Kimi K2.5 (Non-reasoning)
KimiKimiOpen WeightMIT · Uso Comercial
Descripción
Kimi K2.5 is Moonshot AI's flagship agentic model and a new SOTA open model. It unifies vision and text, thinking and non-thinking modes, and single-agent and multi-agent execution into one model. Built with Full-Parameter RL tuning, it achieves state-of-the-art performance across agents, coding, image, and video benchmarks.
Fecha de lanzamiento
2026-01-27
Parámetros
1.0T
Longitud del contexto
262K
Modalidades
image, text, video
Radar de capacidades
26
general
40
coding
79
reasoning
52
science
50
agents
80
multimodal
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Capacidad agéntica | 126 | 34.0 | LS |
| Ranking de codificación | 196 | 54.0 | AA |
| Ranking general | 200 | 55.0 | AA |
| Ranking multimodal | 26 | 57.0 | LS |
| Ciencia | 184 | 56.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
(LLM Stats (zeroeval))Agents
WideSearch
79.0%Aut.
DeepSearchQA
77.1%Aut.
BrowseCompOpenAI (2025)
74.9%Aut.
PaperBench
63.5%Aut.
Terminal-Bench 2.0Stanford × Laude Institute (2026)
50.8%Aut.
SWE-Bench ProPrinceton NLP (2024)
50.7%Aut.
CyberGym
41.3%Aut.
FrontierSWE
26.0%
Biology
GPQANYU + Cohere + Anthropic (2023)
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%
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
(Artificial Analysis)Intelligence Index(Artificial Analysis)30.1
Tau2(Sierra + U Toronto + Vector Institute (2025))0.8
Gpqa(NYU + Cohere + Anthropic (2023))0.8
Lcr(Artificial Analysis)0.7
Ifbench(Google Research (2023))0.4
Scicode(UIUC + Argonne National Lab (2024))0.4
Terminalbench Hard(Stanford × Laude Institute (2026))0.2
Hle(Center for AI Safety + Scale AI (2025))0.1
Puntuaciones por categoría LLM Stats
(LLM Stats (zeroeval))Language90
Legal90
Finance90
Image To Text80
Long Context80
Math80
Frontend Development80
Video80
Multimodal70
Physics70
Reasoning70
Search70
Structured Output70
General70
Healthcare70
Biology70
Chemistry70
Vision70
Agents60
Code50
Tool Calling50
Safety40
Precios
Precio de entrada$0.6 / 1M tokens
Precio de salida$3 / 1M tokens
Precio mixto (3:1)$1.2 / 1M tokens
Precio de lectura caché$0.095 / 1M tokens
Velocidad
Tokens/seg0.0
Retraso del primer token0.00s
Tiempo hasta la respuesta0.00s
Ranking de Precios por Proveedor
Ranking de Precios por Proveedor
1 proveedores
ProveedorEntradaSalida
1KimiPRINCIPAL
$0.6
$3
Comparar precios entre diferentes proveedores de API para este modelo.