← All models
Compare

Gemma 4 26B A4B vs Kimi K2.5

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

Gemma 4 26B A4BKimi K2.5
Gemma 4 26B A4BGoogle DeepMindKimi K2.5Moonshot · 11 in the news
Scores
Intelligence (ECI)148
Coding2644
Math53
Reasoning & Knowledge436
Agentic & Tools39
Specifications
DeveloperGoogle DeepMindMoonshot
FamilyGemmaKimi
ReleasedApr 2, 2026Feb 2, 2026
Parameters1T
AvailabilityOpen weights (unrestricted)Open weights (unrestricted)
Context window262K
Price — $/M input$0.38
Price — $/M output$2.02
Inputstext, image
Outputstext
Benchmarks
WebDev Arena13591431
WeirdML35%46%
AIME 2024/202592%
APEX14%
ARC-AGI65%
ARC-AGI-212%
FrontierMath28%
FrontierMath Tier 44%
GPQA Diamond88%
Humanity's Last Exam24%
SimpleBench47%
SimpleQA Verified34%
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.