← All models
Compare

Gemini 3.1 Pro vs Grok 4

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

Gemini 3.1 ProGrok 4
Gemini 3.1 ProGoogle DeepMind · 2 in the newsGrok 4xAI
Scores
Intelligence (ECI)156147
Coding7115
Math7622
Reasoning & Knowledge9648
Agentic & Tools8816
Specifications
DeveloperGoogle DeepMindxAI
FamilyGeminiGrok
ReleasedFeb 19, 2026Jul 9, 2025
Parameters3T
AvailabilityAPI accessAPI access
Context window
Price — $/M input
Price — $/M output
Inputs
Outputs
Benchmarks
AIME 2024/202596%84%
APEX34%15%
ARC-AGI98%67%
ARC-AGI-277%16%
FrontierMath37%20%
FrontierMath Tier 417%2%
GPQA Diamond94%87%
GSO (code optimization)23%
Humanity's Last Exam46%
METR task horizon6.4 h1.8 h
SimpleBench80%61%
SimpleQA Verified77%48%
SWE-bench Verified76%
Terminal-Bench80%27%
WebDev Arena1461
WeirdML72%46%
GDPval (win/tie rate)24%

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.