Gemini 2.5 Pro vs o3-mini
Wins 6 of 7 areas
Coding · Agents · Reasoning · Facts · Math · Long documents
Wins 0 of 7 areas
—
Gemini 2.5 Pro is the stronger all-rounder.o3-mini is cheaper.
Scores updated · 44 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 2.5 Pro5 of 5 tests
- CodingWriting and fixing software40Gemini 2.5 Pro4 of 4 tests
- AgentsCarrying out multi-step tasks on its own10Gemini 2.5 Pro1 of 3 tests · 2 ties
- FactsGetting facts right instead of making them up21Gemini 2.5 Pro2 of 3 tests
- MathCompetition and research-level math10Gemini 2.5 Pro1 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts10Gemini 2.5 Pro1 of 1 test
- Following instructionsDoing exactly what it is asked11Even1 each
Long documents rests on a single test.
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-mini costs 51% 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 2.5 Pro pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+40.7points ahead
- Common-sense trick questionsSimpleBench+28.8points ahead
- Reasons across sets of long documentsAA-LCR+26points ahead
Where o3-mini pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+18.4points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+9.8points ahead
Every test, side by side
All 44 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 2.5 Pro
- Terminal-Bench 2.1Gemini 2.5 Pro by 2428.54.5+24
- Terminal-Bench HardGemini 2.5 Pro by 20.426.56.1+20.4
- SWE-bench VerifiedGemini 2.5 Pro by 13.963.249.3+13.9
- SciCodeGemini 2.5 Pro by 3.546.342.8+3.5
AgentsGemini 2.5 Pro
- τ-Bench V3 · BankingGemini 2.5 Pro by 4.59.75.2+4.5
- GDPValtie00tie
- Terminal-Bench 4.0tie00tie
ReasoningGemini 2.5 Pro
- SimpleBenchGemini 2.5 Pro by 28.851.622.8+28.8
- GPQA DiamondGemini 2.5 Pro by 6.383.677.3+6.3
- Humanity's Last ExamGemini 2.5 Pro by 61812+6
- CritPtGemini 2.5 Pro by 2.32.60.3+2.3
- ARC-AGI-2Gemini 2.5 Pro by 1.94.93+1.9
FactsGemini 2.5 Pro
- SimpleQA VerifiedGemini 2.5 Pro by 40.75615.3+40.7
- AA-Omniscience · AccuracyGemini 2.5 Pro by 17.83921.3+17.8
- AA-Omniscience · Non-hallucinationo3-mini by 9.89.118.9+9.8
MathGemini 2.5 Pro
- FrontierMath Tiers 1-3 (v2)Gemini 2.5 Pro by 624.618.6+6
- FrontierMath Tier 4tie00tie
Following instructionsEven
- IFBencho3-mini by 18.448.767.1+18.4
- Multi-ChallengeGemini 2.5 Pro by 13.753.639.9+13.7
Other results24 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.
- HMMT Feb. 2025Gemini 2.5 Pro by 52.580.828.3+52.5
- SimpleQAGemini 2.5 Pro by 35.850.815+35.8
- AIME 2025Gemini 2.5 Pro by 34.78348.3+34.7
- Artificial Analysis Coding IndexGemini 2.5 Pro by 30.446.716.3+30.4
- HarmBencho3-mini by 29.865.495.2+29.8
- AA-OmniscienceGemini 2.5 Pro by 26.3-16.4-42.6+26.3
- τ²-Bench Telecom (AA run)Gemini 2.5 Pro by 22.854.131.3+22.8
- usamo_2025Gemini 2.5 Pro by 22.324.42.1+22.3
- TAU-bench (airline)Gemini 2.5 Pro by 17.65032.4+17.6
- AIME 2024Gemini 2.5 Pro by 12.49279.6+12.4
- livecodebench_hardGemini 2.5 Pro by 1259.447.4+12
- Aider-PolyglotGemini 2.5 Pro by 9.876.566.7+9.8
- TAU-bench (retail)Gemini 2.5 Pro by 9.46757.6+9.4
- XSTestGemini 2.5 Pro by 4.698.794.1+4.6
- AA IntelligenceGemini 2.5 Pro by 41511+4
- LiveCodeBencho3-mini by 3.574.277.7+3.5
- livecodebench_mediumGemini 2.5 Pro by 3.190.687.5+3.1
- ARC-AGI-1Gemini 2.5 Pro by 2.53734.5+2.5
- bbqGemini 2.5 Pro by 2.396.494.1+2.3
- simple_safety_testso3-mini by 29799+2
- AIR-Bench 2024o3-mini by 1.373.674.9+1.3
- anthropic_red_teamtie99.598.6tie
- livecodebench_easytie98.899.1tie
- frontiermath_tier_4_v1tie4.24.2tie
Questions people ask
Which is better, Gemini 2.5 Pro or o3-mini?
Gemini 2.5 Pro wins six of the seven areas where both have results: coding, agents, reasoning, facts, math and long documents. o3-mini wins none, but costs 51% less. They are level on following instructions.
Which is better for coding?
Gemini 2.5 Pro. It wins 4 of the 4 coding tests both models report; o3-mini wins none.
Which is cheaper?
Gemini 2.5 Pro costs $1.25 per million input tokens and $10.00 per million output tokens; o3-mini costs $1.10 and $4.40. That makes o3-mini about 51% cheaper for the same work.
How do you compare the two?
We use the 44 benchmark tests both models have published scores on. The verdict counts the 20 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 24 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.