Urambazaji
AI BENCHY
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 K3 (max) vs Kimi K2.6 (medium) vs GPT-5.6 Sol (medium) vs GPT-5.6 Terra (high): GPT-5.6 Sol (medium) inaongoza kwenye Alama kwa 9.4. Kimi K2.6 (medium) inaongoza kwenye Uaminifu kwa 10.0. GPT-5.6 Sol (medium) ina Jumla ya gharama ya chini zaidi kwa $0.508. GPT-5.6 Terra (high) ndiyo ya haraka zaidi kwa 11.22s.

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-08-29

Nafasi
#59
Jumla ya tokeni za matokeo
224,128
Muda wa majibu (wastani)
142.84s
Jumla ya gharama
$3.467
Nafasi
#107
Jumla ya tokeni za matokeo
347,519
Muda wa majibu (wastani)
115.89s
Jumla ya gharama
$1.247
Nafasi
#8
Jumla ya tokeni za matokeo
34,977
Muda wa majibu (wastani)
12.63s
Jumla ya gharama
$0.508
Nafasi
#58
Jumla ya tokeni za matokeo
56,088
Muda wa majibu (wastani)
11.22s
Jumla ya gharama
$0.836
Muundo unaopendekezwa GPT-5.6 Sol (medium)

It has the best score here (9.4), while costing about 3.6x less than miundo mingine katika ulinganisho huu.

Ulinganisho wa kina

Kipimo Kimi K3 Kimi K3 max Toleo: 2026-07-16 Kimi K2.6 Kimi K2.6 medium Toleo: 2026-04-20 GPT-5.6 Sol GPT-5.6 Sol medium Toleo: 2026-07-09 GPT-5.6 Terra GPT-5.6 Terra high Toleo: 2026-07-09
Alama 7.9 7.2 9.4 8.0
Nafasi #59 #107 #8 #58
Uaminifu 9.0 10.0 10.0 10.0
Uthabiti 9.2 8.3 8.9 9.3
Majaribio 66/66 66/66 66/66 66/66
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 77.3% 63.6% 90.9% 68.2%
Majaribio yasiyo thabiti 2 4 3 2
Jumla ya uendeshaji 66 66 66 66
Gharama kwa matokeo 21.668 10.029 8.025 7.293
Jumla ya gharama $3.467 $1.247 $0.508 $0.836
Bei ya ingizo $3.000 / 1M $0.950 / 1M $2.000 / 1M $2.000 / 1M
Bei ya toleo $15.000 / 1M $4.000 / 1M $10.000 / 1M $12.000 / 1M
Jumla ya tokeni za ingizo 34,960 68,913 79,006 81,056
Tokeni za matokeo 2,887 64,654 4,696 5,055
Tokeni za hoja 221,241 282,865 30,281 51,033
Muda wa majibu (wastani) 142.84s 115.89s 12.63s 11.22s
Muda wa majibu (upeo) 766.58s 876.20s 79.40s 91.49s
Muda wa majibu (jumla) 2714.02s 2433.66s 277.88s 246.77s
Vigezo 2.8T jumla (104B vinavyotumika) 1T jumla (32B vinavyotumika) ~2T jumla (~150B vinavyotumika) ~1T jumla (~60B vinavyotumika)
Upatikanaji Uzani unapatikana Uzani unapatikana Imefungwa Imefungwa

Onyesho la kizazi cha modeli

Hamster playing table tennis

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

#59 MoonshotAI: Kimi K3

max
Gharama
$0.281
Muda
506.9s
Tokeni
18,863 tok

#107 MoonshotAI: Kimi K2.6

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

#8 GPT-5.6 Sol

medium
Gharama
$0.124
Muda
57.2s
Tokeni
4,199 tok

#58 GPT-5.6 Terra

high
Gharama
$0.055
Muda
30.2s
Tokeni
3,748 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 K3 10.0 10.0 100.0% 0 325.79s 8,061 460 84,012
Kimi K2.6 5.7 8.6 33.3% 0 214.42s 2,925 9,970 77,189
GPT-5.6 Sol 10.0 10.0 100.0% 0 9.40s 7,302 394 4,706
GPT-5.6 Terra 7.6 7.2 77.8% 1 9.14s 7,302 370 6,087

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho