Claude Opus 4.5 vs GPT-5.1
Wins 2 of 7 areas
Coding · Reasoning
Wins 3 of 7 areas
Images and charts · Long documents · Following instructions
GPT-5.1 wins more areas, narrowly.Claude Opus 4.5 is better at coding.
Scores updated · 42 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.
- Images and chartsUnderstanding pictures, charts and video02GPT-5.12 of 2 tests
- Following instructionsDoing exactly what it is asked02GPT-5.12 of 2 tests
- Long documentsFinding answers in very long texts01GPT-5.11 of 1 test
- CodingWriting and fixing software41Claude Opus 4.54 of 5 tests
- ReasoningHard problems that need careful thinking20Claude Opus 4.52 of 4 tests · 2 ties
- AgentsCarrying out multi-step tasks on its own11Even1 each
- FactsGetting facts right instead of making them up22Even2 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-5.1 costs 63% 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-5.1 pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+14.9points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+13.8points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+9.1points ahead
Where Claude Opus 4.5 pulls ahead
- Real work tasks from 44 professionsGDPVal+30.8points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+20points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+8.9points ahead
Every test, side by side
All 42 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.5
- LMArena · WebDevClaude Opus 4.5 by 74 rating points14691395+74 rating
- SciCodeClaude Opus 4.5 by 6.249.543.3+6.2
- SWE-bench VerifiedClaude Opus 4.5 by 4.680.976.3+4.6
- LiveCodeBench v6GPT-5.1 by 2.284.887+2.2
- Terminal-Bench HardClaude Opus 4.5 by 1.54745.5+1.5
AgentsEven
- GDPValClaude Opus 4.5 by 30.847.316.5+30.8
- BrowseCompGPT-5.1 by 13.83750.8+13.8
ReasoningClaude Opus 4.5
- ARC-AGI-2Claude Opus 4.5 by 2037.617.6+20
- Humanity's Last ExamClaude Opus 4.5 by 1.630.128.5+1.6
- GPQA Diamondtie86.687.3tie
- CritPttie4.64.9tie
FactsEven
- AA-Omniscience · Non-hallucinationGPT-5.1 by 9.13948.1+9.1
- AA-Omniscience · AccuracyClaude Opus 4.5 by 8.946.637.7+8.9
- SimpleQA VerifiedGPT-5.1 by 2.345.748+2.3
- Vectara HHEM hallucination ratelower is betterClaude Opus 4.5 by 1.210.912.1+1.2
Images and chartsGPT-5.1
Following instructionsGPT-5.1
- IFBenchGPT-5.1 by 14.95872.9+14.9
- Multi-ChallengeGPT-5.1 by 4.45963.4+4.4
Other results22 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 Agentic IndexClaude Opus 4.5 by 3859.621.6+38
- ARC-AGI-2 (Verified)Claude Opus 4.5 by 2037.617.6+20
- τ²-BenchClaude Opus 4.5 by 15.598.282.7+15.5
- vectara_avg_summary_lengthGPT-5.1 by 139.9 rating points114.5254.4+139.9 rating
- Terminal-Bench 2.0Claude Opus 4.5 by 11.759.347.6+11.7
- τ²-Bench (Retail)Claude Opus 4.5 by 1188.977.9+11
- ARC-AGI-1Claude Opus 4.5 by 9.28272.8+9.2
- AA-OmniscienceClaude Opus 4.5 by 8.6145.4+8.6
- swe_bench_bashClaude Opus 4.5 by 8.474.466+8.4
- frontiermath_tier_4_v1GPT-5.1 by 8.34.212.5+8.3
- τ²-Bench Telecom (AA run)Claude Opus 4.5 by 7.689.581.9+7.6
- MMMU (validation)GPT-5.1 by 4.780.785.4+4.7
- AA IntelligenceClaude Opus 4.5 by 4.429.124.7+4.4
- HMMT Feb. 2025GPT-5.1 by 3.492.996.3+3.4
- MMLU-ProClaude Opus 4.5 by 2.589.587+2.5
- Artificial Analysis Coding IndexGPT-5.1 by 1.647.849.4+1.6
- HMMT Nov. 2025Claude Opus 4.5 by 1.693.391.7+1.6
- vectara_answer_rateGPT-5.1 by 1.398.7100+1.3
- AIME 2025GPT-5.1 by 1.292.894+1.2
- vectara_factual_consistencyClaude Opus 4.5 by 1.289.187.9+1.2
- HLE (with tools)tie43.242.7tie
- MMMLUtie90.891tie
Questions people ask
Which is better, Claude Opus 4.5 or GPT-5.1?
GPT-5.1 wins three of the seven areas where both have results: images and charts, long documents and following instructions. Claude Opus 4.5 wins coding and reasoning. They are level on agents and facts.
Which is better for coding?
Claude Opus 4.5. It wins 4 of the 5 coding tests both models report; GPT-5.1 wins 1.
Which is cheaper?
Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; GPT-5.1 costs $1.25 and $10.00. That makes GPT-5.1 about 63% cheaper for the same work.
How do you compare the two?
We use the 42 benchmark tests both models have published scores on. The verdict counts the 20 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 22 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.