Gemini 2.5 Pro vs GPT-5 nano
Wins 5 of 8 areas
Coding · Reasoning · Facts · Images and charts · Long documents
Wins 2 of 8 areas
Agents · Following instructions
Gemini 2.5 Pro is the stronger all-rounder.GPT-5 nano is cheaper and better at agents.
Scores updated · 37 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. 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 2.5 Pro4 of 4 tests
- CodingWriting and fixing software30Gemini 2.5 Pro3 of 3 tests
- FactsGetting facts right instead of making them up31Gemini 2.5 Pro3 of 4 tests
- Images and chartsUnderstanding pictures, charts and video20Gemini 2.5 Pro2 of 2 tests
- Long documentsFinding answers in very long texts10Gemini 2.5 Pro1 of 1 test
- AgentsCarrying out multi-step tasks on its own01GPT-5 nano1 of 1 test
- Following instructionsDoing exactly what it is asked01GPT-5 nano1 of 1 test
- MathCompetition and research-level math11Even1 each
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.
GPT-5 nano costs 96% 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+44.3points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+28.4points ahead
- Reasons across sets of long documentsAA-LCR+24points ahead
Where GPT-5 nano pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+31.9points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+18.9points ahead
Every test, side by side
All 37 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 2.5 Pro
- SWE-bench VerifiedGemini 2.5 Pro by 28.463.234.8+28.4
- Terminal-Bench HardGemini 2.5 Pro by 14.426.512.1+14.4
- SciCodeGemini 2.5 Pro by 9.746.336.6+9.7
ReasoningGemini 2.5 Pro
- GPQA DiamondGemini 2.5 Pro by 1683.667.6+16
- Humanity's Last ExamGemini 2.5 Pro by 8.5189.5+8.5
- CritPtGemini 2.5 Pro by 2.62.60+2.6
- ARC-AGI-2Gemini 2.5 Pro by 2.34.92.6+2.3
FactsGemini 2.5 Pro
- SimpleQA VerifiedGemini 2.5 Pro by 44.35611.7+44.3
- AA-Omniscience · Non-hallucinationGPT-5 nano by 31.99.141+31.9
- AA-Omniscience · AccuracyGemini 2.5 Pro by 203919.1+20
- Vectara HHEM hallucination ratelower is betterGemini 2.5 Pro by 3.5710.5+3.5
Images and chartsGemini 2.5 Pro
- MMMU-ProGemini 2.5 Pro by 13.974.961+13.9
- LMArena · VisionGemini 2.5 Pro by 104 rating points12631159+104 rating
MathEven
- FrontierMath Tiers 1-3 (v2)Gemini 2.5 Pro by 4.624.620+4.6
- FrontierMath Tier 4GPT-5 nano by 2.402.4+2.4
Following instructionsGPT-5 nano
- IFBenchGPT-5 nano by 18.948.767.6+18.9
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.
- HarmBenchGPT-5 nano by 3365.498.4+33
- Artificial Analysis Coding IndexGemini 2.5 Pro by 26.446.720.3+26.4
- ARC-AGI-1Gemini 2.5 Pro by 20.33716.7+20.3
- AA Agentic IndexGPT-5 nano by 19.73.523.2+19.7
- τ²-Bench Telecom (AA run)Gemini 2.5 Pro by 17.654.136.5+17.6
- AIR-Bench 2024GPT-5 nano by 14.273.687.8+14.2
- AA-OmniscienceGemini 2.5 Pro by 12.4-16.4-28.7+12.4
- HMMT 2025GPT-5 nano by 9.965.775.6+9.9
- vectara_factual_consistencyGemini 2.5 Pro by 3.59389.5+3.5
- simple_safety_testsGPT-5 nano by 397100+3
- AIME 2025GPT-5 nano by 2.28385.2+2.2
- frontiermath_tier_4_v1Gemini 2.5 Pro by 2.14.22.1+2.1
- AA IntelligenceGemini 2.5 Pro by 21513+2
- HMMT Nov. 2025GPT-5 nano by 1.78081.7+1.7
- bbqGPT-5 nano by 1.296.497.6+1.2
- XSTestGemini 2.5 Pro by 1.198.797.6+1.1
- vectara_answer_ratetie99.1100tie
- anthropic_red_teamtie99.599.5tie
- vectara_avg_summary_lengthtie106.4105.7tie
Questions people ask
Which is better, Gemini 2.5 Pro or GPT-5 nano?
Gemini 2.5 Pro wins five of the eight areas we test: coding, reasoning, facts, images and charts and long documents. GPT-5 nano wins agents and following instructions, and costs 96% less. They are level on math.
Which is better for coding?
Gemini 2.5 Pro. It wins 3 of the 3 coding tests both models report; GPT-5 nano wins none.
Which is cheaper?
Gemini 2.5 Pro costs $1.25 per million input tokens and $10.00 per million output tokens; GPT-5 nano costs $0.05 and $0.40. That makes GPT-5 nano about 96% cheaper for the same work.
How do you compare the two?
We use the 37 benchmark tests both models have published scores on. The verdict counts the 18 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.