Urambazaji
AI BENCHY
Your ad here

AI BENCHY Compare

OpenAI: GPT-5.3-Codex vs Qwen: Qwen3.5 Plus 2026-02-15

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-04-11

Kipimo GPT-5.3-Codex GPT-5.3-Codex medium Toleo: 2026-02-05 Qwen3.5 Plus 2026-02-15 Qwen3.5 Plus 2026-02-15 medium Toleo: 2026-02-15
Alama 8.6 8.5
Nafasi #5 #6
Uthabiti 8.7 9.1
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 83.3% 83.3%
Majaribio yasiyo thabiti 3 2
Jumla ya uendeshaji 54 54
Gharama kwa matokeo 4.405 1.566
Jumla ya gharama $0.573 $0.220
Bei ya ingizo $1.750 / 1M $0.260 / 1M
Bei ya toleo $14.000 / 1M $1.560 / 1M
Tokeni za matokeo 2,279 2,121
Tokeni za hoja 35,179 111,889
Muda wa majibu (wastani) 15.38s 46.56s
Muda wa majibu (upeo) 100.93s 120.91s
Muda wa majibu (jumla) 276.91s 512.20s

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

Mbinu za kupinga AI Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
GPT-5.3-Codex 8.7 7.9 91.7% 1 4.16s 240 1,722
Qwen3.5 Plus 2026-02-15 8.2 7.9 83.3% 1 45.78s 205 21,236
Uandishi wa msimbo Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
GPT-5.3-Codex 10.0 10.0 100.0% 0 8.95s 491 1,530
Qwen3.5 Plus 2026-02-15 10.0 10.0 100.0% 0 120.91s 367 19,367
Mchanganyiko Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
GPT-5.3-Codex 10.0 10.0 100.0% 0 19.56s 364 2,731
Qwen3.5 Plus 2026-02-15 10.0 10.0 100.0% 0 46.85s 421 7,906
Uchanganuzi na uchimbaji wa data Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
GPT-5.3-Codex 10.0 10.0 100.0% 0 3.07s 234 728
Qwen3.5 Plus 2026-02-15 10.0 10.0 100.0% 0 46.91s 270 14,916
Mahususi kwa domeni Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
GPT-5.3-Codex 5.9 7.2 55.6% 1 64.31s 64 25,308
Qwen3.5 Plus 2026-02-15 5.3 10.0 33.3% 0 17.50s 35 16,680
Akili ya jumla Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
GPT-5.3-Codex 4.6 10.0 0.0% 0 4.87s 187 331
Qwen3.5 Plus 2026-02-15 4.7 1.6 66.7% 1 79.86s 73 8,675
Ufuataji wa maagizo Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
GPT-5.3-Codex 10.0 10.0 100.0% 0 3.04s 93 693
Qwen3.5 Plus 2026-02-15 10.0 10.0 100.0% 0 31.93s 101 7,704
Utatuzi wa mafumbo Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
GPT-5.3-Codex 9.0 7.9 88.9% 1 5.12s 352 1,644
Qwen3.5 Plus 2026-02-15 10.0 10.0 100.0% 0 34.57s 340 14,496
Mwito wa zana Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
GPT-5.3-Codex 10.0 10.0 100.0% 0 6.37s 254 492
Qwen3.5 Plus 2026-02-15 10.0 10.0 100.0% 0 7.54s 309 909

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho

Gemini 3 Flash PreviewlowvsGPT-5.3-CodexmediumGemini 3 Flash PreviewlowvsQwen3.5 Plus 2026-02-15mediumGemini 3 Flash PreviewnonevsQwen3.5 Plus 2026-02-15mediumGemini 3.1 Flash Lite PreviewlowvsQwen3.5 Plus 2026-02-15mediumGemini 3 Flash PreviewnonevsGPT-5.3-CodexmediumGemini 3.1 Flash Lite PreviewlowvsGPT-5.3-CodexmediumGPT-5.2 ChatnonevsQwen3.5 Plus 2026-02-15mediumGemini 3.1 Flash Lite PreviewnonevsQwen3.5 Plus 2026-02-15mediumGemini 3.1 Flash Lite PreviewnonevsGPT-5.3-CodexmediumGPT-5.3 ChatnonevsQwen3.5 Plus 2026-02-15mediumClaude Sonnet 4.6nonevsQwen3.5 Plus 2026-02-15mediumClaude Sonnet 4.6nonevsGPT-5.3-Codexmedium