Urambazaji
Advertise here

Claude Sonnet 5.5 (max) vs GPT-5.3-Codex (medium)

Claude Sonnet 5.5 (max) inaongoza kwa average score: 9.0 vs 8.9. GPT-5.3-Codex (medium) ina gharama ya chini ya benchmark: $0.988 vs $7.545. GPT-5.3-Codex (medium) ni ya haraka zaidi: 16.91s vs 83.04s, na pass rates 81.8% vs 83.3%.

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-09-29

Modeli zilizolinganishwa

Nafasi
#39
Jumla ya tokeni za matokeo
727,349
Muda wa majibu (wastani)
83.04s
Jumla ya gharama
$7.545
Nafasi
#43
Jumla ya tokeni za matokeo
60,374
Muda wa majibu (wastani)
16.91s
Jumla ya gharama
$0.988
Muundo unaopendekezwa GPT-5.3-Codex (medium)

Its score stays close to the best score here (8.9 vs 9.0), while costing about 7.6x less than Claude Sonnet 5.5 (max).

Ulinganisho wa kina

Kipimo Claude Sonnet 5.5 Claude Sonnet 5.5 max Toleo: 2026-09-29 GPT-5.3-Codex GPT-5.3-Codex medium Toleo: 2026-02-05
Alama 9.0 8.9
Nafasi #39 #43
Uaminifu 10.0 10.0
Uthabiti 9.4 8.6
Majaribio 66/66 66/66
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 81.8% 83.3%
Majaribio yasiyo thabiti 2 4
Jumla ya uendeshaji 66 66
Gharama kwa matokeo 44.380 6.171
Jumla ya gharama $7.545 $0.988
Bei ya ingizo $2.000 / 1M $1.750 / 1M
Bei ya toleo $10.000 / 1M $14.000 / 1M
Jumla ya tokeni za ingizo 135,496 81,187
Tokeni za matokeo 8,153 6,258
Tokeni za hoja 719,196 54,116
Muda wa majibu (wastani) 83.04s 16.91s
Muda wa majibu (upeo) 488.39s 100.93s
Muda wa majibu (jumla) 1826.84s 372.03s
Vigezo ~1T jumla (~100B vinavyotumika) ~1.2T jumla (~80B vinavyotumika)
Upatikanaji Imefungwa Imefungwa

Onyesho la kizazi cha modeli

Hamster playing table tennis

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

#39 Claude Sonnet 5.5

max
OpenRouter returned no showcase content (finish_reason: length).
Gharama
$0.000
Muda
571.7s
Tokeni
0 tok

#43 GPT-5.3-Codex

medium
Gharama
$0.049
Muda
54.9s
Tokeni
3,580 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
Claude Sonnet 5.5 10.0 10.0 100.0% 0 55.26s 10,608 580 70,730
GPT-5.3-Codex 10.0 10.0 100.0% 0 19.50s 7,302 535 10,890

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho