Gemini 3 Pro vs o1
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.
Scores updated · 33 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 thinking40Gemini 3 Pro4 of 4 tests
- CodingWriting and fixing software30Gemini 3 Pro3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video20Gemini 3 Pro2 of 2 tests
- FactsGetting facts right instead of making them up21Gemini 3 Pro2 of 3 tests
- AgentsCarrying out multi-step tasks on its own10Gemini 3 Pro1 of 1 test
- Long documentsFinding answers in very long texts10Gemini 3 Pro1 of 1 test
- Following instructionsDoing exactly what it is asked00Even0 each · 1 tie
Agents, long documents and following instructions rest on a single test 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.
Gemini 3 Pro costs 81% 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
- Common-sense trick questionsSimpleBench+36.3points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+34.9points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+32.7points ahead
Where o1 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+21.9points ahead
Every test, side by side
All 33 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 3 Pro
- SWE-bench VerifiedGemini 3 Pro by 34.976.241.3+34.9
- Terminal-Bench HardGemini 3 Pro by 28.841.712.9+28.8
- SciCodeGemini 3 Pro by 20.356.135.8+20.3
ReasoningGemini 3 Pro
- SimpleBenchGemini 3 Pro by 36.376.440.1+36.3
- Humanity's Last ExamGemini 3 Pro by 32.739.77+32.7
- GPQA DiamondGemini 3 Pro by 16.190.874.7+16.1
- CritPtGemini 3 Pro by 8.89.10.3+8.8
FactsGemini 3 Pro
- SimpleQA VerifiedGemini 3 Pro by 31.872.941.1+31.8
- AA-Omniscience · Non-hallucinationo1 by 21.98.530.4+21.9
- AA-Omniscience · AccuracyGemini 3 Pro by 21.355.834.5+21.3
Images and chartsGemini 3 Pro
- MathVistaGemini 3 Pro by 1889.871.8+18
- LMArena · VisionGemini 3 Pro by 137 rating points13051168+137 rating
Other results18 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.
- metr_re_benchGemini 3 Pro by 35350+35
- SimpleQAGemini 3 Pro by 29.772.142.4+29.7
- metr_hcastGemini 3 Pro by 28.771.342.6+28.7
- AA-OmniscienceGemini 3 Pro by 26.315.3-11.1+26.3
- τ²-Bench Telecom (AA run)Gemini 3 Pro by 24.587.162.6+24.5
- HarmBencho1 by 23.872.596.3+23.8
- LiveBenchGemini 3 Pro by 21.173.452.3+21.1
- AA Agentic IndexGemini 3 Pro by 20.95231.1+20.9
- AIME 2025Gemini 3 Pro by 18.310081.7+18.3
- AA IntelligenceGemini 3 Pro by 12.82815.2+12.8
- AIR-Bench 2024o1 by 6.873.280+6.8
- Artificial Analysis Coding IndexGemini 3 Pro by 6.846.539.7+6.8
- MMMLUGemini 3 Pro by 4.191.887.7+4.1
- simple_safety_testso1 by 1.597.599+1.5
- anthropic_red_teamo1 by 1.29798.3+1.2
- bbqGemini 3 Pro by 1.198.497.3+1.1
- metr_swaatie99.5100tie
- XSTesttie97.397tie
Questions people ask
Which is better, Gemini 3 Pro or o1?
Gemini 3 Pro wins six of the seven areas where both have results: coding, agents, reasoning, facts, images and charts and long documents. o1 wins none. 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; o1 wins none.
Which is cheaper?
Gemini 3 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; o1 costs $15.00 and $60.00. That makes Gemini 3 Pro about 81% cheaper for the same work.
How do you compare the two?
We use the 33 benchmark tests both models have published scores on. The verdict counts the 15 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 18 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.