Google · model passport
Gemini 3 Pro
gemini-3-pro- Cloud only
- Proprietary licence
- Released 2026-01-09(first seen on LMArena)
- Overall · LMArena
- 1,485#17 of 396
- Best percentile
- 96.0Overall
- Cohort standing
- 72.5median 55.2
What the data says
Benchmarked on 8 of 27 tracked axes. Every figure below is the model's own published result on that board.
Strongest axes
- 96 pct — Overall (1,485)
- 94.2 pct — Factuality Arena (1,481)
- 93.9 pct — Hard prompts (1,502)
Uneven: 61.8 percentile points between its best and worst axis — 96 pct on Overall versus 34.2 pct on Document Arena.
- Overall96 pct1,485Verify →
- Factuality Arena94.2 pct1,481Verify →
- Hard prompts93.9 pct1,502Verify →
- Vision Arena93.3 pct1,289Verify →
- Instruction following93.2 pct1,472Verify →
- Coding90.5 pct1,517Verify →
- WebDev Arena52.5 pct1,440Verify →
- Document Arena34.2 pct1,451Verify →
- Search ArenaNot benchmarked
- Agent ArenaNot benchmarked
- GPQA DiamondNot benchmarked
- AIME (math)Not benchmarked
- FrontierMathNot benchmarked
- SimpleQA VerifiedNot benchmarked
- ARC-AGI-2Not benchmarked
- Humanity's Last ExamNot benchmarked
- SimpleBenchNot benchmarked
- LiveBenchNot benchmarked
- BFCL v4 (function calling)Not benchmarked
- SWE-bench Verified (live board)Not benchmarked
- Terminal-Bench 4.0Not benchmarked
- MMLU-Pro (Artificial Analysis)Not benchmarked
- LiveCodeBench (Artificial Analysis)Not benchmarked
- IFBench (Artificial Analysis)Not benchmarked
- HHEM Hallucination (Vectara)Not benchmarked
- SWE-bench VerifiedNot benchmarked
- Terminal-BenchNot benchmarked
Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.
Gemini 3 Pro stands at 72.5 (raw mean 81) — measured on 8 of 27 axes.
Gemini 3 Pro stands at 72.5 versus a cohort median of 55.2 across 116 models released within 180 days — above the peer median.
Gemini 3 Pro scores in the 96th percentile on Overall.
Gemini 3 Pro scores at percentile 94.2 on Factuality Arena.
Gemini 3 Pro ranks between #23 and #90 across 6 built-in weightings — best under "Conversation-first", worst under "Coding-focused".
Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →