← All models
Compare

Gemini 3.1 Pro vs GPT-5

Gemini 3.1 Pro (Google DeepMind) and GPT-5 (OpenAI) compared on benchmarks, pricing, context window, and use-case rankings.

AttributeGemini 3.1 ProGoogle DeepMind · 3 in the newsGPT-5OpenAI · 41 in the news
Scores
Intelligence (ECI)155150
Coding6545
Math7470
Reasoning & Knowledge9456
Agentic & Tools8335
Specifications
DeveloperGoogle DeepMindOpenAI
FamilyGeminiGPT
ReleasedFeb 19, 2026Aug 7, 2025
Parameters
AvailabilityAPI accessAPI access
Context window400K
Price — $/M input$1.25
Price — $/M output$10.00
Inputstext, image, file
Outputstext
Benchmarks
AIME 2024/202596%91%
APEX34%18%
ARC-AGI98%66%
ARC-AGI-277%10%
FrontierMath37%32%
FrontierMath Tier 417%13%
GPQA Diamond94%86%
GSO (code optimization)23%7%
Humanity's Last Exam46%25%
METR task horizon6.4 h3.4 h
SimpleBench80%57%
SimpleQA Verified77%51%
SWE-bench Verified76%74%
Terminal-Bench80%50%
WebDev Arena14611395
WeirdML72%61%
GDPval (win/tie rate)38%
LiveCodeBench85%
MATH Level 598%
MMLU-Pro87%
SciCode43%
τ²-bench85%

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.

Frequently asked questions

Is Gemini 3.1 Pro better than GPT-5?

On Epoch AI's Capabilities Index, Gemini 3.1 Pro scores higher (155) than GPT-5 (150). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.

Which is better for coding, Gemini 3.1 Pro or GPT-5?

Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Gemini 3.1 Pro ranks higher — 65th vs 45th percentile among the models tracked on Model Beat.

Want a different match-up? Open the compare tool to add or swap models.

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