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

AI BENCHY Compare

OpenAI: GPT-5.2 Chat vs Qwen: Qwen3.5-27B

Linganisha:

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-03-03

Kipimo OpenAI: GPT-5.2 Chat none Toleo: 2025-12-11 Qwen: Qwen3.5-27B medium Toleo: 2026-02-24
Nafasi #12 #5
Wastani wa alama 7.41 8.55
Uthabiti 9.45 9.55
Gharama kwa matokeo 2.261 2.950
Jumla ya gharama $0.227 $0.325
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 73.8% 83.3%
Majaribio yasiyo thabiti 1 1
Tokeni za matokeo 14,267 1,091
Tokeni za hoja 0 131,807

Modeli bora kwa alama

Alama dhidi ya gharama ya jumla

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-5.2 Chat 10.00 10.00 100.0% 0 1,651 0
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-5.2 Chat 9.88 10.00 100.0% 0 980 0
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-5.2 Chat 4.00 10.00 33.3% 0 7,810 0
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-5.2 Chat 5.50 6.13 66.7% 1 1,528 0
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-5.2 Chat 7.00 10.00 66.7% 0 1,743 0
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-5.2 Chat 10.00 10.00 100.0% 0 555 0
Qwen: Qwen3.5-27B 10.00 10.00 100.0% 0 348 1,323

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho