Claude Opus 4.5 vs GPT-5.6 Luna
GPT-5.6 Luna leads Claude Opus 4.5 on coding, 58.0 to 44.0 on the Vibe Coding Index, and GPT-5.6 Luna costs 20.8x less per output token ($1.20 vs $25.00 per million). Updated October 22, 2026; 76 benchmarks have a result for both.
vs boards won of 76 shared
Claude Opus 4.5 or GPT-5.6 Luna: which to pick
Pick GPT-5.6 Luna for coding: it scores 58.0 on the Vibe Coding Index against 44.0 for Claude Opus 4.5.
Pick Claude Opus 4.5 for work measured by WeirdML or LMArena Text: coding, where it leads.
Model AClaude Opus 4.5Anthropic44.0/1003 independent benchmarks$1.37 per solved taskModel BGPT-5.6 LunaOpenAI58.0/1006 independent benchmarks$0.04 per solved task
- Shared results
- 76
- Claude Opus 4.5 only
- 32
- GPT-5.6 Luna only
- 43
- Like-for-like categories
- 8 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
GPT-5.6 Luna
GPT-5.6 Luna scores 58.0 against 44.0.
3 and 6 benchmarks behind the scores
Intelligence
AA Intelligence Index
GPT-5.6 Luna
GPT-5.6 Luna leads, 37.3 against 29.1.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only GPT-5.6 Luna has a AA Agentic Index result, 42.1.
Directional only
Reasoning
GPQA Diamond
GPT-5.6 Luna
GPT-5.6 Luna leads, 91.7% against 85.9%.
Same board, both measured
Math
AIME
No call
Only Claude Opus 4.5 has a AIME result, 95.4%.
Directional only
Knowledge
MMLU Pro
Claude Opus 4.5
Claude Opus 4.5 leads, 87.3% against 86.0%.
Same board, both measured
Web design
Design Arena: websites
GPT-5.6 Luna
GPT-5.6 Luna leads, 1255 against 1247.
Same board, both measured
Long documents
Listed context window
GPT-5.6 Luna
GPT-5.6 Luna takes 1.05M tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-5.6 Luna
Claude Opus 4.5 $0.018, GPT-5.6 Luna $0.0008 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
GPT-5.6 Luna
Claude Opus 4.5 $1.37, GPT-5.6 Luna $0.04.
Published attempt cost and pass rate
At a glance
- Coding index
- Claude Opus 4.5 44.0 from 3 benchmarks, GPT-5.6 Luna 58.0 from 6 benchmarks.
- Widest category
- Math, 23.5 points apart on average over 6 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): Claude Opus 4.5 20.6% against GPT-5.6 Luna 77.1%, 56.4 points apart on a 0 to 100 scale.
- Output price
- Claude Opus 4.5 $25.00 against GPT-5.6 Luna $1.20 per million output tokens, 20.8x apart.
- Context window
- Claude Opus 4.5 takes 200K tokens, GPT-5.6 Luna 1.05M.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Claude Opus 4.5 | Bars | GPT-5.6 Luna | Ties |
|---|---|---|---|---|
| Coding | 3 | 5 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 1 | 1 | ||
| Reasoning | 6 | 8 | ||
| Math | 1 | 5 | ||
| Knowledge | 11 | 1 | ||
| Web design | 5 | 3 | ||
| General | 19 | 5 | ||
| All shared boards | 46 | 30 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index35
| Benchmark | Claude Opus 4.5 | GPT-5.6 Luna | Leader |
|---|---|---|---|
| SWE-bench Verified | 79.2% | Not measured | Only Claude Opus 4.5 measured |
| SWE-bench (full test set) | 52.6% | Not measured | Only Claude Opus 4.5 measured |
| SWE-bench Multilingual | 70.7% | Not measured | Only Claude Opus 4.5 measured |
| LiveBench coding | Not measured | 73.6% | Only GPT-5.6 Luna measured |
| LMArena WebDev | 1494 | 1518 | GPT-5.6 Luna |
