AI BENCHY
Linganisha Chati
โค๏ธ XCS
Your ad here

#22

Qwen: Qwen3.5-35B-A3B

Qwen ยท qwen/qwen3.5-35b-a3b::medium

Fungua kichagua ulinganisho wa modeli

Wastani wa alama

5.93

Gharama kwa matokeo

5.169

Uthabiti

6.62

Jumla ya gharama

$0.362

Majaribio sahihi

7/14

Jaribio huhesabiwa kuwa limepita kikamilifu tu ikiwa run zake zote zimepita.

Majaribio yenye makosa

7

Kiwango cha kupita kwa kila jaribio: 73.8%

Majaribio yasiyo thabiti

6

Muda wa majibu: wastani 44.87s ยท jumla 628.19s ยท upeo 106.00s

Hakufuata maelekezo: 2 Muda umeisha: 2 Jibu lisilo sahihi: 2 Hitilafu ya API: 1

Modeli bora kwa alama

Chagua modeli ya kwanza, kisha bofya modeli ya pili kufungua ukurasa wa kulinganisha bega kwa bega.

Mgawanyo wa kategoria

Kategoria Wastani wa alama Uthabiti Majaribio sahihi
Anti-AI Tricks 10.00 10.00 3/3
Data parsing and extraction 5.50 5.87 1/2
Domain specific 1.00 4.42 0/3
Instructions following 8.00 6.80 1/2
Puzzle Solving 4.34 4.70 1/3
Tool Calling 10.00 10.00 1/1