Urambazaji
AI BENCHY
Advertise here

Gemma 4 31B vs GPT-5.6 Luna (low)

GPT-5.6 Luna (low) inaongoza kwa average score: 6.2 vs 6.1. Gemma 4 31B ina gharama ya chini ya benchmark: $0.016 vs $0.051. GPT-5.6 Luna (low) ni ya haraka zaidi: 5.20s vs 5.41s, na pass rates 43.9% vs 54.5%.

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-08-20

Nafasi
#178
Jumla ya tokeni za matokeo
13,317
Muda wa majibu (wastani)
5.41s
Jumla ya gharama
$0.016
Nafasi
#167
Jumla ya tokeni za matokeo
26,286
Muda wa majibu (wastani)
5.20s
Jumla ya gharama
$0.051
Muundo unaopendekezwa Gemma 4 31B

Its score stays close to the best score here (6.1 vs 6.2), while costing about 3.2x less than GPT-5.6 Luna (low).

Ulinganisho wa kina

Kipimo Gemma 4 31B Gemma 4 31B none Toleo: 2026-04-02 Inapatikana bure GPT-5.6 Luna GPT-5.6 Luna low Toleo: 2026-07-09
Alama 6.1 6.2
Nafasi #178 #167
Uaminifu 10.0 10.0
Uthabiti 9.6 8.2
Majaribio 66/66 66/66
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 43.9% 54.5%
Majaribio yasiyo thabiti 1 5
Jumla ya uendeshaji 66 66
Gharama kwa matokeo 0.366 2.437
Jumla ya gharama $0.016 $0.051
Bei ya ingizo $0.090 / 1M $0.200 / 1M
Bei ya toleo $0.340 / 1M $1.200 / 1M
Jumla ya tokeni za ingizo 125,703 96,355
Tokeni za matokeo 13,317 8,213
Tokeni za hoja 0 18,073
Muda wa majibu (wastani) 5.41s 5.20s
Muda wa majibu (upeo) 29.95s 19.44s
Muda wa majibu (jumla) 108.12s 114.46s
Vigezo 30.7B ~400B jumla (~17B vinavyotumika)
Upatikanaji Chanzo huria Imefungwa

Onyesho la kizazi cha modeli

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#178 Gemma 4 31B

none
Gharama
$0.001
Muda
12.8s
Tokeni
795 tok

#167 GPT-5.6 Luna

low
Gharama
$0.011
Muda
10.2s
Tokeni
1,897 tok

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

Uandishi wa msimbo Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za ingizo Tokeni za matokeo Tokeni za hoja
Gemma 4 31B 5.5 10.0 33.3% 0 11.19s 8,381 735 0
GPT-5.6 Luna 5.5 10.0 33.3% 0 4.61s 7,302 557 3,535

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho