Urambazaji
AI BENCHY
Advertise here

AI BENCHY Compare

Google: Gemini 3.5 Flash vs StepFun: Step 3.5 Flash

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-05-22

Kipimo Gemini 3.5 Flash Gemini 3.5 Flash low Toleo: 2026-05-19 Step 3.5 Flash Step 3.5 Flash none Toleo: 2026-02-01
Alama 9.3 7.8
Nafasi #3 #32
Uaminifu 10.0 10.0
Uthabiti 10.0 10.0
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 90.0% 66.7%
Majaribio yasiyo thabiti 0 0
Jumla ya uendeshaji 60 36
Gharama kwa matokeo 1.582 0.328
Jumla ya gharama $0.285 $0.020
Bei ya ingizo $1.500 / 1M $0.090 / 1M
Bei ya toleo $9.000 / 1M $0.300 / 1M
Tokeni za matokeo 2,027 64,795
Tokeni za hoja 23,938 0
Muda wa majibu (wastani) 2.98s 39.03s
Muda wa majibu (upeo) 6.44s 114.12s
Muda wa majibu (jumla) 59.59s 312.26s

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
Gemini 3.5 Flash 10.0 10.0 100.0% 0 2.52s 209 2,536
Step 3.5 Flash 10.0 10.0 100.0% 0 34.99s 21,766 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
Gemini 3.5 Flash 6.8 10.0 50.0% 0 5.54s 452 6,839
Step 3.5 Flash 3.0 10.0 0.0% 0 0ms 0 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
Gemini 3.5 Flash 10.0 10.0 100.0% 0 6.44s 351 3,050
Step 3.5 Flash 0.0 0.0 0.0% 0 0ms 0 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
Gemini 3.5 Flash 10.0 10.0 100.0% 0 1.81s 279 1,164
Step 3.5 Flash 0.0 0.0 0.0% 0 0ms 0 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
Gemini 3.5 Flash 7.7 10.0 66.7% 0 3.39s 12 4,538
Step 3.5 Flash 10.0 10.0 100.0% 0 34.54s 7,389 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
Gemini 3.5 Flash 10.0 10.0 100.0% 0 2.27s 119 916
Step 3.5 Flash 4.0 10.0 0.0% 0 14.37s 2,451 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
Gemini 3.5 Flash 9.9 10.0 100.0% 0 1.86s 71 1,652
Step 3.5 Flash 10.0 10.0 100.0% 0 9.30s 1,427 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
Gemini 3.5 Flash 10.0 10.0 100.0% 0 2.35s 288 2,150
Step 3.5 Flash - - - - - - - -
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
Gemini 3.5 Flash 10.0 10.0 100.0% 0 3.27s 234 403
Step 3.5 Flash 0.0 0.0 0.0% 0 0ms 0 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
Gemini 3.5 Flash 10.0 10.0 100.0% 0 1.88s 12 690
Step 3.5 Flash 3.0 10.0 0.0% 0 114.12s 31,762 0

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho

Gemini 3.5 FlashlowvsQwen3.7 MaxmediumClaude Opus 4.7mediumvsGemini 3.5 FlashlowGemini 3.5 FlashlowvsGPT-5.5mediumGemini 3.5 FlashlowvsQwen3.6 Max PreviewmediumGemini 3.5 FlashlowvsGPT-5.3-CodexmediumGemini 3.5 FlashlowvsGLM 5mediumGemini 3.5 FlashlowvsQwen3.5 Plus 2026-02-15mediumSeed-2.0-LitemediumvsGemini 3.5 FlashlowGemini 3.5 FlashlowvsQwen3.5-27BmediumGemini 3.5 FlashlowvsQwen3.7 MaxnoneGemini 3.5 FlashlowvsGPT-5.4mediumGemini 3.5 FlashlowvsGLM 5 Turbomedium