GPT-5.1 vs GPT-5 mini
Wins 6 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Long documents
Wins 0 of 7 areas
—
GPT-5.1 is the stronger all-rounder.GPT-5 mini is cheaper.
Scores updated · 40 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 software40GPT-5.14 of 4 tests
- ReasoningHard problems that need careful thinking40GPT-5.14 of 4 tests
- FactsGetting facts right instead of making them up30GPT-5.13 of 4 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video20GPT-5.12 of 2 tests
- AgentsCarrying out multi-step tasks on its own10GPT-5.11 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts10GPT-5.11 of 1 test
- Following instructionsDoing exactly what it is asked11Even1 each
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.
GPT-5 mini costs 80% 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
- Command-line tasks in a real terminalTerminal-Bench 2.1+48.7points ahead
- Short factual questions, answered correctlySimpleQA Verified+26.4points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+16.5points ahead
Where GPT-5 mini pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+2.5points ahead
Every test, side by side
All 40 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.1
- Terminal-Bench 2.1GPT-5.1 by 48.752.43.7+48.7
- SWE-bench VerifiedGPT-5.1 by 16.576.359.8+16.5
- Terminal-Bench HardGPT-5.1 by 12.245.533.3+12.2
- SciCodeGPT-5.1 by 4.343.339+4.3
ReasoningGPT-5.1
- ARC-AGI-2GPT-5.1 by 13.217.64.4+13.2
- Humanity's Last ExamGPT-5.1 by 728.521.5+7
- CritPtGPT-5.1 by 4.94.90+4.9
- GPQA DiamondGPT-5.1 by 4.587.382.8+4.5
FactsGPT-5.1
- SimpleQA VerifiedGPT-5.1 by 26.44821.6+26.4
- AA-Omniscience · AccuracyGPT-5.1 by 12.737.725+12.7
- AA-Omniscience · Non-hallucinationGPT-5.1 by 4.548.143.6+4.5
- Vectara HHEM hallucination ratelower is bettertie12.112.9tie
Images and chartsGPT-5.1
- MMMU-ProGPT-5.1 by 5.475.570.1+5.4
- LMArena · VisionGPT-5.1 by 48 rating points12501202+48 rating
Following instructionsEven
- Multi-ChallengeGPT-5.1 by 4.463.459+4.4
- IFBenchGPT-5 mini by 2.572.975.4+2.5
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.
- Artificial Analysis Coding IndexGPT-5.1 by 33.849.415.6+33.8
- AA-OmniscienceGPT-5.1 by 22.75.4-17.3+22.7
- ARC-AGI-1GPT-5.1 by 18.572.854.3+18.5
- τ²-Bench Telecom (AA run)GPT-5.1 by 13.581.968.4+13.5
- AA Agentic IndexGPT-5.1 by 12.721.68.9+12.7
- vectara_avg_summary_lengthGPT-5.1 by 84.7 rating points254.4169.7+84.7 rating
- AA IntelligenceGPT-5.1 by 7.924.716.8+7.9
- bbqGPT-5 mini by 7.688.796.3+7.6
- HMMT Nov. 2025GPT-5.1 by 7.591.784.2+7.5
- frontiermath_tier_4_v1GPT-5.1 by 6.212.56.3+6.2
- swe_bench_bashGPT-5.1 by 6.26659.8+6.2
- FrontierMath (overall)GPT-5.1 by 4.626.722.1+4.6
- AIME 2025GPT-5.1 by 2.99491.1+2.9
- matharena_visual_math_overallGPT-5 mini by 1.376.978.2+1.3
- vectara_factual_consistencytie87.987.1tie
- AIR-Bench 2024tie86.285.7tie
- HarmBenchtie97.697.1tie
- XSTesttie98.297.7tie
- anthropic_red_teamtie99.599.1tie
- simple_safety_teststie99.8100tie
- vectara_answer_ratetie10099.9tie
Questions people ask
Which is better, GPT-5.1 or GPT-5 mini?
GPT-5.1 wins six of the seven areas where both have results: coding, agents, reasoning, facts, images and charts and long documents. GPT-5 mini wins none, but costs 80% less. They are level on following instructions.
Which is better for coding?
GPT-5.1. It wins 4 of the 4 coding tests both models report; GPT-5 mini wins none.
Which is cheaper?
GPT-5.1 costs $1.25 per million input tokens and $10.00 per million output tokens; GPT-5 mini costs $0.25 and $2.00. That makes GPT-5 mini about 80% cheaper for the same work.
How do you compare the two?
We use the 40 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 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.