GPT-5.1 vs GPT-5.4
Wins 0 of 7 areas
—
Wins 6 of 7 areas
Coding · Agents · Reasoning · Images and charts · Long documents · Following instructions
GPT-5.4 is the stronger all-rounder.GPT-5.1 is cheaper.
Scores updated · 43 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.
- CodingWriting and fixing software04GPT-5.44 of 4 tests
- ReasoningHard problems that need careful thinking04GPT-5.44 of 4 tests
- AgentsCarrying out multi-step tasks on its own03GPT-5.43 of 3 tests
- Images and chartsUnderstanding pictures, charts and video02GPT-5.42 of 2 tests
- Long documentsFinding answers in very long texts01GPT-5.41 of 1 test
- Following instructionsDoing exactly what it is asked01GPT-5.41 of 1 test
- FactsGetting facts right instead of making them up22Even2 each
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-5.1 costs 36% 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-5.4 pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+55.7points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+31.9points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+25.9points ahead
Where GPT-5.1 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+39.8points ahead
- Short factual questions, answered correctlySimpleQA Verified+2.9points ahead
Every test, side by side
All 43 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.4
- Terminal-Bench 2.1GPT-5.4 by 25.952.478.3+25.9
- SciCodeGPT-5.4 by 13.343.356.6+13.3
- Terminal-Bench HardGPT-5.4 by 12.145.557.6+12.1
- LMArena · WebDevGPT-5.4 by 70 rating points13951465+70 rating
AgentsGPT-5.4
- BrowseCompGPT-5.4 by 31.950.882.7+31.9
- τ-Bench V3 · BankingGPT-5.4 by 23.715.939.6+23.7
- GDPValGPT-5.4 by 20.916.537.4+20.9
ReasoningGPT-5.4
- ARC-AGI-2GPT-5.4 by 55.717.673.3+55.7
- CritPtGPT-5.4 by 18.54.923.4+18.5
- Humanity's Last ExamGPT-5.4 by 15.228.543.7+15.2
- GPQA DiamondGPT-5.4 by 4.787.392+4.7
FactsEven
- AA-Omniscience · Non-hallucinationGPT-5.1 by 39.848.18.3+39.8
- AA-Omniscience · AccuracyGPT-5.4 by 13.237.750.9+13.2
- Vectara HHEM hallucination ratelower is betterGPT-5.4 by 5.112.17+5.1
- SimpleQA VerifiedGPT-5.1 by 2.94845.1+2.9
Images and chartsGPT-5.4
- LMArena · VisionGPT-5.4 by 52 rating points12501302+52 rating
- MMMU-ProGPT-5.4 by 2.975.578.4+2.9
Other results24 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.
- Terminal-Bench 2.0GPT-5.4 by 27.547.675.1+27.5
- AA Agentic IndexGPT-5.4 by 22.621.644.2+22.6
- Artificial Analysis Coding IndexGPT-5.4 by 21.749.471.1+21.7
- ARC-AGI-1GPT-5.4 by 20.972.893.7+20.9
- FrontierMath (overall)GPT-5.4 by 20.926.747.6+20.9
- vectara_avg_summary_lengthGPT-5.1 by 172.7 rating points254.481.7+172.7 rating
- matharena_visual_math_overallGPT-5.4 by 15.676.992.5+15.6
- frontiermath_tier_4_v1GPT-5.4 by 14.612.527.1+14.6
- AA IntelligenceGPT-5.4 by 14.324.739+14.3
- HLE (with tools)GPT-5.4 by 9.342.752+9.3
- HealthBench Professional length-adjustedGPT-5.4 by 8.539.648.1+8.5
- τ²-Bench Telecom (AA run)GPT-5.4 by 5.281.987.1+5.2
- vectara_factual_consistencyGPT-5.4 by 5.187.993+5.1
- HMMT Nov. 2025GPT-5.4 by 4.191.795.8+4.1
- HealthBench Hard length-adjustedGPT-5.4 by 3.725.429.1+3.7
- HealthBench length-adjustedGPT-5.4 by 3.150.954+3.1
- HealthBench Consensus length-adjustedGPT-5.4 by 1.39596.3+1.3
- MMLU-Protie8787.5tie
- AA-Omnisciencetie5.45.8tie
- vectara_answer_ratetie10099.9tie
- Image input eval - extremism (not_unsafe)tie11tie
- Image input eval - harms-erotic (not_unsafe)tie11tie
- Image input eval - hate (not_unsafe)tie11tie
- Image input eval - self-harm (not_unsafe)tie11tie
Questions people ask
Which is better, GPT-5.1 or GPT-5.4?
GPT-5.4 wins six of the seven areas where both have results: coding, agents, reasoning, images and charts, long documents and following instructions. GPT-5.1 wins none, but costs 36% less. They are level on facts.
Which is better for coding?
GPT-5.4. It wins 4 of the 4 coding tests both models report; GPT-5.1 wins none.
Which is cheaper?
GPT-5.1 costs $1.25 per million input tokens and $10.00 per million output tokens; GPT-5.4 costs $2.50 and $15.00. That makes GPT-5.1 about 36% cheaper for the same work.
How do you compare the two?
We use the 43 benchmark tests both models have published scores on. The verdict counts the 19 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 24 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.