GPT-4.1 vs GPT-5 nano
Wins 5 of 8 areas
Coding · Agents · Facts · Images and charts · Long documents
Wins 3 of 8 areas
Reasoning · Math · Following instructions
GPT-4.1 is the stronger all-rounder.GPT-5 nano is cheaper and better at reasoning.
Scores updated · 34 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.
- CodingWriting and fixing software30GPT-4.13 of 3 tests
- FactsGetting facts right instead of making them up31GPT-4.13 of 4 tests
- Images and chartsUnderstanding pictures, charts and video10GPT-4.11 of 2 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own10GPT-4.11 of 1 test
- Long documentsFinding answers in very long texts10GPT-4.11 of 1 test
- ReasoningHard problems that need careful thinking02GPT-5 nano2 of 3 tests · 1 tie
- MathCompetition and research-level math01GPT-5 nano1 of 1 test
- Following instructionsDoing exactly what it is asked01GPT-5 nano1 of 1 test
Agents, math, 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 three tests each model wins by the widest margin. Scores are out of 100.
Where GPT-4.1 pulls ahead
- Reasons across sets of long documentsAA-LCR+23.3points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+19.8points ahead
- Short factual questions, answered correctlySimpleQA Verified+19.4points ahead
Where GPT-5 nano pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+34.3points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+24.6points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+14points ahead
Every test, side by side
All 34 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-4.1
- SWE-bench VerifiedGPT-4.1 by 19.854.634.8+19.8
- SciCodeGPT-4.1 by 1.538.136.6+1.5
- Terminal-Bench HardGPT-4.1 by 1.513.612.1+1.5
ReasoningGPT-5 nano
- Humanity's Last ExamGPT-5 nano by 5.34.29.5+5.3
- GPQA DiamondGPT-5 nano by 166.667.6+1
- CritPttie00tie
FactsGPT-4.1
- AA-Omniscience · Non-hallucinationGPT-5 nano by 34.36.741+34.3
- SimpleQA VerifiedGPT-4.1 by 19.431.111.7+19.4
- AA-Omniscience · AccuracyGPT-4.1 by 8.727.819.1+8.7
- Vectara HHEM hallucination ratelower is betterGPT-4.1 by 4.95.610.5+4.9
Images and chartsGPT-4.1
- LMArena · VisionGPT-4.1 by 51 rating points12101159+51 rating
- MMMU-Protie61.261tie
Following instructionsGPT-5 nano
- IFBenchGPT-5 nano by 24.64367.6+24.6
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.
- HMMT 2025GPT-5 nano by 46.728.975.6+46.7
- AIME 2025GPT-5 nano by 38.846.485.2+38.8
- AIR-Bench 2024GPT-5 nano by 2364.887.8+23
- ARC-AGI-1GPT-5 nano by 11.25.516.7+11.2
- AA-OmniscienceGPT-5 nano by 10.9-39.6-28.7+10.9
- τ²-Bench Telecom (AA run)GPT-4.1 by 10.647.136.5+10.6
- HarmBenchGPT-5 nano by 6.791.798.4+6.7
- bbqGPT-5 nano by 592.697.6+5
- vectara_factual_consistencyGPT-4.1 by 4.994.489.5+4.9
- AA Agentic IndexGPT-4.1 by 4.127.323.2+4.1
- frontiermath_tier_4_v1GPT-5 nano by 2.102.1+2.1
- Artificial Analysis Coding IndexGPT-4.1 by 1.521.820.3+1.5
- vectara_avg_summary_lengthGPT-5 nano by 14 rating points91.7105.7+14 rating
- AA Intelligencetie12.713tie
- anthropic_red_teamtie99.399.5tie
- XSTesttie97.997.6tie
- vectara_answer_ratetie99.9100tie
- simple_safety_teststie100100tie
Questions people ask
Which is better, GPT-4.1 or GPT-5 nano?
GPT-4.1 wins five of the eight areas we test: coding, agents, facts, images and charts and long documents. GPT-5 nano wins reasoning, math and following instructions, and costs 96% less.
Which is better for coding?
GPT-4.1. It wins 3 of the 3 coding tests both models report; GPT-5 nano wins none.
Which is cheaper?
GPT-4.1 costs $2.00 per million input tokens and $8.00 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 34 benchmark tests both models have published scores on. The verdict counts the 16 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.