Urambazaji
Advertise here

Mercury 2.5 Preview (low) vs GPT-4o-mini (default)

Mercury 2.5 Preview (low) inaongoza kwa average score: 5.0 vs 5.0. Mercury 2.5 Preview (low) ina gharama ya chini ya benchmark: $0.015 vs $0.024. GPT-4o-mini (default) ni ya haraka zaidi: 4.16s vs 4.92s, na pass rates 44.9% vs 21.7%.

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-10-16

Modeli zilizolinganishwa

Nafasi
#336
Jumla ya tokeni za matokeo
36,870
Muda wa majibu (wastani)
4.92s
Jumla ya gharama
$0.015
Nafasi
#339
Jumla ya tokeni za matokeo
3,627
Muda wa majibu (wastani)
4.16s
Jumla ya gharama
$0.024
Muundo unaopendekezwa Mercury 2.5 Preview (low)

It has the best score here (5.0), while costing about 1.6x less than GPT-4o-mini (default).

Ulinganisho wa kina

Kipimo Mercury 2.5 Preview Mercury 2.5 Preview low Toleo: 2026-09-02 GPT-4o-mini GPT-4o-mini default Toleo: 2024-07-18
Alama 5.0 5.0
Nafasi #336 #339
Uaminifu 9.9 10.0
Uthabiti 7.1 9.9
Majaribio 69/69 69/69
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 44.9% 21.7%
Majaribio yasiyo thabiti 8 0
Jumla ya uendeshaji 69 69
Gharama kwa matokeo 0.244 0.480
Jumla ya gharama $0.015 $0.024
Bei ya ingizo $0.040 / 1M $0.150 / 1M
Bei ya toleo $0.150 / 1M $0.600 / 1M
Bei ya kusoma akiba Haipo $0.075 / 1M
Bei ya kuandika akiba Haipo Haipo
Jumla ya tokeni za ingizo 235,438 145,180
Tokeni za matokeo 8,136 3,627
Tokeni za hoja 28,734 0
Muda wa majibu (wastani) 4.92s 4.16s
Muda wa majibu (upeo) 84.47s 39.99s
Muda wa majibu (jumla) 113.24s 70.70s
Vigezo ~100B ~8B
Upatikanaji Imefungwa Imefungwa

Bei za akiba zinahusu tokeni za ingizo. Kusoma hutumia tena maelekezo yaliyohifadhiwa; kuandika huyahifadhi na kunaweza kuongeza gharama. Tokeni za matokeo hutumia bei ya matokeo.

Onyesho la kizazi cha modeli

Hamster playing table tennis

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

#336 Mercury 2.5 Preview

low
Gharama
$0.001
Muda
1.5s
Tokeni
1,169 tok

#339 GPT-4o-mini

default
Gharama
$0.001
Muda
6.6s
Tokeni
742 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
Mercury 2.5 Preview 5.5 10.0 33.3% 0 972ms 7,794 695 2,263
GPT-4o-mini 3.2 9.6 0.0% 0 1.63s 7,314 367 0

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho

KAT Coder AIR V2.5lowvsGPT-4o-minidefaultMiniMax M2.7mediumvsGPT-4o-minidefaultMercury 2.5 PreviewlowvsLaguna S 2.1mediumInapatikana bureMercury 2.5 PreviewlowvsMiniMax M2.7mediumDots 3 Note PreviewdefaultInapatikana burevsMercury 2.5 PreviewlowGPT-4o-minidefaultvsInkling SmallnoneInapatikana bureApodex 1.1 MinidefaultInapatikana burevsMercury 2.5 PreviewlowGPT-4o-minidefaultvsLaguna S 2.1highInapatikana bureGPT-4o-minidefaultvsLaguna S 2.1mediumInapatikana bureMercury 2.5 PreviewlowvsMiMo-V2.5-PrononeMercury 2.5 PreviewlowvsKAT Coder AIR V2.5mediumGPT-4o-minidefaultvsMiMo-V2.5none