Urambazaji
AI BENCHY
Advertise here

AI BENCHY Compare

OpenAI: GPT-5.2 vs Qwen: Qwen3.6 27B

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

Kipimo GPT-5.2 GPT-5.2 medium Toleo: 2025-12-11 Qwen3.6 27B Qwen3.6 27B medium Toleo: 2026-04-20
Alama 7.4 6.6
Nafasi #57 #83
Uaminifu 10.0 9.9
Uthabiti 8.3 8.1
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 70.0% 58.3%
Majaribio yasiyo thabiti 4 5
Jumla ya uendeshaji 60 60
Gharama kwa matokeo 4.081 3.015
Jumla ya gharama $0.490 $0.272
Bei ya ingizo $1.750 / 1M $0.317 / 1M
Bei ya toleo $14.000 / 1M $3.200 / 1M
Tokeni za matokeo 2,754 13,007
Tokeni za hoja 28,303 105,697
Muda wa majibu (wastani) 16.44s 57.65s
Muda wa majibu (upeo) 77.80s 168.22s
Muda wa majibu (jumla) 213.77s 1153.04s

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-5.2 6.5 8.0 58.3% 1 7.81s 567 2,002
Qwen3.6 27B 8.3 10.0 75.0% 0 12.62s 582 4,311
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-5.2 10.0 10.0 100.0% 0 23.15s 490 8,269
Qwen3.6 27B 6.6 10.0 50.0% 0 165.39s 4,760 26,668
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-5.2 10.0 10.0 100.0% 0 14.06s 291 1,757
Qwen3.6 27B 7.0 3.7 66.7% 1 83.07s 2,088 14,689
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-5.2 10.0 10.0 100.0% 0 3.15s 234 420
Qwen3.6 27B 3.5 1.4 50.0% 2 37.30s 568 9,404
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-5.2 5.9 7.2 55.6% 1 77.80s 42 10,342
Qwen3.6 27B 2.9 7.2 11.1% 1 73.38s 3,510 20,352
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-5.2 3.7 9.7 0.0% 0 4.32s 162 269
Qwen3.6 27B 6.5 3.4 66.7% 1 39.53s 81 3,045
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-5.2 9.9 10.0 100.0% 0 3.12s 94 614
Qwen3.6 27B 10.0 10.0 100.0% 0 37.96s 346 6,548
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-5.2 7.6 7.3 77.8% 1 5.47s 609 938
Qwen3.6 27B 7.7 10.0 66.7% 0 60.21s 281 11,919
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-5.2 4.7 1.6 66.7% 1 10.30s 239 469
Qwen3.6 27B 10.0 10.0 100.0% 0 16.88s 390 2,954
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-5.2 3.0 10.0 0.0% 0 28.18s 26 3,223
Qwen3.6 27B 3.0 10.0 0.0% 0 80.99s 401 5,807

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho

DeepSeek V4 FlashhighInapatikana burevsGPT-5.2mediumQwen3.6 27BmediumvsGrok Build 0.1noneGemini 3.1 Flash LitenonevsQwen3.6 27BmediumGPT-5.5nonevsQwen3.6 27BmediumGemini 3.1 Flash LitelowvsGPT-5.2mediumDeepSeek V4 ProhighvsQwen3.6 27BmediumGemini 3.1 Flash Lite PreviewnonevsGPT-5.2mediumGemini 3.1 Flash LiteminimalvsQwen3.6 27BmediumGemma 4 31BnoneInapatikana burevsQwen3.6 27BmediumRing-2.6-1TnonevsGPT-5.2mediumGemini 3.1 Flash Lite PreviewlowvsGPT-5.2mediumGemini 3 Flash PreviewnonevsGPT-5.2medium