Benchmarks

Artificial Analysis Intelligence Index v4.3 Intelligence Index · Oct 1, 2026

ConfigurationHarnessScoreCost per task
Gemini 3.1 Pro Preview—29.7—

Terminal-Bench 4.0 (AA) Resolution Rate % · Oct 1, 2026

ConfigurationHarnessScoreCost per task
Artificial Analysis - Gemini 3.1 Pro PreviewArtificial Analysis4.0—

Code Arena | WebDev Overall Arena Score · Sep 30, 2026

ConfigurationHarnessScoreCost per task
gemini-3.1-pro-preview—1446.0 (1441.0–1451.0)—

Agent Arena · Overall (Ranking / Pareto) Net Improvement % · Sep 30, 2026

ConfigurationHarnessScoreCost per task
Gemini 3.1 Pro Preview—-7.3 (-8.3–-6.4)—

Data: real-api-pricingSources and licenses