← All models
Compare

Gemini 3.1 Pro vs Magistral Small 1.2

Gemini 3.1 Pro (Google DeepMind) and Magistral Small 1.2 (Mistral AI) compared on benchmarks, pricing, context window, and use-case rankings.

AttributeGemini 3.1 ProGoogle DeepMind · 3 in the newsMagistral Small 1.2Mistral AI
Scores
Intelligence (ECI)155
Coding6522
Math7421
Reasoning & Knowledge945
Agentic & Tools835
Specifications
DeveloperGoogle DeepMindMistral AI
FamilyGemini
ReleasedFeb 19, 2026Sep 18, 2025
Parameters
AvailabilityAPI accessOpen weights (unrestricted)
Context window
Price — $/M input
Price — $/M output
Inputs
Outputs
Benchmarks
AIME 2024/202596%80%
APEX34%
ARC-AGI98%
ARC-AGI-277%
FrontierMath37%
FrontierMath Tier 417%
GPQA Diamond94%66%
GSO (code optimization)23%
Humanity's Last Exam46%6%
METR task horizon6.4 h
SimpleBench80%
SimpleQA Verified77%
SWE-bench Verified76%
Terminal-Bench80%
WebDev Arena1461
WeirdML72%
LiveCodeBench72%
MMLU-Pro77%
SciCode35%
τ²-bench28%

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

Which is better for coding, Gemini 3.1 Pro or Magistral Small 1.2?

Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Gemini 3.1 Pro ranks higher — 65th vs 22th 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.