GPT-5.1 vs o3
Wins 6 of 7 areas
Coding · Agents · Reasoning · Images and charts · Long documents · Following instructions
Wins 0 of 7 areas
—
GPT-5.1 is the stronger all-rounder.o3 is cheaper.
Scores updated · 38 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 5 tests · 1 tie
- CodingWriting and fixing software30GPT-5.13 of 3 tests
- Images and chartsUnderstanding pictures, charts and video30GPT-5.13 of 3 tests
- AgentsCarrying out multi-step tasks on its own20GPT-5.12 of 2 tests
- Following instructionsDoing exactly what it is asked20GPT-5.12 of 2 tests
- Long documentsFinding answers in very long texts10GPT-5.11 of 1 test
- FactsGetting facts right instead of making them up11Even1 each · 1 tie
Long documents rests on a single test.
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.
o3 costs 11% 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
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+36.2points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+11.1points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+8.4points ahead
Where o3 pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+1.4points ahead
Every test, side by side
All 38 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.1
- Terminal-Bench HardGPT-5.1 by 8.445.537.1+8.4
- SWE-bench VerifiedGPT-5.1 by 7.276.369.1+7.2
- SciCodeGPT-5.1 by 2.343.341+2.3
AgentsGPT-5.1
- GDPValGPT-5.1 by 3.716.512.8+3.7
- BrowseCompGPT-5.1 by 1.150.849.7+1.1
ReasoningGPT-5.1
- ARC-AGI-2GPT-5.1 by 11.117.66.5+11.1
- Humanity's Last ExamGPT-5.1 by 8.428.520.1+8.4
- GPQA DiamondGPT-5.1 by 4.687.382.7+4.6
- CritPtGPT-5.1 by 3.84.91.1+3.8
- SimpleBenchtie53.253.1tie
FactsEven
- AA-Omniscience · Non-hallucinationGPT-5.1 by 36.248.111.9+36.2
- SimpleQA Verifiedo3 by 1.44849.4+1.4
- AA-Omniscience · Accuracytie37.738.6tie
Images and chartsGPT-5.1
- MMMU-ProGPT-5.1 by 5.475.570.1+5.4
- LMArena · VisionGPT-5.1 by 36 rating points12501214+36 rating
- MMMUGPT-5.1 by 2.585.482.9+2.5
Following instructionsGPT-5.1
- Multi-ChallengeGPT-5.1 by 363.460.4+3
- IFBenchGPT-5.1 by 1.572.971.4+1.5
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.
- AA-OmniscienceGPT-5.1 by 20.95.4-15.6+20.9
- HMMT Feb. 2025GPT-5.1 by 18.896.377.5+18.8
- AA Agentic Indexo3 by 14.521.636.1+14.5
- ARC-AGI-1GPT-5.1 by 1272.860.8+12
- Artificial Analysis Coding IndexGPT-5.1 by 1149.438.4+11
- FrontierMath (overall)GPT-5.1 by 10.926.715.8+10.9
- frontiermath_tier_4_v1GPT-5.1 by 10.412.52.1+10.4
- bbqo3 by 9.288.797.9+9.2
- AIME 2025GPT-5.1 by 7.69486.4+7.6
- AA IntelligenceGPT-5.1 by 4.524.720.2+4.5
- τ²-Bench (Retail)o3 by 2.377.980.2+2.3
- Tau2 airlineGPT-5.1 by 2.26764.8+2.2
- MMLU-ProGPT-5.1 by 28785+2
- AIR-Bench 2024GPT-5.1 by 1.786.284.5+1.7
- anthropic_red_teamGPT-5.1 by 1.299.598.3+1.2
- τ²-Bench Telecom (AA run)GPT-5.1 by 1.281.980.7+1.2
- XSTesttie98.297.3tie
- HarmBenchtie97.698.4tie
- simple_safety_teststie99.899tie
Questions people ask
Which is better, GPT-5.1 or o3?
GPT-5.1 wins six of the seven areas where both have results: coding, agents, reasoning, images and charts, long documents and following instructions. o3 wins none, but costs 11% less. They are level on facts.
Which is better for coding?
GPT-5.1. It wins 3 of the 3 coding tests both models report; o3 wins none.
Which is cheaper?
GPT-5.1 costs $1.25 per million input tokens and $10.00 per million output tokens; o3 costs $2.00 and $8.00. That makes o3 about 11% cheaper for the same work.
How do you compare the two?
We use the 38 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 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.