GPT-5 vs GPT-5 nano
Wins 7 of 8 areas
Coding · Agents · Reasoning · Images and charts · Math · Long documents · Following instructions
Wins 0 of 8 areas
—
GPT-5 is the stronger all-rounder.GPT-5 nano is cheaper.
Scores updated · 39 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 thinking40GPT-54 of 4 tests
- CodingWriting and fixing software30GPT-53 of 3 tests
- Images and chartsUnderstanding pictures, charts and video20GPT-52 of 2 tests
- MathCompetition and research-level math20GPT-52 of 2 tests
- AgentsCarrying out multi-step tasks on its own10GPT-51 of 1 test
- Long documentsFinding answers in very long texts10GPT-51 of 1 test
- Following instructionsDoing exactly what it is asked10GPT-51 of 1 test
- FactsGetting facts right instead of making them up22Even2 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 GPT-5 pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+40.1points ahead
- Short factual questions, answered correctlySimpleQA Verified+38.4points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+35.4points ahead
Where GPT-5 nano pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+23.2points ahead
Every test, side by side
All 39 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5
- SWE-bench VerifiedGPT-5 by 40.174.934.8+40.1
- Terminal-Bench HardGPT-5 by 20.532.612.1+20.5
- SciCodeGPT-5 by 6.342.936.6+6.3
ReasoningGPT-5
- Humanity's Last ExamGPT-5 by 1928.59.5+19
- GPQA DiamondGPT-5 by 17.885.467.6+17.8
- ARC-AGI-2GPT-5 by 7.39.92.6+7.3
- CritPtGPT-5 by 5.75.70+5.7
FactsEven
- SimpleQA VerifiedGPT-5 by 38.450.111.7+38.4
- AA-Omniscience · Non-hallucinationGPT-5 nano by 23.217.841+23.2
- AA-Omniscience · AccuracyGPT-5 by 21.240.319.1+21.2
- Vectara HHEM hallucination ratelower is betterGPT-5 nano by 4.615.110.5+4.6
Images and chartsGPT-5
- MMMU-ProGPT-5 by 13.274.261+13.2
- LMArena · VisionGPT-5 by 49 rating points12081159+49 rating
MathGPT-5
- FrontierMath Tiers 1-3 (v2)GPT-5 by 35.455.420+35.4
- FrontierMath Tier 4GPT-5 by 19.621.92.4+19.6
Other results21 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.
- ARC-AGI-1GPT-5 by 4965.716.7+49
- τ²-Bench Telecom (AA run)GPT-5 by 48.384.836.5+48.3
- swe_bench_bashGPT-5 by 30.26534.8+30.2
- AA-OmniscienceGPT-5 by 20-8.7-28.7+20
- HMMT 2025GPT-5 by 17.793.375.6+17.7
- Artificial Analysis Coding IndexGPT-5 by 17.537.820.3+17.5
- FrontierMath (overall)GPT-5 by 16.726.39.6+16.7
- frontiermath_tier_4_v1GPT-5 by 10.412.52.1+10.4
- AA IntelligenceGPT-5 by 102313+10
- AIME 2025GPT-5 by 9.494.685.2+9.4
- HMMT Nov. 2025GPT-5 by 7.589.281.7+7.5
- vectara_avg_summary_lengthGPT-5 by 57 rating points162.7105.7+57 rating
- vectara_factual_consistencyGPT-5 nano by 4.684.989.5+4.6
- AA Agentic IndexGPT-5 by 3.326.523.2+3.3
- bbqtie96.897.6tie
- HarmBenchtie97.698.4tie
- anthropic_red_teamtie99.199.5tie
- XSTesttie97.197.6tie
- simple_safety_teststie99.8100tie
- AIR-Bench 2024tie87.787.8tie
- vectara_answer_ratetie99.9100tie
Questions people ask
Which is better, GPT-5 or GPT-5 nano?
GPT-5 wins seven of the eight areas we test: coding, agents, reasoning, images and charts, math, long documents and following instructions. GPT-5 nano wins none, but costs 96% less. They are level on facts.
Which is better for coding?
GPT-5. It wins 3 of the 3 coding tests both models report; GPT-5 nano wins none.
Which is cheaper?
GPT-5 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 39 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 21 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.