Private AI
Kimi K2 0905. Kimi-k2 is a Mixture-of-Experts (MoE) foundation model with exceptional coding and agent capabilities, featuring 1 trillion total parameters and 32 billion activated parameters. In benchmark evaluations covering general knowledge reasoning, programming, mathematics, and agent-related tasks, the K2 model outperforms other leading open-source models. Quantized at FP8.
Added Sep 25, 2025
Model weightsContext Window
256.0K
Max Output
262.1K
Avg output tokens (7d)
341 tokens
Input Price (Auto)
$0.42/1M
Output Price (Auto)
$1.89/1M
Cache Read (Auto)
$0.21/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
23.5
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
GPQA Diamond
Graduate-level scientific reasoning
76.7%
Better than 66% of models compared
HLE
Humanity's Last Exam
6.3%
Better than 47% of models compared
IFBench
Instruction-following benchmark
41.7%
Better than 43% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
73.4%
Better than 65% of models compared
AA-LCR
Long context reasoning evaluation
52.3%
Better than 61% of models compared
SciCode
Python programming for scientific computing
30.7%
Better than 46% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
23.5%
AIME 2025
American Invitational Mathematics Examination 2025
57.3%
Better than 54% of models compared
MMLU-Pro
Professional and academic subject knowledge
81.9%
Better than 77% of models compared
Last updated Jul 15, 2026
Artificial AnalysisBetter than 63% of models compared
LiveCodeBench
Contamination-free coding benchmark
61.0%
Better than 67% of models compared
