Claude Opus 5.5 vs GPT-5.2
Wins 8 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents · Following instructions
Wins 0 of 8 areas
—
Claude Opus 5.5 is the stronger all-rounder.GPT-5.2 is cheaper.
Scores updated · 34 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. 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 software60Claude Opus 5.56 of 6 tests
- ReasoningHard problems that need careful thinking50Claude Opus 5.55 of 5 tests
- FactsGetting facts right instead of making them up30Claude Opus 5.53 of 4 tests · 1 tie
- MathCompetition and research-level math30Claude Opus 5.53 of 3 tests
- Images and chartsUnderstanding pictures, charts and video20Claude Opus 5.52 of 2 tests
- AgentsCarrying out multi-step tasks on its own10Claude Opus 5.51 of 1 test
- Long documentsFinding answers in very long texts10Claude Opus 5.51 of 1 test
- Following instructionsDoing exactly what it is asked10Claude Opus 5.51 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-5.2 costs 34% 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 Claude Opus 5.5 pulls ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+63.3points ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+60points ahead
- Common-sense trick questionsSimpleBench+42.6points ahead
Where GPT-5.2 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 34 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 5.5
- SWE-bench ProClaude Opus 5.5 by 6089.929.9+60
- LMArena · WebDevClaude Opus 5.5 by 390 rating points18071417+390 rating
- SWE-bench MultilingualClaude Opus 5.5 by 27.293.966.7+27.2
- LiveBench · Agentic CodingClaude Opus 5.5 by 21.471.750.3+21.4
- SciCodeClaude Opus 5.5 by 14.866.952.1+14.8
- LiveBench · CodingClaude Opus 5.5 by 13.289.376.1+13.2
ReasoningClaude Opus 5.5
- SimpleBenchClaude Opus 5.5 by 42.688.445.8+42.6
- ARC-AGI-2Claude Opus 5.5 by 38.891.752.9+38.8
- Humanity's Last ExamClaude Opus 5.5 by 23.761.437.7+23.7
- CritPtClaude Opus 5.5 by 20.131.711.6+20.1
- LiveBench · ReasoningClaude Opus 5.5 by 992.283.2+9
FactsClaude Opus 5.5
- SimpleQA VerifiedClaude Opus 5.5 by 35.172.237.1+35.1
- AA-Omniscience · Non-hallucinationClaude Opus 5.5 by 22.641.418.8+22.6
- AA-Omniscience · AccuracyClaude Opus 5.5 by 21.966.244.3+21.9
- Vectara HHEM hallucination ratelower is bettertie9.910.8tie
Images and chartsClaude Opus 5.5
- MMMU-ProClaude Opus 5.5 by 13.187.774.6+13.1
- LMArena · VisionClaude Opus 5.5 by 75 rating points13211246+75 rating
MathClaude Opus 5.5
- FrontierMath Tier 4Claude Opus 5.5 by 63.39531.7+63.3
- FrontierMath Tiers 1-3 (v2)Claude Opus 5.5 by 23.891.267.4+23.8
- LiveBench · MathematicsClaude Opus 5.5 by 3.997.193.2+3.9
Following instructionsClaude Opus 5.5
- LiveBench · Instruction FollowingClaude Opus 5.5 by 3.965.761.8+3.9
Other results11 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-OmniscienceClaude Opus 5.5 by 47.346.4-0.9+47.3
- GDPval-AA (Elo)Claude Opus 5.5 by 358 rating points18201462+358 rating
- AA IntelligenceClaude Opus 5.5 by 27.257.630.4+27.2
- HLE (with tools)Claude Opus 5.5 by 22.267.745.5+22.2
- ARC-AGI-1Claude Opus 5.5 by 11.397.586.2+11.3
- livebench_languageClaude Opus 5.5 by 6.586.379.8+6.5
- HealthBench length-adjustedClaude Opus 5.5 by 3.860.656.8+3.8
- livebench_data_analysisClaude Opus 5.5 by 2.180.378.2+2.1
- vectara_factual_consistencytie90.189.2tie
- vectara_avg_summary_lengthtie192.1186.3tie
- vectara_answer_ratetie99.7100tie
Questions people ask
Which is better, Claude Opus 5.5 or GPT-5.2?
Claude Opus 5.5 wins all eight areas we test: coding, agents, reasoning, facts, images and charts, math, long documents and following instructions. GPT-5.2 wins none, but costs 34% less.
Which is better for coding?
Claude Opus 5.5. It wins 6 of the 6 coding tests both models report; GPT-5.2 wins none.
Which is cheaper?
Claude Opus 5.5 costs $4.00 per million input tokens and $20.00 per million output tokens; GPT-5.2 costs $1.75 and $14.00. That makes GPT-5.2 about 34% cheaper for the same work.
How do you compare the two?
We use the 34 benchmark tests both models have published scores on. The verdict counts the 23 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 11 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.