Urambazaji
Advertise here

Trinity Large Thinking (high) vs ERNIE-Light-DT-1.0

Trinity Large Thinking (high) inaongoza kwa average score: 5.7 vs 5.6. ERNIE-Light-DT-1.0 ina gharama ya chini ya benchmark: $0.524 vs $0.794. ERNIE-Light-DT-1.0 ni ya haraka zaidi: 24.16s vs 74.52s, na pass rates 42.0% vs 36.2%.

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-11-13

Modeli zilizolinganishwa

Nafasi
#345
Jumla ya tokeni za matokeo
717,762
Muda wa majibu (wastani)
74.52s
Jumla ya gharama
$0.794
Nafasi
#357
Jumla ya tokeni za matokeo
76,149
Muda wa majibu (wastani)
24.16s
Jumla ya gharama
$0.524
Muundo unaopendekezwa ERNIE-Light-DT-1.0

Its score stays close to the best score here (5.6 vs 5.7), while costing about 1.5x less than Trinity Large Thinking (high).

Ulinganisho wa kina

Kipimo Trinity Large Thinking Trinity Large Thinking high Toleo: 2026-07-28 ERNIE-Light-DT-1.0 ERNIE-Light-DT-1.0 none Toleo: 2026-11-12
Alama 5.7 5.6
Nafasi #345 #357
Uaminifu 10.0 9.2
Uthabiti 7.3 9.7
Majaribio 69/69 69/69
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 42.0% 36.2%
Majaribio yasiyo thabiti 8 1
Jumla ya uendeshaji 69 69
Gharama kwa matokeo 11.289 6.545
Jumla ya gharama $0.794 $0.524
Bei ya ingizo $0.250 / 1M $1.130 / 1M
Bei ya toleo $0.800 / 1M $3.941 / 1M
Bei ya kusoma akiba $0.060 / 1M $0.113 / 1M
Bei ya kuandika akiba Haipo Haipo
Jumla ya tokeni za ingizo 283,116 197,790
Tokeni za matokeo 277,920 76,149
Tokeni za hoja 665,124 0
Muda wa majibu (wastani) 74.52s 24.16s
Muda wa majibu (upeo) 510.21s 449.96s
Muda wa majibu (jumla) 1713.90s 555.78s
Vigezo 398B jumla (13B vinavyotumika) ~320B jumla (~18B vinavyotumika)
Upatikanaji Uzani unapatikana 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.

#345 Trinity Large Thinking

high
Gharama
$0.028
Muda
130.1s
Tokeni
34,387 tok

#357 ERNIE-Light-DT-1.0

none
Gharama
$0.009
Muda
14.9s
Tokeni
2,144 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
Trinity Large Thinking 3.7 4.7 33.3% 2 245.04s 7,204 83,616 266,836
ERNIE-Light-DT-1.0 4.3 7.4 11.1% 1 151.72s 6,005 68,639 0

Badilisha jozi ya ulinganisho