Gemini 3 Pro (High) — benchmark results

Gemini 3 Pro evaluated at the high reasoning-effort setting. Provider: Google. Released 2025-11-18. Access: API.

Unified ELO 1822 ± 26, rank #123 of 1776 rated models, from 39 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Vals AI MATH 50096.4Accuracy (%)99.5
MCPMark53.94Pass@1 (%)97.4
VitaBench31.5Cross-Scenario Avg@4 (%)95
Vals AI MGSM93.93Accuracy (%)90.9
Pencil Puzzle Bench - Light Up20Direct-ask Success Rate (%)89
Pencil Puzzle Bench - Slitherlink13.3Direct-ask Success Rate (%)88
MedCode52.2Score (self-reported)86.8
ALE-Bench1176.75Performance (Self-Refine x1) (self-reported)84.6
IOI38.83Score (self-reported)77.4
ATLAS62.6ATLAScore (self-reported)77.3
Pencil Puzzle Bench - Nurimisaki6.7Direct-ask Success Rate (%)71
Pencil Puzzle Bench - Shikaku6.7Direct-ask Success Rate (%)71

Interactive version: theaggregate.ai/model?slug=gemini-3-pro-high · How the rankings work · Data refreshed daily, snapshot 2026-07-22.