← All models
Compare

Gemini 3.1 Pro vs Kimi K2.6

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

Gemini 3.1 ProKimi K2.6
Gemini 3.1 ProGoogle DeepMind · 3 in the newsKimi K2.6Moonshot · 7 in the news
Scores
Intelligence (ECI)155151
Coding6879
Math7776
Reasoning & Knowledge9668
Agentic & Tools8887
Specifications
DeveloperGoogle DeepMindMoonshot
FamilyGeminiKimi
ReleasedFeb 19, 2026Apr 20, 2026
Parameters1T
AvailabilityAPI accessOpen weights (unrestricted)
Context window262K
Price — $/M input$0.55
Price — $/M output$3.20
Inputstext, image
Outputstext
Benchmarks
AIME 2024/202596%96%
APEX34%
ARC-AGI98%
ARC-AGI-277%
FrontierMath37%39%
FrontierMath Tier 417%15%
GPQA Diamond94%91%
GSO (code optimization)23%
Humanity's Last Exam46%36%
METR task horizon6.4 h
SimpleBench80%
SimpleQA Verified77%39%
SWE-bench Verified76%77%
Terminal-Bench80%
WebDev Arena14611526
WeirdML72%56%
SciCode54%
τ²-bench96%

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.