Urambazaji
AI BENCHY
Your ad here

AI BENCHY Compare

DeepSeek: DeepSeek V4 Pro vs MoonshotAI: Kimi K2.5

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-04-24

Kipimo DeepSeek V4 Pro DeepSeek V4 Pro none Toleo: 2026-04-24 Kimi K2.5 Kimi K2.5 medium Toleo: 2026-01-27
Alama 6.7 7.0
Nafasi #59 #53
Uthabiti 9.5 6.8
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 51.9% 72.2%
Majaribio yasiyo thabiti 1 7
Jumla ya uendeshaji 26 54
Gharama kwa matokeo 0.317 2.444
Jumla ya gharama $0.029 $0.220
Bei ya ingizo $1.740 / 1M $0.440 / 1M
Bei ya toleo $3.480 / 1M $2.000 / 1M
Tokeni za matokeo 1,596 42,176
Tokeni za hoja 0 84,870
Muda wa majibu (wastani) 24.23s 72.43s
Muda wa majibu (upeo) 109.46s 150.77s
Muda wa majibu (jumla) 436.17s 796.70s

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 V4 Pro 4.8 10.0 25.0% 0 36.12s 221 0
Kimi K2.5 7.3 5.8 83.3% 2 51.38s 2,789 8,880
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 V4 Pro 10.0 10.0 100.0% 0 33.40s 246 0
Kimi K2.5 4.7 1.6 66.7% 1 150.77s 1,269 9,749
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 V4 Pro 9.5 10.0 100.0% 0 34.55s 826 0
Kimi K2.5 10.0 10.0 100.0% 0 71.37s 703 3,713
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 V4 Pro 10.0 10.0 100.0% 0 54.04s 65 0
Kimi K2.5 10.0 10.0 100.0% 0 49.78s 563 7,940
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 V4 Pro 5.3 10.0 33.3% 0 3.74s 6 0
Kimi K2.5 3.5 4.4 33.3% 2 137.29s 20,753 30,564
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 V4 Pro 4.5 10.0 0.0% 0 6.06s 45 0
Kimi K2.5 6.5 3.4 66.7% 1 69.73s 3,815 4,262
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 V4 Pro 6.5 10.0 50.0% 0 3.57s 22 0
Kimi K2.5 10.0 10.0 100.0% 0 92.47s 5,371 6,547
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 V4 Pro 6.0 7.1 44.4% 1 28.25s 92 0
Kimi K2.5 5.3 7.3 44.4% 1 45.40s 6,671 12,403
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 V4 Pro 10.0 10.0 100.0% 0 6.47s 73 0
Kimi K2.5 10.0 10.0 100.0% 0 31.74s 242 812

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho

DeepSeek V4 PrononevsGrok 4.1 FastmediumDeepSeek V4 PrononevsNemotron 3 SupermediumInapatikana bureGemma 4 31BnoneInapatikana burevsKimi K2.5mediumDeepSeek V4 PrononevsMercury 2mediumKimi K2.5mediumvsQwen3.5 Plus 2026-02-15noneDeepSeek V4 PrononevsGrok 4.20mediumDeepSeek V4 PrononevsGPT-5 MinimediumKimi K2.5mediumvsGLM 5noneDeepSeek V4 ProhighvsKimi K2.5mediumClaude Sonnet 4.6nonevsKimi K2.5mediumDeepSeek V4 PrononevsGPT-5 NanomediumKimi K2.5mediumvsMiMo-V2-Omninone