| AA Coding Index | Not measured | 71.4 | Only GPT-5.6 Luna measured |
| LiveCodeBench (Vals AI) | 83.7% | Not measured | Only Claude Opus 4.5 measured |
| SWE-bench Verified (Vals AI) | 76.4% | 93.0% | GPT-5.6 Luna |
| Terminal-Bench 4 (Vals AI) | Not measured | 11.6% | Only GPT-5.6 Luna measured |
| Vibe Code Bench (Vals AI) | 20.6% | 77.1% | GPT-5.6 Luna |
| Code migration (Vals AI) | Not measured | 44.5% | Only GPT-5.6 Luna measured |
| ProgramBench (Vals AI) | Not measured | 0.0% | Only GPT-5.6 Luna measured |
| IOI (Vals AI) | Not measured | 61.8% | Only GPT-5.6 Luna measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 79.0% | Only GPT-5.6 Luna measured |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 22.6% | Only GPT-5.6 Luna measured |
| SkillsBench (Vals AI) | Not measured | 60.5% | Only GPT-5.6 Luna measured |
| CyberBench (Vals AI) | Not measured | 73.6% | Only GPT-5.6 Luna measured |
| LiveCodeBench (Artificial Analysis run) | 87.1% | Not measured | Only Claude Opus 4.5 measured |
| SciCode | Not measured | 53.6% | Only GPT-5.6 Luna measured |
| Terminal-Bench Hard (Artificial Analysis run) | 47.0% | Not measured | Only Claude Opus 4.5 measured |
| Terminal-Bench | 63.1% | Not measured | Only Claude Opus 4.5 measured |
| FrontierCode | Not measured | 39.8% | Only GPT-5.6 Luna measured |
| GSO-Bench | 26.5% | Not measured | Only Claude Opus 4.5 measured |
| WeirdML | 63.7% | 60.9% | Claude Opus 4.5 |
| Cybench | 82.0% | Not measured | Only Claude Opus 4.5 measured |
| ALE-Bench | Not measured | 1667.4 | Only GPT-5.6 Luna measured |
| LMArena Text: coding | 1503 | 1466 | Claude Opus 4.5 |
| LMArena Text: software and IT | 1483 | 1463 | Claude Opus 4.5 |
| LMArena WebDev: React | 1478 | 1508 | GPT-5.6 Luna |
| LMArena WebDev: HTML | 1510 | 1520 | GPT-5.6 Luna |
| LMArena WebDev: from an image | Not measured | 1517 | Only GPT-5.6 Luna measured |
| SciCode | Not measured | 6.2% | Only GPT-5.6 Luna measured |
| Neither model has a result on the other 7 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Claude Opus 4.5 | GPT-5.6 Luna | Leader |
|---|---|---|---|
| AA Intelligence Index | 29.1 | 37.3 | GPT-5.6 Luna |
| Epoch Capabilities Index | 150.1 | 156.5 | GPT-5.6 Luna |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Claude Opus 4.5 | GPT-5.6 Luna | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 42.1 | Only GPT-5.6 Luna measured |
| Design Arena: agents building web apps | 1159 | Not measured | Only Claude Opus 4.5 measured |
| Design Arena: agents building full-stack apps | 1156 | Not measured | Only Claude Opus 4.5 measured |
| Design Arena: agents building mobile apps | 1188 | Not measured | Only Claude Opus 4.5 measured |
| Design Arena: agents building Android apps | 1177 | Not measured | Only Claude Opus 4.5 measured |
| LiveBench research | Not measured | 51.0% | Only GPT-5.6 Luna measured |
| LiveBench browser | Not measured | 68.0% | Only GPT-5.6 Luna measured |
| LiveBench long agentic | Not measured | 30.4% | Only GPT-5.6 Luna measured |
| SREBench (Vals AI) | Not measured | 1.5% | Only GPT-5.6 Luna measured |
| Finance Agent (Vals AI) | Not measured | 55.0% | Only GPT-5.6 Luna measured |
| Tax Agent Bench (Vals AI) | Not measured | 24.8% | Only GPT-5.6 Luna measured |
| Legal Research Bench (Vals AI) | Not measured | 36.5% | Only GPT-5.6 Luna measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 67.1% | Only GPT-5.6 Luna measured |
| BioMysteryBench (Vals AI) | Not measured | 61.5% | Only GPT-5.6 Luna measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 0.0% | Only GPT-5.6 Luna measured |
| Vals Science Index | Not measured | 25.3% | Only GPT-5.6 Luna measured |
| τ²-Bench Telecom | 89.5% | Not measured | Only Claude Opus 4.5 measured |
| APEX-Agents | Not measured | 43.0% | Only GPT-5.6 Luna measured |
| METR time horizons | 75.0% | Not measured | Only Claude Opus 4.5 measured |
| Remote Labor Index | 3.8% | Not measured | Only Claude Opus 4.5 measured |
| GDPval | 45.5% | Not measured | Only Claude Opus 4.5 measured |
| BALROG | 43.5% | 45.6% | GPT-5.6 Luna |
| DeepResearch Bench | 54.8% | Not measured | Only Claude Opus 4.5 measured |
| OSWorld | 66.3% | Not measured | Only Claude Opus 4.5 measured |
| Vending-Bench 2 | $4,967 | $4,095 | Claude Opus 4.5 |
| Berkeley Function Calling Leaderboard (BFCL) | 77.5% | Not measured | Only Claude Opus 4.5 measured |
| Neither model has a result on the other 15 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index68
| Benchmark | Claude Opus 4.5 | GPT-5.6 Luna | Leader |
|---|---|---|---|
| GPQA Diamond | 85.9% | 91.7% | GPT-5.6 Luna |
| LiveBench reasoning | Not measured | 85.6% | Only GPT-5.6 Luna measured |
| MysteryMechanism (Vals AI) | Not measured | 14.4% | Only GPT-5.6 Luna measured |
| MMMU Pro (Vals AI) | 83.0% | 85.0% | GPT-5.6 Luna |
| GPQA Diamond (Artificial Analysis run) | 86.6% | 91.1% | GPT-5.6 Luna |
| Humanity's Last Exam (Artificial Analysis run) | 30.1% | 39.5% | GPT-5.6 Luna |
| GPQA Diamond (Epoch AI run) | 86.0% | 91.6% | GPT-5.6 Luna |
| ARC-AGI | 80.0% | 88.0% | GPT-5.6 Luna |
| ARC-AGI-2 | 37.6% | 59.5% | GPT-5.6 Luna |
| SimpleBench | 62.0% | 46.8% | Claude Opus 4.5 |
| Chess puzzles | 14.0% | 43.0% | GPT-5.6 Luna |
| Mystery game puzzles | 22.0% | 21.0% | Claude Opus 4.5 |
| EBR-bench | 14.3% | Not measured | Only Claude Opus 4.5 measured |
| VPCT | 40.0% | Not measured | Only Claude Opus 4.5 measured |
| LMArena Text: hard prompts | 1476 | 1451 | Claude Opus 4.5 |
| LMArena Text: expert | 1487 | 1478 | Claude Opus 4.5 |
| LMArena Text: hard prompts in English | 1482 | 1460 | Claude Opus 4.5 |
| LMArena Vision: diagrams | Not measured | 1273 | Only GPT-5.6 Luna measured |
| LMArena Vision: homework | Not measured | 1282 | Only GPT-5.6 Luna measured |
| Kagi LLM Benchmark | 80.2% | 49.1% | Claude Opus 4.5 |
| Neither model has a result on the other 2 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index15
| Benchmark | Claude Opus 4.5 | GPT-5.6 Luna | Leader |
|---|---|---|---|
| AIME | 95.4% | Not measured | Only Claude Opus 4.5 measured |
| MGSM (Vals AI) | 95.2% | Not measured | Only Claude Opus 4.5 measured |
| AA Math Index | 91.3 | Not measured | Only Claude Opus 4.5 measured |
| AIME 2025 (Artificial Analysis run) | 91.3% | Not measured | Only Claude Opus 4.5 measured |
| OTIS Mock AIME | 86.1% | 98.3% | GPT-5.6 Luna |
| FrontierMath, tiers 1 to 3 | 34.4% | 82.1% | GPT-5.6 Luna |
