Kimi K2.5 (Reasoning)
KimiKimi
Fecha de lanzamiento
2026-01-27
Parámetros
—
Longitud del contexto
262K
Modalidades
image, text, video
Radar de capacidades
36
general
49
coding
88
reasoning
63
scienceest.
50
agents
80
multimodal
Science usa un proxy de razonamiento cuando los benchmarks científicos dedicados no están disponibles.
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Ranking de codificación | 81 | 71.0 | AA |
| Ranking general | 46 | 76.0 | AA |
| Ciencia | 35 | 76.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
Agents
WideSearch
79.0%Aut.
DeepSearchQA
77.1%Aut.
BrowseComp
74.9%Aut.
PaperBench
63.5%Aut.
Terminal-Bench 2.0
50.8%Aut.
SWE-Bench Pro
50.7%Aut.
CyberGym
41.3%Aut.
FrontierSWE
26.0%Aut.
Biology
GPQA
87.6%Aut.
SciCode
48.7%Aut.
Code
SWE-Bench Verified
76.8%Aut.
SWE-bench Multilingual
73.0%Aut.
OJBench (C++)
57.4%Aut.
Economics
FinSearchComp T2&T3
67.8%Aut.
Finance
MMLU-Pro
87.1%Aut.
General
LiveCodeBench v6
85.0%Aut.
MMMU-Pro
78.5%Aut.
SimpleVQA
0.71 / 100Aut.
LiveBench
69.1%Aut.
LongBench v2
61.0%Aut.
Healthcare
VideoMMMU
86.6%Aut.
Image To Text
OCRBench
92.3%Aut.
Long Context
LongVideoBench
79.8%Aut.
LVBench
75.9%Aut.
AA-LCR
70.0%Aut.
Math
AIME 2025
96.1%Aut.
HMMT 2025
95.4%Aut.
MathVista-Mini
90.1%Aut.
MathVision
84.2%Aut.
IMO-AnswerBench
81.8%Aut.
Humanity's Last Exam
50.2%Aut.
Multimodal
InfoVQAtest
92.6%Aut.
OmniDocBench 1.5
88.8%Aut.
Video-MME
87.4%Aut.
MMVU
80.4%Aut.
CharXiv-R
77.5%Aut.
MotionBench
70.4%Aut.
WorldVQA
46.3%Aut.
ZEROBench
0.11 / 100Aut.
Reasoning
Seal-0
57.4%Aut.
Índices de evaluación AA
Intelligence Index38.1
Tau21.0
Gpqa0.9
Ifbench0.7
Lcr0.7
Scicode0.5
Terminalbench Hard0.3
Hle0.3
Puntuaciones por categoría LLM Stats
Language90
Legal90
Finance90
Image To Text80
Long Context80
Math80
Multimodal80
Frontend Development80
Video80
Vision80
Physics70
Reasoning70
Search70
Structured Output70
General70
Healthcare70
Biology70
Chemistry70
Agents60
Code50
Tool Calling50
Safety40
Precios
Precio de entrada$0.58 / 1M tokens
Precio de salida$3 / 1M tokens
Precio mixto (3:1)$1.185 / 1M tokens
Precio de lectura caché$0.1 / 1M tokens
Velocidad
Tokens/seg47.2
Retraso del primer token1.19s
Tiempo hasta la respuesta64.11s
Ranking de Precios por Proveedor
Ranking de Precios por Proveedor
30 proveedores
Más barato: NanoGPTMás caro: evroc
ProveedorEntradaSalida
1NanoGPTMás barato
$0.3
$1.9
2HPC-AI
$0.3
$1.5
3OpenRouter
$0.375
$2.025
4Chutes
$0.44
$2
5SiliconFlow (China)
$0.45
$2.25
6Deep Infra
$0.45
$2.25
7Kilo Gateway
$0.45
$2.2
8Meganova
$0.45
$2.8
9SiliconFlow
$0.45
$2.25
10routing.run
$0.462
$2.42
11Weights & Biases
$0.5
$2.85
12Nebius Token Factory
$0.5
$2.5
13Together AI
$0.5
$2.8
14Neuralwatt
$0.52
$2.59
15Synthetic
$0.55
$2.19
16Venice AI
$0.56
$3.5
17KimiPRINCIPAL
$0.58
$3
18ZenMux
$0.58
$3.02
19Alibaba (China)
$0.6
$3
20Jiekou.AI
$0.6
$3
21Hugging Face
$0.6
$3
22NovitaAI
$0.6
$3
23Cloudflare AI Gateway
$0.6
$3
24Amazon Bedrock
$0.6
$3
25Baseten
$0.6
$3
26Vercel AI Gateway
$0.6
$3
27OrcaRouter
$0.6
$3
28Merge Gateway
$0.6
$3
29CrofAI
$1
$3
30evroc
$1.47
$5.9
Comparar precios entre diferentes proveedores de API para este modelo.