Urambazaji
AI BENCHY
AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com

AI BENCHY Compare

DeepSeek: DeepSeek V4 Flash vs StepFun: Step 3.5 Flash

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-04-24

Kipimo DeepSeek V4 Flash DeepSeek V4 Flash high Toleo: 2026-04-24 Step 3.5 Flash Step 3.5 Flash medium Toleo: 2026-02-01
Alama 7.8 7.9
Nafasi #35 #34
Uthabiti 7.8 9.1
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 79.6% 70.6%
Majaribio yasiyo thabiti 5 2
Jumla ya uendeshaji 52 49
Gharama kwa matokeo 0.189 0.000
Jumla ya gharama $0.021 $0.000
Bei ya ingizo $0.140 / 1M $0.100 / 1M
Bei ya toleo $0.280 / 1M $0.300 / 1M
Tokeni za matokeo 1,757 71,904
Tokeni za hoja 55,907 155,607
Muda wa majibu (wastani) 47.47s 26.78s
Muda wa majibu (upeo) 255.28s 170.45s
Muda wa majibu (jumla) 854.45s 294.58s

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
DeepSeek V4 Flash 8.3 10.0 75.0% 0 28.51s 140 7,770
Step 3.5 Flash 10.0 10.0 100.0% 0 13.56s 14,376 17,668
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
DeepSeek V4 Flash 10.0 10.0 100.0% 0 62.48s 369 9,361
Step 3.5 Flash - - - - - - - -
Mchanganyiko Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
DeepSeek V4 Flash 10.0 10.0 100.0% 0 76.57s 465 7,347
Step 3.5 Flash 10.0 10.0 100.0% 0 29.57s 1,176 12,984
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
DeepSeek V4 Flash 10.0 10.0 100.0% 0 28.03s 201 1,179
Step 3.5 Flash 10.0 10.0 100.0% 0 15.01s 600 13,886
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
DeepSeek V4 Flash 4.1 4.4 44.5% 2 112.69s 19 24,857
Step 3.5 Flash 5.3 7.2 44.4% 1 170.45s 45,350 90,436
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
DeepSeek V4 Flash 6.1 3.1 66.7% 1 25.15s 79 632
Step 3.5 Flash 5.5 10.0 0.0% 0 6.54s 2,214 2,584
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
DeepSeek V4 Flash 10.0 10.0 100.0% 0 15.36s 63 1,622
Step 3.5 Flash 8.5 6.8 83.3% 1 4.98s 2,284 3,412
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
DeepSeek V4 Flash 6.4 4.5 77.8% 2 25.53s 193 2,597
Step 3.5 Flash 5.3 10.0 33.3% 0 7.72s 5,629 10,835
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
DeepSeek V4 Flash 10.0 10.0 100.0% 0 74.73s 228 542
Step 3.5 Flash 10.0 10.0 100.0% 0 11.91s 275 3,802

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho