Claude Opus 4.5 vs GPT-5.6 Luna
Wins 2 of 8 areas
Facts · Following instructions
Wins 6 of 8 areas
Coding · Agents · Reasoning · Images and charts · Math · Long documents
GPT-5.6 Luna is the stronger all-rounder.Claude Opus 4.5 is better at facts.
Scores updated · 39 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 software06GPT-5.6 Luna6 of 6 tests
- ReasoningHard problems that need careful thinking05GPT-5.6 Luna5 of 5 tests
- MathCompetition and research-level math14GPT-5.6 Luna4 of 5 tests
- AgentsCarrying out multi-step tasks on its own02GPT-5.6 Luna2 of 3 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video12GPT-5.6 Luna2 of 3 tests
- Long documentsFinding answers in very long texts01GPT-5.6 Luna1 of 1 test
- FactsGetting facts right instead of making them up30Claude Opus 4.53 of 3 tests
- Following instructionsDoing exactly what it is asked10Claude Opus 4.51 of 1 test
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 95% 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-5.6 Luna pulls ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+53.6points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+47.7points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+46.3points ahead
Where Claude Opus 4.5 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+31.6points ahead
- Short factual questions, answered correctlySimpleQA Verified+4.7points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+3.9points ahead
Every test, side by side
All 39 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.6 Luna
- SWE-bench VerifiedGPT-5.6 Luna by 12.180.993+12.1
- SWE-bench ProGPT-5.6 Luna by 10.75262.7+10.7
- LiveBench · Agentic CodingGPT-5.6 Luna by 8.739.748.4+8.7
- LMArena · WebDevGPT-5.6 Luna by 50 rating points14691519+50 rating
- SciCodeGPT-5.6 Luna by 4.149.553.6+4.1
- LiveBench · CodingGPT-5.6 Luna by 3.279.782.9+3.2
AgentsGPT-5.6 Luna
- BrowseCompGPT-5.6 Luna by 46.33783.3+46.3
- OSWorld-VerifiedGPT-5.6 Luna by 6.366.372.6+6.3
- GDPValtie47.348tie
ReasoningGPT-5.6 Luna
- ARC-AGI-2GPT-5.6 Luna by 2237.659.6+22
- CritPtGPT-5.6 Luna by 164.620.6+16
- Humanity's Last ExamGPT-5.6 Luna by 9.430.139.5+9.4
- LiveBench · ReasoningGPT-5.6 Luna by 5.580.185.6+5.5
- GPQA DiamondGPT-5.6 Luna by 4.586.691.1+4.5
FactsClaude Opus 4.5
- AA-Omniscience · Non-hallucinationClaude Opus 4.5 by 31.6397.4+31.6
- SimpleQA VerifiedClaude Opus 4.5 by 4.745.741+4.7
- AA-Omniscience · AccuracyClaude Opus 4.5 by 3.946.642.7+3.9
Images and chartsGPT-5.6 Luna
- CharXiv (RQ)GPT-5.6 Luna by 15.567.282.7+15.5
- MMMU-ProGPT-5.6 Luna by 4.67478.6+4.6
- MathVistaClaude Opus 4.5 by 3.380.276.9+3.3
MathGPT-5.6 Luna
- FrontierMath Tier 4GPT-5.6 Luna by 53.64.958.5+53.6
- FrontierMath Tiers 1-3 (v2)GPT-5.6 Luna by 47.734.482.1+47.7
- HMMT Feb. 2026GPT-5.6 Luna by 13.285.398.5+13.2
- LiveBench · MathematicsClaude Opus 4.5 by 3.290.487.2+3.2
- AIME 2026GPT-5.6 Luna by 2.595.197.6+2.5
Following instructionsClaude Opus 4.5
- LiveBench · Instruction FollowingClaude Opus 4.5 by 2.562.560.1+2.5
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.
- BrowseComp (context management)GPT-5.6 Luna by 26.257.884+26.2
- AA-OmniscienceClaude Opus 4.5 by 24.314-10.3+24.3
- Artificial Analysis Coding IndexGPT-5.6 Luna by 23.647.871.4+23.6
- AA Agentic IndexClaude Opus 4.5 by 16.959.642.7+16.9
- SimpleVQAClaude Opus 4.5 by 16.569.753.2+16.5
- ToolathlonGPT-5.6 Luna by 9.943.553.4+9.9
- ARC-AGI-1GPT-5.6 Luna by 8.78290.7+8.7
- livebench_languageClaude Opus 4.5 by 8.781.372.6+8.7
- AA IntelligenceGPT-5.6 Luna by 8.229.137.3+8.2
- HLE (with tools)GPT-5.6 Luna by 5.543.448.9+5.5
- livebench_data_analysisGPT-5.6 Luna by 3.674.478+3.6
- VideoMMMUClaude Opus 4.5 by 3.384.481.1+3.3
Questions people ask
Which is better, Claude Opus 4.5 or GPT-5.6 Luna?
GPT-5.6 Luna wins six of the eight areas we test: coding, agents, reasoning, images and charts, math and long documents. Claude Opus 4.5 wins facts and following instructions.
Which is better for coding?
GPT-5.6 Luna. It wins 6 of the 6 coding tests both models report; Claude Opus 4.5 wins none.
Which is cheaper?
Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; GPT-5.6 Luna costs $0.20 and $1.20. That makes GPT-5.6 Luna about 95% cheaper for the same work.
How do you compare the two?
We use the 39 benchmark tests both models have published scores on. The verdict counts the 27 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.