": {
"chars": 479808,
"words": 82964,
"tokens": 231367,
"cpt": 2.0737961766371176,
"tpw": 2.788763801166771
},
"english": {
"chars": 69308,
"words": 9805,
"tokens": 21401,
"cpt": 3.238540255128265,
"tpw": 2.182661907190209
},
"math": {
"chars": 518667,
"words": 91001,
"tokens": 147361,
"cpt": 3.5197033136311506,
"tpw": 1.6193338534741377
},
"code": {
"chars": 600000,
"words": 115473,
"tokens": 165268,
"cpt": 3.630466878040516,
"tpw": 1.4312263472846467
}
}
},
{
"name": "GPT-4 (cl100k_base)",
"vocab": 100277,
"by_label": {
"arabic": {
"chars": 479808,
"words": 82964,
"tokens": 335815,
"cpt": 1.428786683143993,
"tpw": 4.047719492792054
},
"english": {
"chars": 69308,
"words": 9805,
"tokens": 22607,
"cpt": 3.065776087052683,
"tpw": 2.3056603773584907
},
"math": {
"chars": 518667,
"words": 91001,
"tokens": 149086,
"cpt": 3.478978576123848,
"tpw": 1.6382896891242953
},
"code": {
"chars": 600000,
"words": 115473,
"tokens": 166345,
"cpt": 3.606961435570651,
"tpw": 1.440553202913235
}
}
},
{
"name": "Falcon-7B",
"vocab": 65024,
"by_label": {
"arabic": {
"chars": 479808,
"words": 82964,
"tokens": 484375,
"cpt": 0.9905713548387097,
"tpw": 5.838375681018273
},
"english": {
"chars": 69308,
"words": 9805,
"tokens": 25481,
"cpt": 2.71998744162317,
"tpw": 2.5987761346251914
},
"math": {
"chars": 518667,
"words": 91001,
"tokens": 166874,
"cpt": 3.1081354794635474,
"tpw": 1.833760068570675
},
"code": {
"chars": 600000,
"words": 115473,
"tokens": 186896,
"cpt": 3.2103415803441484,
"tpw": 1.6185255427675733
}
}
}
]
}