Urambazaji
AI BENCHY
Your ad here

AI BENCHY Compare

DeepSeek: DeepSeek V3.2 vs Xiaomi: MiMo-V2-Pro

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-03-20

Kipimo DeepSeek V3.2 DeepSeek V3.2 none Toleo: 2025-12-01 MiMo-V2-Pro MiMo-V2-Pro medium Toleo: 2026-03-18
Alama 6.4 8.0
Nafasi #42 #20
Uthabiti 8.5 8.5
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 51.0% 76.5%
Majaribio yasiyo thabiti 3 3
Jumla ya uendeshaji 51 45
Gharama kwa matokeo 0.220 1.110
Jumla ya gharama $0.016 $0.123
Bei ya ingizo $0.260 / 1M $1.000 / 1M
Bei ya toleo $0.380 / 1M $3.000 / 1M
Tokeni za matokeo 7,831 1,875
Tokeni za hoja 0 26,959
Muda wa majibu (wastani) 12.35s 9.78s
Muda wa majibu (upeo) 115.89s 64.71s
Muda wa majibu (jumla) 209.94s 156.45s

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 3.2 9.8 0.0% 0 7.63s 1,419 0
MiMo-V2-Pro 10.0 10.0 100.0% 0 3.06s 223 1,107
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
MiMo-V2-Pro 4.7 1.6 66.7% 1 64.71s 380 14,186
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
MiMo-V2-Pro 7.3 5.8 83.3% 1 17.20s 260 7,484
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 3.6 7.2 22.2% 1 1.61s 24 0
MiMo-V2-Pro 5.3 10.0 33.3% 0 6.00s 155 1,048
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 10.0 10.0 100.0% 0 2.86s 67 0
MiMo-V2-Pro 10.0 10.0 100.0% 0 4.06s 198 424
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
MiMo-V2-Pro 9.9 10.0 100.0% 0 3.36s 83 667
Puzzle Solving 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 8.5 7.5 88.9% 1 7.37s 1,136 0
MiMo-V2-Pro 7.0 7.2 55.6% 1 4.71s 313 1,179
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
MiMo-V2-Pro 10.0 10.0 100.0% 0 8.19s 263 864

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho

Gemini 3 Flash PreviewnonevsMiMo-V2-PromediumGemini 3.1 Flash Lite PreviewlowvsMiMo-V2-PromediumDeepSeek V3.2nonevsMercury 2mediumDeepSeek V3.2nonevsGPT-5 NanomediumDeepSeek V3.2nonevsGrok 4.20 Multi-Agent BetamediumGemini 3.1 Flash Lite PreviewnonevsMiMo-V2-PromediumGPT-5.2 ChatnonevsMiMo-V2-PromediumDeepSeek V3.2nonevsgpt-oss-120bmediumInapatikana bureGPT-5.3 ChatnonevsMiMo-V2-PromediumDeepSeek V3.2nonevsMiniMax M2.5mediumInapatikana bureDeepSeek V3.2nonevsGPT-5 MinimediumDeepSeek V3.2nonevsNemotron 3 SupermediumInapatikana bure