Gemini 3 Pro (Preview) (High) — benchmark results

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

Unified ELO 1952 ± 27, rank #39 of 1776 rated models, from 63 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AA LiveCodeBench91.75Pass@1 (%)100
AA MMLU-Pro89.76Accuracy (%)100
AA Omniscience - Law64.3Accuracy (%)100
Eleusis Benchmark17.26Avg Floored Score100
AA Global-MMLU-Lite - Arabic92.67Accuracy (%)99.2
UGI - Natural Intelligence74.29NatInt Score99.2
AA Global-MMLU-Lite - Italian94.33Accuracy (%)99.1
AA Global-MMLU-Lite - Japanese93.17Accuracy (%)99.1
AA Global-MMLU-Lite - Spanish94.17Accuracy (%)99.1
AA Global-MMLU-Lite - Swahili91Accuracy (%)99.1
AA Global-MMLU-Lite - Yoruba86.25Accuracy (%)99.1
AA Omniscience - Humanities & Social Sciences56.6Accuracy (%)98.9

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