← All models
Compare

Gemini 3.1 Pro vs Gemma 4 26B A4B

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

Gemini 3.1 ProGemma 4 26B A4B
Gemini 3.1 ProGoogle DeepMind · 3 in the newsGemma 4 26B A4BGoogle DeepMind
Scores
Intelligence (ECI)156
Coding6826
Math76
Reasoning & Knowledge964
Agentic & Tools88
Specifications
DeveloperGoogle DeepMindGoogle DeepMind
FamilyGeminiGemma
ReleasedFeb 19, 2026Apr 2, 2026
Parameters
AvailabilityAPI accessOpen weights (unrestricted)
Context window
Price — $/M input
Price — $/M output
Inputs
Outputs
Benchmarks
AIME 2024/202596%
APEX34%
ARC-AGI98%
ARC-AGI-277%
FrontierMath37%
FrontierMath Tier 417%
GPQA Diamond94%
GSO (code optimization)23%
Humanity's Last Exam46%
METR task horizon6.4 h
SimpleBench80%
SimpleQA Verified77%
SWE-bench Verified76%
Terminal-Bench80%
WebDev Arena14611359
WeirdML72%35%

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.