Urambazaji
AI BENCHY
Advertise here

AI BENCHY Compare

ByteDance Seed: Seed-2.0-Lite vs StepFun: Step 3.7 Flash

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-05-29

Kipimo Seed-2.0-Lite Seed-2.0-Lite medium Toleo: 2026-02-14 Step 3.7 Flash Step 3.7 Flash medium Toleo: 2026-05-29
Alama 8.1 7.9
Nafasi #24 #32
Uaminifu 10.0 9.9
Uthabiti 8.9 9.2
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 75.0% 71.7%
Majaribio yasiyo thabiti 3 2
Jumla ya uendeshaji 60 58
Gharama kwa matokeo 1.166 2.663
Jumla ya gharama $0.152 $0.347
Bei ya ingizo $0.250 / 1M $0.200 / 1M
Bei ya toleo $2.000 / 1M $1.150 / 1M
Tokeni za matokeo 3,224 294,481
Tokeni za hoja 67,040 0
Muda wa majibu (wastani) 36.67s 18.32s
Muda wa majibu (upeo) 168.71s 113.98s
Muda wa majibu (jumla) 733.46s 366.45s

Modeli bora kwa alama

Alama dhidi ya gharama ya jumla

Muda wa majibu (wastani)

Alama vs Muda wa majibu (wastani)

Jumla ya tokeni za matokeo

Alama vs Jumla ya tokeni za matokeo

Mgawanyo wa kategoria

Mbinu za kupinga AI Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
Seed-2.0-Lite 8.3 10.0 75.0% 0 17.99s 996 7,142
Step 3.7 Flash 8.7 7.9 91.7% 1 9.65s 32,185 0
Uandishi wa msimbo Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
Seed-2.0-Lite 7.0 9.7 50.0% 0 107.65s 452 20,524
Step 3.7 Flash 8.2 6.7 83.3% 1 10.64s 19,320 0
Mchanganyiko Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
Seed-2.0-Lite 10.0 10.0 100.0% 0 37.67s 506 4,299
Step 3.7 Flash 10.0 10.0 100.0% 0 9.06s 7,106 0
Uchanganuzi na uchimbaji wa data Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
Seed-2.0-Lite 10.0 10.0 100.0% 0 9.07s 246 1,742
Step 3.7 Flash 10.0 10.0 100.0% 0 2.75s 3,020 0
Mahususi kwa domeni Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
Seed-2.0-Lite 5.9 7.2 55.6% 1 88.74s 15 23,897
Step 3.7 Flash 7.7 10.0 66.7% 0 48.27s 70,347 0
Akili ya jumla Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
Seed-2.0-Lite 6.7 3.6 66.7% 1 18.25s 304 1,620
Step 3.7 Flash 4.0 10.0 0.0% 0 6.85s 3,987 0
Ufuataji wa maagizo Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
Seed-2.0-Lite 10.0 10.0 100.0% 0 7.26s 71 1,480
Step 3.7 Flash 9.8 10.0 100.0% 0 1.83s 2,166 0
Utatuzi wa mafumbo Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
Seed-2.0-Lite 9.0 7.9 88.9% 1 10.23s 403 3,285
Step 3.7 Flash 5.7 9.9 33.3% 0 6.19s 15,071 0
Mwito wa zana Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
Seed-2.0-Lite 10.0 10.0 100.0% 0 12.38s 222 1,011
Step 3.7 Flash 10.0 10.0 100.0% 0 4.16s 2,115 0
Maarifa ya jumla Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
Seed-2.0-Lite 3.0 10.0 0.0% 0 48.32s 9 2,040
Step 3.7 Flash 3.0 10.0 0.0% 0 113.98s 139,164 0

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho