Gemini 4 Neon (Medium): benchmark results

Provider: Google. Released 2026-11-18. Access: API.

Aggregate Rating 1962 ± 12, rank #20 of 2286 rated models, from 112 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AA MKA - Output File Type - spreadsheet - Regression WSR97.89Weighted Satisfaction Rate (%)100
AI Coding Daily (Antigravity) - React-TS Code Quality18React-TS Code Quality (max 20) points, LLM-judged rubric sco100
AA GDP.pdf32.8All Criteria Pass Rate (%)99.5
AA GDP.pdf - Criterion Pass Rate82.76Macro Criterion Pass Rate (%)99.3
AutomationBench-AA77.81Guardrail-Adjusted Objective Completion (%)98.9
AutomationBench-AA - Finance - Raw Objective Completion96.69Raw Objective Completion (%)98.9
AutomationBench-AA - Strict53.58Strict Task Success (%)98.6
AutomationBench-AA - Support - Raw Objective Completion93.99Raw Objective Completion (%)98.2
AA GDP.pdf - Insurance - Criterion Pass Rate90.81Criterion Pass Rate (%)97.9
AA-Briefcase - Presentation Elo1677.85Elo97.9
AutomationBench53.27Strict Task Pass Rate (%)97.7
AutomationBench-AA - HR - Raw Objective Completion81.29Raw Objective Completion (%)97.2

Interactive version: theaggregate.ai/model?slug=gemini-4-neon-medium · How It Works · Data refreshed daily, snapshot 2026-11-20.