Urambazaji
AI BENCHY
Advertise here

AI BENCHY Compare

Google: Gemma 4 26B A4B vs StepFun: Step 3.7 Flash

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

Kipimo Gemma 4 26B A4B Gemma 4 26B A4B medium Toleo: 2026-04-03 Inapatikana bure Step 3.7 Flash Step 3.7 Flash low Toleo: 2026-05-29
Alama 7.8 7.4
Nafasi #34 #60
Uaminifu 10.0 10.0
Uthabiti 9.2 8.7
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 73.3% 68.3%
Majaribio yasiyo thabiti 2 3
Jumla ya uendeshaji 60 60
Gharama kwa matokeo 0.317 2.796
Jumla ya gharama $0.045 $0.336
Bei ya ingizo $0.060 / 1M $0.200 / 1M
Bei ya toleo $0.330 / 1M $1.150 / 1M
Tokeni za matokeo 28,000 285,209
Tokeni za hoja 82,045 0
Muda wa majibu (wastani) 50.92s 16.06s
Muda wa majibu (upeo) 369.32s 124.75s
Muda wa majibu (jumla) 967.47s 321.11s

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
Gemma 4 26B A4B 10.0 10.0 100.0% 0 6.20s 1,142 3,045
Step 3.7 Flash 8.7 7.9 91.7% 1 4.02s 10,896 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
Gemma 4 26B A4B 2.9 10.0 0.0% 0 258.40s 14,838 26,122
Step 3.7 Flash 10.0 10.0 100.0% 0 9.43s 14,569 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
Gemma 4 26B A4B 9.6 10.0 100.0% 0 73.55s 5,415 13,112
Step 3.7 Flash 10.0 10.0 100.0% 0 7.98s 6,426 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
Gemma 4 26B A4B 10.0 10.0 100.0% 0 16.51s 1,567 2,827
Step 3.7 Flash 7.3 5.8 83.3% 1 2.29s 2,667 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
Gemma 4 26B A4B 2.9 4.4 22.2% 2 23.62s 2,469 7,105
Step 3.7 Flash 5.3 7.2 44.4% 1 43.31s 104,487 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
Gemma 4 26B A4B 10.0 10.0 100.0% 0 29.76s 25 5,075
Step 3.7 Flash 3.4 9.3 0.0% 0 7.00s 4,604 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
Gemma 4 26B A4B 10.0 10.0 100.0% 0 17.54s 887 4,470
Step 3.7 Flash 9.8 10.0 100.0% 0 1.58s 1,857 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
Gemma 4 26B A4B 10.0 10.0 100.0% 0 5.79s 410 2,128
Step 3.7 Flash 5.5 9.9 33.3% 0 1.84s 3,564 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
Gemma 4 26B A4B 10.0 10.0 100.0% 0 9.01s 450 1,256
Step 3.7 Flash 10.0 10.0 100.0% 0 3.25s 1,360 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
Gemma 4 26B A4B 3.0 10.0 0.0% 0 180.87s 797 16,905
Step 3.7 Flash 3.0 10.0 0.0% 0 124.75s 134,779 0

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho

Kimi K2.6mediumInapatikana burevsStep 3.7 FlashlowStep 3.7 FlashlowvsMiMo-V2.5mediumGemma 4 26B A4BmediumInapatikana burevsGPT-5.2 ChatnoneGPT-5.3 ChatnonevsStep 3.7 FlashlowStep 3.7 FlashlowvsGLM 5V TurbomediumStep 3.7 FlashlowvsGLM 5.1mediumGPT-5.2mediumvsStep 3.7 FlashlowGPT-5.4 MinimediumvsStep 3.7 FlashlowGemma 4 26B A4BmediumInapatikana burevsQwen3.7 MaxnoneGemini 3.1 Flash Lite PreviewnonevsStep 3.7 FlashlowClaude Opus 4.8nonevsStep 3.7 FlashlowDeepSeek V3.2mediumvsStep 3.7 Flashlow