Urambazaji
AI BENCHY
Linganisha Chati
❤️ Made by XCS
Your ad here

AI BENCHY Compare

OpenAI: GPT-5.3-Codex vs Qwen: Qwen3.5-27B

Jina la modeli:

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe : 2026-02-27 15:16

Muhtasari

Kipimo OpenAI: GPT-5.3-Codex medium Toleo: Tarehe ya kutolewa haijulikani Qwen: Qwen3.5-27B medium Toleo: Tarehe ya kutolewa haijulikani
Nafasi #7 #5
Alama 7.93 8.55
Uthabiti 8.84 9.55
Gharama kwa matokeo 4.641 2.950
Jumla ya gharama $0.465 $0.325
Majaribio sahihi
Majaribio yenye makosa 4 3
Kiwango cha kupita kwa kila jaribio 78.6% 83.3%
Majaribio yasiyo thabiti 2 1
Tokeni za matokeo 1,201 1,091
Tokeni za hoja 30,056 131,807

Mgawanyo wa kategoria

Mbinu za kupinga AI Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Tokeni za matokeo Tokeni za hoja
OpenAI: GPT-5.3-Codex 10.00 10.00 100.0% 0 216 1,421
Qwen: Qwen3.5-27B 10.00 10.00 100.0% 0 102 8,956
Uchanganuzi na uchimbaji wa data Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Tokeni za matokeo Tokeni za hoja
OpenAI: GPT-5.3-Codex 10.00 10.00 100.0% 0 234 735
Qwen: Qwen3.5-27B 9.88 10.00 100.0% 0 270 16,150
Mahususi kwa domeni Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Tokeni za matokeo Tokeni za hoja
OpenAI: GPT-5.3-Codex 4.00 7.21 55.6% 1 64 25,308
Qwen: Qwen3.5-27B 4.00 10.00 33.3% 0 43 52,368
Ufuataji wa maagizo Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Tokeni za matokeo Tokeni za hoja
OpenAI: GPT-5.3-Codex 9.00 10.00 50.0% 0 93 693
Qwen: Qwen3.5-27B 9.00 6.88 83.3% 1 97 11,638
Puzzle Solving Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Tokeni za matokeo Tokeni za hoja
OpenAI: GPT-5.3-Codex 7.00 7.38 77.8% 1 340 1,407
Qwen: Qwen3.5-27B 10.00 10.00 100.0% 0 231 41,372
Mwito wa zana Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Tokeni za matokeo Tokeni za hoja
OpenAI: GPT-5.3-Codex 10.00 10.00 100.0% 0 254 492
Qwen: Qwen3.5-27B 10.00 10.00 100.0% 0 348 1,323

Badilisha jozi ya ulinganisho