Urambazaji
AI BENCHY
Advertise here

AI BENCHY Compare

OpenAI: GPT-5 Mini vs StepFun: Step 3.5 Flash

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-06-01

Kipimo GPT-5 Mini GPT-5 Mini medium Toleo: 2025-08-07 Step 3.5 Flash Step 3.5 Flash medium Toleo: 2026-02-01
Alama 7.2 7.4
Nafasi #73 #61
Uaminifu 10.0 10.0
Uthabiti 9.1 9.1
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 61.7% 61.4%
Majaribio yasiyo thabiti 2 2
Jumla ya uendeshaji 60 57
Gharama kwa matokeo 1.348 0.133
Jumla ya gharama $0.149 $0.062
Bei ya ingizo $0.250 / 1M $0.090 / 1M
Bei ya toleo $2.000 / 1M $0.300 / 1M
Tokeni za matokeo 6,723 90,478
Tokeni za hoja 63,082 173,544
Muda wa majibu (wastani) 23.75s 43.20s
Muda wa majibu (upeo) 88.15s 170.45s
Muda wa majibu (jumla) 475.03s 561.54s

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
GPT-5 Mini 7.1 7.6 66.7% 1 13.86s 1,715 6,378
Step 3.5 Flash 10.0 10.0 100.0% 0 40.57s 20,391 24,176
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
GPT-5 Mini 10.0 10.0 100.0% 0 30.74s 580 12,544
Step 3.5 Flash 2.5 6.0 33.3% 1 62.83s 12,098 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
GPT-5 Mini 10.0 10.0 100.0% 0 88.15s 754 11,520
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
GPT-5 Mini 10.0 10.0 100.0% 0 12.58s 453 3,200
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
GPT-5 Mini 3.6 7.2 22.2% 1 44.63s 293 14,016
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
GPT-5 Mini 4.5 10.0 0.0% 0 13.50s 349 1,856
Step 3.5 Flash 5.5 10.0 0.0% 0 22.39s 240 3,506
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
GPT-5 Mini 10.0 10.0 100.0% 0 11.59s 310 3,968
Step 3.5 Flash 8.3 10.0 50.0% 0 4.78s 2,364 3,521
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
GPT-5 Mini 5.6 9.8 33.3% 0 15.20s 1,622 6,144
Step 3.5 Flash 5.3 10.0 33.3% 0 7.22s 5,630 10,861
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
GPT-5 Mini 10.0 10.0 100.0% 0 18.64s 487 1,600
Step 3.5 Flash 10.0 10.0 100.0% 0 11.91s 275 3,802
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
GPT-5 Mini 3.0 10.0 0.0% 0 9.99s 160 1,856
Step 3.5 Flash 3.0 10.0 0.0% 0 108.45s 2,354 10,372

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho

GPT-5 MinimediumvsStep 3.7 FlashhighGPT-5.3 ChatnonevsStep 3.5 FlashmediumGemini 3.1 Flash LitelowvsStep 3.5 FlashmediumRing-2.6-1TnonevsGPT-5 MinimediumGPT-5 MinimediumvsQwen3.6 Max PreviewnoneClaude Opus 4.8nonevsStep 3.5 FlashmediumGemini 3.1 Flash Lite PreviewnonevsStep 3.5 FlashmediumClaude Opus 4.8nonevsGPT-5 MinimediumRing-2.6-1TnonevsStep 3.5 FlashmediumClaude Sonnet 4.6nonevsGPT-5 MinimediumGPT-5 MinimediumvsStep 3.7 FlashlowGemini 3.1 Flash LitelowvsGPT-5 Minimedium