GPT-5.1 vs GPT-5 nano
Wins 7 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Long documents · Following instructions
Wins 0 of 7 areas
—
GPT-5.1 is the stronger all-rounder.GPT-5 nano 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 thinking40GPT-5.14 of 4 tests
- CodingWriting and fixing software30GPT-5.13 of 3 tests
- FactsGetting facts right instead of making them up31GPT-5.13 of 4 tests
- Images and chartsUnderstanding pictures, charts and video20GPT-5.12 of 2 tests
- AgentsCarrying out multi-step tasks on its own10GPT-5.11 of 1 test
- Long documentsFinding answers in very long texts10GPT-5.11 of 1 test
- Following instructionsDoing exactly what it is asked10GPT-5.11 of 1 test
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-5.1 pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+41.5points ahead
- Short factual questions, answered correctlySimpleQA Verified+36.3points ahead
- Reasons across sets of long documentsAA-LCR+35points ahead
Where GPT-5 nano pulls ahead
No clear win on a test scored out of 100.
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.
CodingGPT-5.1
- SWE-bench VerifiedGPT-5.1 by 41.576.334.8+41.5
- Terminal-Bench HardGPT-5.1 by 33.445.512.1+33.4
- SciCodeGPT-5.1 by 6.743.336.6+6.7
ReasoningGPT-5.1
- GPQA DiamondGPT-5.1 by 19.787.367.6+19.7
- Humanity's Last ExamGPT-5.1 by 1928.59.5+19
- ARC-AGI-2GPT-5.1 by 1517.62.6+15
- CritPtGPT-5.1 by 4.94.90+4.9
FactsGPT-5.1
- SimpleQA VerifiedGPT-5.1 by 36.34811.7+36.3
- AA-Omniscience · AccuracyGPT-5.1 by 18.637.719.1+18.6
- AA-Omniscience · Non-hallucinationGPT-5.1 by 7.148.141+7.1
- Vectara HHEM hallucination ratelower is betterGPT-5 nano by 1.612.110.5+1.6
Images and chartsGPT-5.1
- MMMU-ProGPT-5.1 by 14.575.561+14.5
- LMArena · VisionGPT-5.1 by 91 rating points12501159+91 rating
Other results20 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-5.1 by 56.172.816.7+56.1
- τ²-Bench Telecom (AA run)GPT-5.1 by 45.481.936.5+45.4
- AA-OmniscienceGPT-5.1 by 34.15.4-28.7+34.1
- swe_bench_bashGPT-5.1 by 31.26634.8+31.2
- Artificial Analysis Coding IndexGPT-5.1 by 29.149.420.3+29.1
- FrontierMath (overall)GPT-5.1 by 17.126.79.6+17.1
- vectara_avg_summary_lengthGPT-5.1 by 148.7 rating points254.4105.7+148.7 rating
- AA IntelligenceGPT-5.1 by 11.724.713+11.7
- frontiermath_tier_4_v1GPT-5.1 by 10.412.52.1+10.4
- HMMT Nov. 2025GPT-5.1 by 1091.781.7+10
- bbqGPT-5 nano by 8.988.797.6+8.9
- AIME 2025GPT-5.1 by 8.89485.2+8.8
- AA Agentic IndexGPT-5 nano by 1.621.623.2+1.6
- AIR-Bench 2024GPT-5 nano by 1.686.287.8+1.6
- vectara_factual_consistencyGPT-5 nano by 1.687.989.5+1.6
- HarmBenchtie97.698.4tie
- XSTesttie98.297.6tie
- simple_safety_teststie99.8100tie
- anthropic_red_teamtie99.599.5tie
- vectara_answer_ratetie100100tie
Questions people ask
Which is better, GPT-5.1 or GPT-5 nano?
GPT-5.1 wins all seven areas where both have results: coding, agents, reasoning, facts, images and charts, long documents and following instructions. GPT-5 nano wins none, but costs 96% less.
Which is better for coding?
GPT-5.1. It wins 3 of the 3 coding tests both models report; GPT-5 nano wins none.
Which is cheaper?
GPT-5.1 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 36 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 20 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.