Claude Opus 5.5 vs GPT-5.6 Luna
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-5.6 Luna 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 software50Claude Opus 5.55 of 5 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 3 tests
- MathCompetition and research-level math30Claude Opus 5.53 of 3 tests
- AgentsCarrying out multi-step tasks on its own21Claude Opus 5.52 of 3 tests
- Images and chartsUnderstanding pictures, charts and video10Claude 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
Images and charts, 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-5.6 Luna costs 94% 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
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+48points ahead
- Common-sense trick questionsSimpleBench+41.6points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+36.5points ahead
Where GPT-5.6 Luna pulls ahead
- Finds the root cause of IT system incidentsAA IT-Bench SRE+2.1points ahead
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
- LMArena · WebDevClaude Opus 5.5 by 297 rating points18151518+297 rating
- SWE-bench ProClaude Opus 5.5 by 27.289.962.7+27.2
- LiveBench · Agentic CodingClaude Opus 5.5 by 23.371.748.4+23.3
- SciCodeClaude Opus 5.5 by 13.366.953.6+13.3
- LiveBench · CodingClaude Opus 5.5 by 6.489.382.9+6.4
AgentsClaude Opus 5.5
- Terminal-Bench 4.0Claude Opus 5.5 by 4859.611.6+48
- GDPValClaude Opus 5.5 by 20.168.348.2+20.1
- AA IT-Bench SREGPT-5.6 Luna by 2.138.240.3+2.1
ReasoningClaude Opus 5.5
- SimpleBenchClaude Opus 5.5 by 41.688.446.8+41.6
- ARC-AGI-2Claude Opus 5.5 by 32.191.759.6+32.1
- Humanity's Last ExamClaude Opus 5.5 by 21.961.439.5+21.9
- CritPtClaude Opus 5.5 by 11.131.720.6+11.1
- LiveBench · ReasoningClaude Opus 5.5 by 6.692.285.6+6.6
FactsClaude Opus 5.5
- AA-Omniscience · Non-hallucinationClaude Opus 5.5 by 3441.47.4+34
- SimpleQA VerifiedClaude Opus 5.5 by 31.272.241+31.2
- AA-Omniscience · AccuracyClaude Opus 5.5 by 23.566.242.7+23.5
Images and chartsClaude Opus 5.5
- MMMU-ProClaude Opus 5.5 by 9.187.778.6+9.1
MathClaude Opus 5.5
- FrontierMath Tier 4Claude Opus 5.5 by 36.59558.5+36.5
- LiveBench · MathematicsClaude Opus 5.5 by 9.997.187.2+9.9
- FrontierMath Tiers 1-3 (v2)Claude Opus 5.5 by 9.191.282.1+9.1
Following instructionsClaude Opus 5.5
- LiveBench · Instruction FollowingClaude Opus 5.5 by 5.665.760.1+5.6
Other results12 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 56.746.4-10.3+56.7
- Terminal-Bench 4.0Claude Opus 5.5 by 49.166.417.3+49.1
- OSWorld 2.0Claude Opus 5.5 by 36.281.845.6+36.2
- AA IntelligenceClaude Opus 5.5 by 20.357.637.3+20.3
- livebench_languageClaude Opus 5.5 by 13.786.372.6+13.7
- HealthBench ProfessionalClaude Opus 5.5 by 9.965.655.7+9.9
- Toolathlon VerifiedClaude Opus 5.5 by 9.977.867.9+9.9
- DeepSWE 1.1Claude Opus 5.5 by 7.274.267+7.2
- ARC-AGI-1Claude Opus 5.5 by 6.897.590.7+6.8
- HealthBenchClaude Opus 5.5 by 4.860.655.8+4.8
- HealthBench length-adjustedClaude Opus 5.5 by 4.860.655.8+4.8
- livebench_data_analysisClaude Opus 5.5 by 2.380.378+2.3
Questions people ask
Which is better, Claude Opus 5.5 or GPT-5.6 Luna?
Claude Opus 5.5 wins all eight areas we test: coding, agents, reasoning, facts, images and charts, math, long documents and following instructions. GPT-5.6 Luna wins none, but costs 94% less.
Which is better for coding?
Claude Opus 5.5. It wins 5 of the 5 coding tests both models report; GPT-5.6 Luna wins none.
Which is cheaper?
Claude Opus 5.5 costs $4.00 per million input tokens and $20.00 per million output tokens; GPT-5.6 Luna costs $0.20 and $1.20. That makes GPT-5.6 Luna about 94% 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 22 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 12 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.