Gemini 3 Pro vs o3
Wins 6 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Long documents
Wins 0 of 7 areas
—
Gemini 3 Pro is the stronger all-rounder.o3 is cheaper.
Scores updated · 43 tests both models report · How we compare
Where each one wins
Tests won in each of the seven areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- ReasoningHard problems that need careful thinking50Gemini 3 Pro5 of 5 tests
- Images and chartsUnderstanding pictures, charts and video40Gemini 3 Pro4 of 4 tests
- CodingWriting and fixing software30Gemini 3 Pro3 of 3 tests
- AgentsCarrying out multi-step tasks on its own20Gemini 3 Pro2 of 2 tests
- Long documentsFinding answers in very long texts20Gemini 3 Pro2 of 2 tests
- FactsGetting facts right instead of making them up21Gemini 3 Pro2 of 3 tests
- Following instructionsDoing exactly what it is asked11Even1 each
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
o3 costs 29% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Gemini 3 Pro pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+24.6points ahead
- Short factual questions, answered correctlySimpleQA Verified+23.5points ahead
- Common-sense trick questionsSimpleBench+23.3points ahead
Where o3 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+3.4points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+1points ahead
Every test, side by side
All 43 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 3 Pro
- SciCodeGemini 3 Pro by 15.156.141+15.1
- SWE-bench VerifiedGemini 3 Pro by 7.176.269.1+7.1
- Terminal-Bench HardGemini 3 Pro by 4.641.737.1+4.6
AgentsGemini 3 Pro
- GDPValGemini 3 Pro by 21.434.212.8+21.4
- BrowseCompGemini 3 Pro by 9.559.249.7+9.5
ReasoningGemini 3 Pro
- ARC-AGI-2Gemini 3 Pro by 24.631.16.5+24.6
- SimpleBenchGemini 3 Pro by 23.376.453.1+23.3
- Humanity's Last ExamGemini 3 Pro by 19.639.720.1+19.6
- GPQA DiamondGemini 3 Pro by 8.190.882.7+8.1
- CritPtGemini 3 Pro by 89.11.1+8
FactsGemini 3 Pro
- SimpleQA VerifiedGemini 3 Pro by 23.572.949.4+23.5
- AA-Omniscience · AccuracyGemini 3 Pro by 17.255.838.6+17.2
- AA-Omniscience · Non-hallucinationo3 by 3.48.511.9+3.4
Images and chartsGemini 3 Pro
- MMMU-ProGemini 3 Pro by 10.180.270.1+10.1
- LMArena · VisionGemini 3 Pro by 91 rating points13051214+91 rating
- MathVistaGemini 3 Pro by 389.886.8+3
- CharXiv (RQ)Gemini 3 Pro by 2.881.478.6+2.8
Long documentsGemini 3 Pro
- LongBench v2Gemini 3 Pro by 9.468.258.8+9.4
- AA-LCRGemini 3 Pro by 1.37674.7+1.3
Following instructionsEven
- Multi-ChallengeGemini 3 Pro by 5.365.760.4+5.3
- IFBencho3 by 170.471.4+1
Other results22 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- AA-OmniscienceGemini 3 Pro by 30.815.3-15.6+30.8
- HarmBencho3 by 25.972.598.4+25.9
- SimpleQAGemini 3 Pro by 22.772.149.4+22.7
- HMMT Feb. 2025Gemini 3 Pro by 2097.577.5+20
- metr_re_benchGemini 3 Pro by 203515+20
- frontiermath_tier_4_v1Gemini 3 Pro by 16.718.82.1+16.7
- AA Agentic IndexGemini 3 Pro by 15.95236.1+15.9
- ARC-AGI-1Gemini 3 Pro by 14.27560.8+14.2
- AIME 2025Gemini 3 Pro by 13.610086.4+13.6
- AIR-Bench 2024o3 by 11.373.284.5+11.3
- Artificial Analysis Coding IndexGemini 3 Pro by 8.146.538.4+8.1
- AA IntelligenceGemini 3 Pro by 7.82820.2+7.8
- LiveCodeBenchGemini 3 Pro by 7.39284.7+7.3
- metr_hcastGemini 3 Pro by 6.671.364.7+6.6
- τ²-Bench Telecom (AA run)Gemini 3 Pro by 6.487.180.7+6.4
- MMLU-ProGemini 3 Pro by 5.190.185+5.1
- τ²-Bench (Retail)Gemini 3 Pro by 5.185.380.2+5.1
- VideoMMMUGemini 3 Pro by 4.387.683.3+4.3
- simple_safety_testso3 by 1.597.599+1.5
- anthropic_red_teamo3 by 1.29798.3+1.2
- bbqtie98.497.9tie
- XSTesttie97.397.3tie
Questions people ask
Which is better, Gemini 3 Pro or o3?
Gemini 3 Pro wins six of the seven areas where both have results: coding, agents, reasoning, facts, images and charts and long documents. o3 wins none, but costs 29% less. They are level on following instructions.
Which is better for coding?
Gemini 3 Pro. It wins 3 of the 3 coding tests both models report; o3 wins none.
Which is cheaper?
Gemini 3 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; o3 costs $2.00 and $8.00. That makes o3 about 29% cheaper for the same work.
How do you compare the two?
We use the 43 benchmark tests both models have published scores on. The verdict counts the 21 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 22 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.