Urambazaji
AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com

Modeli zilizolinganishwa

Ulinganisho wa benchmark Kimi K2.6 (medium) vs Kimi K2.5 (medium) vs GLM 5 (medium) vs Claude Opus 4.7 (medium): Claude Opus 4.7 (medium) inaongoza kwenye Alama kwa 8.1. Kimi K2.6 (medium) inaongoza kwenye Uaminifu kwa 10.0. GLM 5 (medium) ina Jumla ya gharama ya chini zaidi kwa $0.479. Claude Opus 4.7 (medium) ndiyo ya haraka zaidi kwa 14.12s.

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-10-26

Modeli zilizolinganishwa

Nafasi
#210
Jumla ya tokeni za matokeo
344,502
Muda wa majibu (wastani)
121.25s
Jumla ya gharama
$1.594
Nafasi
#253
Jumla ya tokeni za matokeo
209,217
Muda wa majibu (wastani)
125.76s
Jumla ya gharama
$0.841
Nafasi
#184
Jumla ya tokeni za matokeo
120,942
Muda wa majibu (wastani)
39.05s
Jumla ya gharama
$0.479
Nafasi
#116
Jumla ya tokeni za matokeo
57,978
Muda wa majibu (wastani)
14.12s
Jumla ya gharama
$3.636
Muundo unaopendekezwa Claude Opus 4.7 (medium)

It has the best score here (8.1), while responding about 6.8x faster than miundo mingine katika ulinganisho huu.

Ulinganisho wa kina

Kipimo Kimi K2.6 Kimi K2.6 medium Toleo: 2026-04-20 Kimi K2.5 Kimi K2.5 medium Toleo: 2026-01-27 GLM 5 GLM 5 medium Toleo: 2026-02-12 Claude Opus 4.7 Claude Opus 4.7 medium Toleo: 2026-04-16
Alama 6.8 6.4 7.2 8.1
Nafasi #210 #253 #184 #116
Uaminifu 10.0 9.6 10.0 10.0
Uthabiti 8.4 7.1 7.9 9.3
Majaribio 69/69 69/69 66/69 69/69
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 60.9% 60.9% 76.8% 81.2%
Majaribio yasiyo thabiti 4 8 5 2
Jumla ya uendeshaji 69 69 66 69
Gharama kwa matokeo 12.282 6.085 2.552 20.200
Jumla ya gharama $1.594 $0.841 $0.479 $3.636
Bei ya ingizo $0.950 / 1M $0.450 / 1M $0.600 / 1M $5.000 / 1M
Bei ya toleo $4.000 / 1M $2.250 / 1M $1.920 / 1M $25.000 / 1M
Bei ya kusoma akiba $0.160 / 1M $0.070 / 1M $0.120 / 1M $0.500 / 1M
Bei ya kuandika akiba Haipo Haipo Haipo $6.250 / 1M
Jumla ya tokeni za ingizo 226,880 292,271 212,440 437,293
Tokeni za matokeo 65,346 55,025 22,922 29,102
Tokeni za hoja 331,325 186,071 115,335 28,876
Muda wa majibu (wastani) 121.25s 125.76s 39.05s 14.12s
Muda wa majibu (upeo) 876.20s 566.79s 110.70s 150.60s
Muda wa majibu (jumla) 2667.55s 2137.84s 546.68s 310.55s
Vigezo 1T jumla (32B vinavyotumika) 1T jumla (32B vinavyotumika) 744B jumla (40B vinavyotumika) ~5T jumla (~500B vinavyotumika)
Upatikanaji Uzani unapatikana Uzani unapatikana Chanzo huria 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.

#210 MoonshotAI: Kimi K2.6

medium
Gharama
$0.013
Muda
103.4s
Tokeni
3,620 tok

#253 MoonshotAI: Kimi K2.5

medium
Gharama
$0.030
Muda
58.6s
Tokeni
8,683 tok

#184 GLM 5

medium
Gharama
$0.005
Muda
20.7s
Tokeni
2,068 tok

#116 Claude Opus 4.7

medium
Gharama
$0.059
Muda
26.8s
Tokeni
2,475 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
Kimi K2.6 5.7 8.6 33.3% 0 214.42s 2,925 9,970 77,189
Kimi K2.5 6.1 4.6 66.7% 2 217.49s 6,935 5,705 74,693
GLM 5 10.0 10.0 100.0% 0 74.30s 7,254 2,997 52,930
Claude Opus 4.7 7.6 7.2 77.8% 1 12.96s 10,635 7,629 1,114

Badilisha jozi ya ulinganisho