Compare

Gemini 3.1 Pro vs Qwen 3.7 Max

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

Gemini 3.1 ProQwen 3.7 Max

Gemini 3.1 ProGoogle DeepMind · 3 in the newsQwen 3.7 MaxAlibaba · 4 in the news

Scores

Intelligence (ECI)155153

Coding6881

Math7778

Reasoning & Knowledge9685

Agentic & Tools8878

Specifications

DeveloperGoogle DeepMindAlibaba

FamilyGeminiQwen

ReleasedFeb 19, 2026May 19, 2026

Parameters——

AvailabilityAPI access—

Context window—1M

Price — $/M input—$1.25

Price — $/M output—$3.75

Inputs—text

Outputs—text

Benchmarks

AIME 2024/202596%95%

APEX34%—

ARC-AGI98%—

ARC-AGI-277%—

FrontierMath37%—

FrontierMath Tier 417%—

GPQA Diamond94%92%

GSO (code optimization)23%—

Humanity's Last Exam46%38%

METR task horizon6.4 h—

SimpleBench80%70%

SimpleQA Verified77%59%

SWE-bench Verified76%77%

Terminal-Bench80%—

WebDev Arena14611541

WeirdML72%—

SciCode—49%

τ²-bench—95%

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.

Gemini 3.1 Pro vs Qwen 3.7 Max

Popular comparisons