Gemini 3 Pro vs GPT-5 mini
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.GPT-5 mini is cheaper.
Scores updated · 36 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 4 tests · 1 tie
- 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 asked11Even1 each
Agents and long documents 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.
GPT-5 mini costs 84% 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
- Short factual questions, answered correctlySimpleQA Verified+51.3points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+30.8points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+26.7points ahead
Where GPT-5 mini pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+35.1points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+5points ahead
Every test, side by side
All 36 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 17.156.139+17.1
- SWE-bench VerifiedGemini 3 Pro by 16.476.259.8+16.4
- Terminal-Bench HardGemini 3 Pro by 8.441.733.3+8.4
ReasoningGemini 3 Pro
- ARC-AGI-2Gemini 3 Pro by 26.731.14.4+26.7
- Humanity's Last ExamGemini 3 Pro by 18.239.721.5+18.2
- CritPtGemini 3 Pro by 9.19.10+9.1
- GPQA DiamondGemini 3 Pro by 890.882.8+8
FactsGemini 3 Pro
- SimpleQA VerifiedGemini 3 Pro by 51.372.921.6+51.3
- AA-Omniscience · Non-hallucinationGPT-5 mini by 35.18.543.6+35.1
- AA-Omniscience · AccuracyGemini 3 Pro by 30.855.825+30.8
- Vectara HHEM hallucination ratelower is bettertie13.612.9tie
Images and chartsGemini 3 Pro
- LMArena · VisionGemini 3 Pro by 103 rating points13051202+103 rating
- MMMU-ProGemini 3 Pro by 10.180.270.1+10.1
Following instructionsEven
- Multi-ChallengeGemini 3 Pro by 6.765.759+6.7
- IFBenchGPT-5 mini by 570.475.4+5
Other results19 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 Agentic IndexGemini 3 Pro by 43.1528.9+43.1
- AA-OmniscienceGemini 3 Pro by 32.615.3-17.3+32.6
- Artificial Analysis Coding IndexGemini 3 Pro by 30.946.515.6+30.9
- HarmBenchGPT-5 mini by 24.672.597.1+24.6
- ARC-AGI-1Gemini 3 Pro by 20.77554.3+20.7
- τ²-Bench Telecom (AA run)Gemini 3 Pro by 18.787.168.4+18.7
- AIR-Bench 2024GPT-5 mini by 12.573.285.7+12.5
- frontiermath_tier_4_v1Gemini 3 Pro by 12.518.86.3+12.5
- AA IntelligenceGemini 3 Pro by 11.22816.8+11.2
- HMMT Nov. 2025Gemini 3 Pro by 9.193.384.2+9.1
- AIME 2025Gemini 3 Pro by 8.910091.1+8.9
- vectara_avg_summary_lengthGPT-5 mini by 67.8 rating points101.9169.7+67.8 rating
- matharena_visual_math_overallGemini 3 Pro by 684.278.2+6
- simple_safety_testsGPT-5 mini by 2.597.5100+2.5
- bbqGemini 3 Pro by 2.198.496.3+2.1
- anthropic_red_teamGPT-5 mini by 29799.1+2
- vectara_factual_consistencytie86.487.1tie
- vectara_answer_ratetie99.499.9tie
- XSTesttie97.397.7tie
Questions people ask
Which is better, Gemini 3 Pro or GPT-5 mini?
Gemini 3 Pro wins six of the seven areas where both have results: coding, agents, reasoning, facts, images and charts and long documents. GPT-5 mini wins none, but costs 84% 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; GPT-5 mini wins none.
Which is cheaper?
Gemini 3 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; GPT-5 mini costs $0.25 and $2.00. That makes GPT-5 mini about 84% cheaper for the same work.
How do you compare the two?
We use the 36 benchmark tests both models have published scores on. The verdict counts the 17 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 19 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.