Urambazaji
AI BENCHY
Your ad here

AI BENCHY Compare

Modeli zilizolinganishwa

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-03-12

Kipimo GPT-5.2 GPT-5.2 medium Toleo: 2025-12-11 GPT-5.3 Chat GPT-5.3 Chat none Toleo: 2026-03-03 GPT-5.4 GPT-5.4 none Toleo: 2026-03-05
Nafasi #29 #20 #51
Wastani wa alama 6.5 7.3 4.5
Uthabiti 7.9 8.5 8.9
Gharama kwa matokeo 3.125 3.163 1.562
Jumla ya gharama $0.313 $0.317 $0.094
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 75.0% 70.8% 41.7%
Majaribio yasiyo thabiti 4 3 2
Jumla ya uendeshaji 48 48 48
Tokeni za matokeo 2,220 19,272 1,819
Tokeni za hoja 16,811 0 0
Muda wa majibu (wastani) 15.33s 5.96s 1.48s
Muda wa majibu (upeo) 77.80s 18.33s 2.89s
Muda wa majibu (jumla) 138.01s 95.30s 23.64s

Modeli bora kwa alama

Alama dhidi ya gharama ya jumla

Muda wa majibu (wastani)

Wastani wa alama vs Muda wa majibu (wastani)

Jumla ya tokeni za matokeo

Wastani wa 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 7.0 7.3 77.8% 1 14.34s 549 2,002
GPT-5.3 Chat 7.3 7.5 77.8% 1 4.72s 3,091 0
GPT-5.4 10.0 7.3 11.1% 1 1.41s 388 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-5.2 10.0 10.0 100.0% 0 14.06s 291 1,757
GPT-5.3 Chat 10.0 10.0 100.0% 0 11.96s 2,614 0
GPT-5.4 10.0 10.0 0.0% 0 2.89s 291 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
GPT-5.2 9.9 10.0 100.0% 0 3.15s 234 420
GPT-5.3 Chat 9.9 10.0 100.0% 0 2.21s 942 0
GPT-5.4 9.9 10.0 100.0% 0 1.04s 222 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
GPT-5.2 4.0 7.2 55.6% 1 77.80s 42 10,342
GPT-5.3 Chat 10.0 4.4 33.3% 2 13.01s 8,264 0
GPT-5.4 4.0 7.2 44.4% 1 1.07s 50 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
GPT-5.2 10.0 9.7 0.0% 0 4.32s 162 269
GPT-5.3 Chat 4.0 10.0 0.0% 0 1.99s 319 0
GPT-5.4 3.0 9.9 0.0% 0 1.78s 184 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
GPT-5.2 9.5 10.0 100.0% 0 3.12s 94 614
GPT-5.3 Chat 9.0 10.0 50.0% 0 3.29s 1,455 0
GPT-5.4 5.5 10.0 50.0% 0 1.07s 81 0
Puzzle Solving 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 7.0 7.3 77.8% 1 5.47s 609 938
GPT-5.3 Chat 10.0 10.0 100.0% 0 2.93s 1,726 0
GPT-5.4 4.0 9.8 33.3% 0 1.52s 357 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
GPT-5.2 10.0 1.6 66.7% 1 10.30s 239 469
GPT-5.3 Chat 10.0 10.0 100.0% 0 8.36s 861 0
GPT-5.4 10.0 10.0 100.0% 0 2.75s 246 0

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho

DeepSeek V3.2mediumvsGPT-5.3 ChatnoneGemini 3.1 Flash Lite PreviewlowvsGPT-5.3 ChatnoneGPT-5.3 ChatnonevsMiMo-V2-FlashmediumGemini 2.5 FlashmediumvsGPT-5.3 ChatnoneGPT-5.3 ChatnonevsGLM 5mediumGPT-5.3 ChatnonevsStep 3.5 FlashmediumInapatikana bureMiniMax M2.5mediumvsGPT-5.4noneGemini 3.1 Flash Lite PreviewmediumvsGPT-5.3 ChatnoneClaude Sonnet 4.6nonevsGPT-5.2mediumGPT-5.2mediumvsQwen3.5 Plus 2026-02-15noneGPT-5.3 ChatnonevsGrok 4.20 BetamediumSeed-2.0-MinimediumvsGPT-5.3 Chatnone