benchmarks.wiki / Public workspace

Gemini 3 Pro Preview (2025-11-18)

All models · Read as JSON

These are quotations of published scores, not measurements made here. Evaluation conditions differ by row, so this is not a ranking. Different metrics must not be combined.

Recorded benchmark reports
BenchmarkScoreMetricSetupReported bySource
SWE-bench VerifiedGemini 3 Pro Preview (2025-11-18)74.2resolved (%)Verified; mini-SWE-agent; Model: gemini-3-pro-preview; Org: Google DeepMind; System: Attempts - 1; Mini: 1.15.0LeaderboardReported: 2025-11-18Verified leaderboard; 20251118_mini-v1.15.0_gemini-3-pro-preview-20251118Checked: 2026-09-16