Urambazaji
AI BENCHY
Advertise here

AI BENCHY Compare

Modeli zilizolinganishwa

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

Kipimo Gemini 3.1 Flash Lite Preview Gemini 3.1 Flash Lite Preview high Toleo: 2026-03-03 Gemini 3.1 Flash Lite Preview Gemini 3.1 Flash Lite Preview medium Toleo: 2026-03-03 GPT-5.3-Codex GPT-5.3-Codex medium Toleo: 2026-02-05
Alama 8.6 7.7 8.3
Nafasi #13 #34 #15
Uaminifu Haipo 10.0 10.0
Uthabiti 10.0 10.0 8.4
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 81.3% 65.0% 81.7%
Majaribio yasiyo thabiti 0 0 4
Jumla ya uendeshaji 48 60 60
Gharama kwa matokeo 17.763 0.481 4.891
Jumla ya gharama $2.310 $0.063 $0.685
Bei ya ingizo $0.250 / 1M $0.250 / 1M $1.750 / 1M
Bei ya toleo $1.500 / 1M $1.500 / 1M $14.000 / 1M
Tokeni za matokeo 1,283 2,204 2,332
Tokeni za hoja 1,533,310 33,657 42,616
Muda wa majibu (wastani) 68.83s 3.68s 15.97s
Muda wa majibu (upeo) 280.52s 14.93s 100.93s
Muda wa majibu (jumla) 1101.32s 73.60s 319.30s

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 3.1 Flash Lite Preview 10.0 10.0 100.0% 0 43.87s 144 193,077
Gemini 3.1 Flash Lite Preview 9.1 10.0 75.0% 0 2.33s 570 4,305
GPT-5.3-Codex 8.7 7.9 91.7% 1 4.16s 240 1,722
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 3.1 Flash Lite Preview 10.0 10.0 100.0% 0 280.52s 335 380,440
Gemini 3.1 Flash Lite Preview 10.0 10.0 100.0% 0 14.93s 327 7,347
GPT-5.3-Codex 10.0 10.0 100.0% 0 19.56s 364 2,731
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 3.1 Flash Lite Preview 10.0 10.0 100.0% 0 7.16s 279 6,186
Gemini 3.1 Flash Lite Preview 10.0 10.0 100.0% 0 2.29s 279 2,952
GPT-5.3-Codex 10.0 10.0 100.0% 0 3.07s 234 728
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 3.1 Flash Lite Preview 5.3 10.0 33.3% 0 127.58s 18 566,202
Gemini 3.1 Flash Lite Preview 3.0 10.0 0.0% 0 4.21s 18 5,325
GPT-5.3-Codex 5.9 7.2 55.6% 1 64.31s 64 25,308
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 3.1 Flash Lite Preview 10.0 10.0 100.0% 0 5.25s 117 3,915
Gemini 3.1 Flash Lite Preview 10.0 10.0 100.0% 0 3.16s 96 1,488
GPT-5.3-Codex 4.6 10.0 0.0% 0 4.87s 187 331
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 3.1 Flash Lite Preview 9.8 10.0 100.0% 0 70.07s 69 190,053
Gemini 3.1 Flash Lite Preview 10.0 10.0 100.0% 0 1.91s 72 2,121
GPT-5.3-Codex 10.0 10.0 100.0% 0 3.04s 93 693
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 3.1 Flash Lite Preview 7.7 10.0 66.7% 0 46.33s 87 190,953
Gemini 3.1 Flash Lite Preview 7.7 10.0 66.7% 0 3.58s 141 1,896
GPT-5.3-Codex 9.0 7.9 88.9% 1 5.12s 352 1,644
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 3.1 Flash Lite Preview 10.0 10.0 100.0% 0 7.73s 234 2,484
Gemini 3.1 Flash Lite Preview 10.0 10.0 100.0% 0 3.80s 234 912
GPT-5.3-Codex 10.0 10.0 100.0% 0 6.37s 254 492
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 3.1 Flash Lite Preview - - - - - - - -
Gemini 3.1 Flash Lite Preview 6.8 10.0 50.0% 0 3.98s 455 5,510
GPT-5.3-Codex 10.0 10.0 100.0% 0 18.45s 514 7,266
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 3.1 Flash Lite Preview - - - - - - - -
Gemini 3.1 Flash Lite Preview 3.0 10.0 0.0% 0 2.68s 12 1,801
GPT-5.3-Codex 2.8 1.6 33.3% 1 14.43s 30 1,701

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho