Urambazaji
AI BENCHY
Advertise here

AI BENCHY Compare

DeepSeek: DeepSeek V3.2 vs OpenAI: gpt-oss-120b

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-05-22

Kipimo DeepSeek V3.2 DeepSeek V3.2 none Toleo: 2025-12-01 gpt-oss-120b gpt-oss-120b none Toleo: 2025-08-05 Inapatikana bure
Alama 5.6 5.2
Nafasi #114 #129
Uaminifu 10.0 10.0
Uthabiti 8.0 8.7
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 46.7% 36.8%
Majaribio yasiyo thabiti 5 3
Jumla ya uendeshaji 60 57
Gharama kwa matokeo 0.254 0.201
Jumla ya gharama $0.018 $0.011
Bei ya ingizo $0.252 / 1M $0.000 / 1M
Bei ya toleo $0.378 / 1M $0.000 / 1M
Tokeni za matokeo 11,163 51,505
Tokeni za hoja 0 0
Muda wa majibu (wastani) 14.46s 21.86s
Muda wa majibu (upeo) 115.89s 113.71s
Muda wa majibu (jumla) 289.21s 349.78s

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
DeepSeek V3.2 3.3 8.2 12.5% 1 9.35s 1,073 0
gpt-oss-120b 6.5 10.0 50.0% 0 32.84s 8,676 0
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
DeepSeek V3.2 3.1 5.4 16.7% 1 20.87s 4,522 0
gpt-oss-120b 4.3 1.1 66.7% 1 9.57s 3,232 0
Mchanganyiko Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
DeepSeek V3.2 6.5 10.0 0.0% 0 115.89s 2,887 0
gpt-oss-120b 3.0 10.0 0.0% 0 0ms 0 0
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
DeepSeek V3.2 6.3 5.8 66.7% 1 9.42s 1,710 0
gpt-oss-120b 6.5 10.0 50.0% 0 7.12s 598 0
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
DeepSeek V3.2 3.0 6.9 16.7% 1 4.17s 21 0
gpt-oss-120b 3.0 10.0 0.0% 0 34.98s 29,483 0
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
DeepSeek V3.2 7.6 10.0 100.0% 0 9.32s 43 0
gpt-oss-120b 4.8 10.0 0.0% 0 10.79s 615 0
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
DeepSeek V3.2 10.0 10.0 100.0% 0 1.52s 66 0
gpt-oss-120b 9.8 10.0 100.0% 0 5.10s 1,982 0
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
DeepSeek V3.2 7.5 7.7 88.9% 1 7.13s 302 0
gpt-oss-120b 4.4 4.5 44.5% 2 9.51s 3,781 0
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
DeepSeek V3.2 10.0 10.0 100.0% 0 11.85s 522 0
gpt-oss-120b 3.0 10.0 0.0% 0 0ms 0 0
Maarifa 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
DeepSeek V3.2 3.0 10.0 0.0% 0 17.23s 17 0
gpt-oss-120b 3.0 10.0 0.0% 0 47.29s 3,138 0

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho

DeepSeek V3.2nonevsgpt-oss-120bmediumInapatikana bureDeepSeek V3.2nonevsMiniMax M2.5mediumInapatikana bureMiniMax M2.7mediumvsgpt-oss-120bnoneInapatikana bureDeepSeek V3.2nonevsMistral Small 4mediumCobuddymediumInapatikana burevsDeepSeek V3.2noneDeepSeek V3.2nonevsElephant Alphamediumgpt-oss-120bnoneInapatikana burevsElephant AlphamediumMistral Small 4mediumvsgpt-oss-120bnoneInapatikana bureMiniMax M2.5mediumInapatikana burevsgpt-oss-120bnoneInapatikana bureDeepSeek V3.2nonevsOwl AlphamediumDeepSeek V3.2nonevsNemotron 3 SupermediumInapatikana buregpt-oss-120bnoneInapatikana burevsQwen3 Coder Nextmedium