Kimi K2.5 Thinking
Kimi K2.5 with thinking mode enabled. Built on Kimi K2 with ~15T mixed visual and text tokens, it excels at general reasoning, visual coding, and agentic tool-calling. Produces reasoning traces for complex multi-step workflows.
- Reasoning
- Vision
- Tool Calling
- Parallel Tool Calls
Added Jan 26, 2026
Model weightsPricing
Auto routing · per 1M tokens- Input
- $0.38
- Output
- $2.00
- Cache read
- $0.070
Specifications
- Context window
- 256K
- Max output
- 65.5K
- Parameters
- 1T / 32B
- Total / active
- Avg output (7d)
- 1.9K tokens
- Longer than 91% of models
Benchmarks
Benchmarks
Sourced from Artificial Analysis.
Intelligence Index
23.5
Coding Index
46.8
Agentic work
T²-Bench Telecom (legacy)
Legacy fallback · Conversational AI agents in dual-control scenarios
95.9%
Better than 96% of models compared
GDPval-AA v2
Economically valuable tasks (Elo)
843 Elo
Better than 38% of models compared
Document reasoning
AA-LCR v1.1
Long context reasoning with updated grading
78.0%
Better than 79% of models compared
Reasoning
HLE
Humanity's Last Exam
30.7%
Better than 79% of models compared
IFBench
Instruction-following benchmark
70.2%
Better than 84% of models compared
CritPt
Research-level physics reasoning
3.1%
Coding
Terminal-Bench Hard (legacy)
Legacy fallback · Agentic coding and terminal use
34.8%
Better than 80% of models compared
Knowledge
AA-Omniscience Accuracy
Proportion of correctly answered questions
35.2%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
65.7%
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
87.9%
Better than 84% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
78.0%
Better than 79% of models compared
GDPval-AA (unversioned / legacy)
Economically valuable tasks
16.2%
Last updated Oct 3, 2026
Artificial AnalysisProviders
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…