← All models
Compare

GPT-5.6 Sol vs Kimi K2.5

Add, remove, or swap models to compare them side by side.

GPT-5.6 SolKimi K2.5
AttributeGPT-5.6 SolOpenAI · 15 in the newsKimi K2.5Moonshot · 15 in the news
Scores
Intelligence (ECI)162148
Coding9547
Math9751
Reasoning & Knowledge9535
Agentic & Tools6652
Specifications
DeveloperOpenAIMoonshot
FamilyGPTKimi
ReleasedJul 9, 2026Feb 2, 2026
Parameters1T
AvailabilityAPI accessOpen weights (unrestricted)
Context window1.1M262K
Price — $/M input$5.00$0.38
Price — $/M output$30.00$2.02
Inputsfile, image, texttext, image
Outputstexttext
Benchmarks
AIME 2024/2025100%92%
APEX40%14%
ARC-AGI98%65%
ARC-AGI-293%12%
GPQA Diamond93%88%
Humanity's Last Exam47%24%
SciCode56%49%
SimpleBench72%47%
SimpleQA Verified72%34%
WebDev Arena16201431
WeirdML89%46%
τ²-bench85%96%
FrontierMath28%
FrontierMath Tier 44%
SWE-bench Verified74%
Terminal-Bench43%

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.

Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.