Urambazaji
Advertise here

Qwen3.8 27B (high) vs Inkling 2 Mini (local Q4) (low)

Qwen3.8 27B (high) inaongoza kwa average score: 8.7 vs 7.6. Inkling 2 Mini (local Q4) (low) ina gharama ya chini ya benchmark: ~$0.292 vs ~$0.298. Inkling 2 Mini (local Q4) (low) ni ya haraka zaidi: 153.99s vs 166.34s, na pass rates 78.3% vs 66.7%.

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-11-22

Modeli zilizolinganishwa

Nafasi
#104
Jumla ya tokeni za matokeo
677,080
Muda wa majibu (wastani)
166.34s
Jumla ya gharama
~$0.298
Nafasi
#202
Jumla ya tokeni za matokeo
129,600
Muda wa majibu (wastani)
153.99s
Jumla ya gharama
~$0.292
Muundo unaopendekezwa Qwen3.8 27B (high)

Ina alama ya juu zaidi katika ulinganisho huu (8.7) na uwiano bora zaidi wa gharama na muda wa kujibu kati ya modeli 2.

Ulinganisho wa kina

Kipimo Qwen3.8 27B Qwen3.8 27B high Toleo: 2026-08-14 Inapatikana bure Inkling 2 Mini (local Q4) Inkling 2 Mini (local Q4) low Toleo: 2026-11-20
Alama 8.7 7.6
Nafasi #104 #202
Uaminifu 9.7 9.7
Uthabiti 9.2 9.6
Majaribio 69/69 69/69
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 78.3% 66.7%
Majaribio yasiyo thabiti 2 1
Jumla ya uendeshaji 69 69
Gharama kwa matokeo ~1.751 ~1.946
Jumla ya gharama ~$0.298 ~$0.292
Bei ya ingizo Haipo Haipo
Bei ya toleo Haipo Haipo
Bei ya kusoma akiba Haipo Haipo
Bei ya kuandika akiba Haipo Haipo
Jumla ya tokeni za ingizo 348,967 312,366
Tokeni za matokeo 1,005 1,631
Tokeni za hoja 676,075 127,969
Muda wa majibu (wastani) 166.34s 153.99s
Muda wa majibu (upeo) 640.85s 1963.67s
Muda wa majibu (jumla) 3825.81s 3541.85s
Vigezo 27.3B 26.4B jumla (3.4B vinavyotumika)
Upatikanaji Uzani unapatikana Chanzo huria

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.

#104 Qwen3.8 27B

high
Gharama
~$0.008
Muda
270.1s
Tokeni
18,963 tok

#202 Thinking Machines: Inkling 2 Mini (local Q4)

low
Gharama
~$0.003
Muda
85.5s
Tokeni
2,977 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
Qwen3.8 27B 8.1 7.0 88.9% 1 248.62s 8,235 346 143,335
Inkling 2 Mini (local Q4) 5.3 7.2 44.4% 1 831.97s 5,668 524 34,490

Badilisha jozi ya ulinganisho

GPT-5.2mediumvsQwen3.8 27BhighInapatikana bureQwen3.8 27BhighInapatikana burevsMiMo-V2.6-PromediumSeed 2.1 TurbomediumvsQwen3.8 27BhighInapatikana bureGPT-6 SollowvsQwen3.8 27BhighInapatikana bureQwen3.8 27BhighInapatikana burevsInkling 2 Mini (local Q4)minimalParticle-1xhighvsQwen3.8 27BhighInapatikana bureMuse EmberlowvsQwen3.8 27BhighInapatikana bureMuse EmbermaxvsQwen3.8 27BhighInapatikana bureQwen3.8 Flash NextmediumvsInkling 2 Mini (local Q4)lowMuse WonderxhighvsInkling 2 Mini (local Q4)lowDeepSeek V4.1 FlashmaxvsQwen3.8 27BhighInapatikana bureMuse Spark 1.2lowvsQwen3.8 27BhighInapatikana bure