Compare
Kimi K2.5 vs Kimi K2.6
Add, remove, or swap models to compare them side by side.
Scores
Intelligence (ECI)148151
Coding5279
Math5676
Reasoning & Knowledge3968
Agentic & Tools5571
Specifications
DeveloperMoonshotMoonshot
FamilyKimiKimi
ReleasedFeb 2, 2026Apr 20, 2026
Parameters1T1T
AvailabilityOpen weights (unrestricted)Open weights (unrestricted)
Context window262K262K
Price — $/M input$0.38$0.66
Price — $/M output$2.02$3.41
Inputstext, imagetext, image
Outputstexttext
Benchmarks
AIME 2024/202592%96%
APEX14%19%
ARC-AGI65%—
ARC-AGI-212%—
FrontierMath28%39%
FrontierMath Tier 44%15%
GPQA Diamond88%91%
Humanity's Last Exam24%36%
SciCode49%54%
SimpleBench47%—
SimpleQA Verified34%39%
SWE-bench Verified74%77%
Terminal-Bench43%—
WebDev Arena14311526
WeirdML46%56%
τ²-bench96%96%
Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.
Popular comparisons
- Claude Fable 5 vs GPT-5.5
- Claude Fable 5 vs Gemini 3.1 Pro
- Claude Fable 5 vs Muse Spark
- Claude Fable 5 vs Qwen 3.7 Max
- Claude Fable 5 vs Kimi K2.6
- Claude Fable 5 vs GLM-5.2
- Claude Fable 5 vs DeepSeek-V4-Pro
- Gemini 3.1 Pro vs GPT-5.5
- GPT-5.5 vs Muse Spark
- GPT-5.5 vs Qwen 3.7 Max
- GPT-5.5 vs Kimi K2.6
- GLM-5.2 vs GPT-5.5
- DeepSeek-V4-Pro vs GPT-5.5
- Gemini 3.1 Pro vs Muse Spark
- Gemini 3.1 Pro vs Qwen 3.7 Max
- Gemini 3.1 Pro vs Kimi K2.6
- Gemini 3.1 Pro vs GLM-5.2
- DeepSeek-V4-Pro vs Gemini 3.1 Pro
- Muse Spark vs Qwen 3.7 Max
- Kimi K2.6 vs Muse Spark
- GLM-5.2 vs Muse Spark
- DeepSeek-V4-Pro vs Muse Spark
- Kimi K2.6 vs Qwen 3.7 Max
- GLM-5.2 vs Qwen 3.7 Max
- DeepSeek-V4-Pro vs Qwen 3.7 Max
- GLM-5.2 vs Kimi K2.6
- DeepSeek-V4-Pro vs Kimi K2.6
- DeepSeek-V4-Pro vs GLM-5.2
- GPT-5 vs GPT-5.5
- GLM-5 vs GLM-5.2
- Kimi K2.5 vs Kimi K2.6
- Kimi K2 vs Kimi K2.6
Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.