| FrontierMath, tier 4 | 4.9% | 61.0% | GPT-5.6 Luna |
| ProofBench | 36.0% | 60.0% | GPT-5.6 Luna |
| LMArena Text: math | 1463 | 1459 | Claude Opus 4.5 |
| LMArena Text: mathematical work | 1468 | 1470 | GPT-5.6 Luna |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index111
| Benchmark | Claude Opus 4.5 | GPT-5.6 Luna | Leader |
|---|---|---|---|
| MMLU Pro | 87.3% | 86.0% | Claude Opus 4.5 |
| LegalBench (Vals AI) | 84.6% | 84.0% | Claude Opus 4.5 |
| CaseLaw (Vals AI) | 62.6% | Not measured | Only Claude Opus 4.5 measured |
| CorpFin (Vals AI) | 65.1% | 64.2% | Claude Opus 4.5 |
| TaxEval (Vals AI) | 74.9% | 76.2% | GPT-5.6 Luna |
| MortgageTax (Vals AI) | 68.7% | 67.3% | Claude Opus 4.5 |
| MedQA (Vals AI) | 95.9% | Not measured | Only Claude Opus 4.5 measured |
| MedCode (Vals AI) | 49.2% | 42.4% | Claude Opus 4.5 |
| MMLU Pro (Artificial Analysis run) | 89.5% | Not measured | Only Claude Opus 4.5 measured |
| SimpleQA Verified | 45.7% | 41.0% | Claude Opus 4.5 |
| GeoBench | 75.0% | Not measured | Only Claude Opus 4.5 measured |
| LMArena Text: science | 1454 | 1433 | Claude Opus 4.5 |
| LMArena Text: medicine and healthcare | 1444 | 1399 | Claude Opus 4.5 |
| LMArena Text: legal and government | 1459 | 1446 | Claude Opus 4.5 |
| LMArena Text: business and finance | 1448 | 1439 | Claude Opus 4.5 |
| FACTS Benchmark Suite | 43.9% | 35.0% | Claude Opus 4.5 |
| Neither model has a result on the other 2 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index53
| Benchmark | Claude Opus 4.5 | GPT-5.6 Luna | Leader |
|---|---|---|---|
| Design Arena: websites | 1247 | 1255 | GPT-5.6 Luna |
| Design Arena: UI components | 1236 | 1248 | GPT-5.6 Luna |
| Design Arena: game dev | 1228 | 1195 | Claude Opus 4.5 |
| Design Arena: data viz | 1243 | 1212 | Claude Opus 4.5 |
| Design Arena: 3D | 1213 | 1121 | Claude Opus 4.5 |
| Design Arena: all code categories | 1241 | 1230 | Claude Opus 4.5 |
| Design Arena: SVG | 1180 | 1193 | GPT-5.6 Luna |
| Design Arena: ASCII art | 1190 | 1142 | Claude Opus 4.5 |
| LiveBench design | Not measured | 76.0% | Only GPT-5.6 Luna measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index195
| Benchmark | Claude Opus 4.5 | GPT-5.6 Luna | Leader |
|---|---|---|---|
| LiveBench data analysis | Not measured | 78.0% | Only GPT-5.6 Luna measured |
| Public Benefits Bench (Vals AI) | Not measured | 61.2% | Only GPT-5.6 Luna measured |
| SAGE (Vals AI) | 52.1% | 44.2% | Claude Opus 4.5 |
| MedScribe (Vals AI) | 85.3% | 84.4% | Claude Opus 4.5 |
| Vals Multimodal Index | Not measured | 69.1% | Only GPT-5.6 Luna measured |
| IFBench | 58.0% | Not measured | Only Claude Opus 4.5 measured |
| Long context reasoning (AA-LCR) | 77.3% | 83.7% | GPT-5.6 Luna |
| DTBench | 89.9% | 89.1% | Claude Opus 4.5 |
| LMCA | 44.5% | 48.5% | GPT-5.6 Luna |
| CL-bench | 21.1% | Not measured | Only Claude Opus 4.5 measured |
| Surface Evolver Bench | Not measured | 61.9% | Only GPT-5.6 Luna measured |
| Furniture assembly | 28.3% | 42.5% | GPT-5.6 Luna |
| LMArena Text | 1451 | 1431 | Claude Opus 4.5 |
| LMArena Text: instruction following | 1478 | 1437 | Claude Opus 4.5 |
| LMArena Text: creative writing | 1445 | 1396 | Claude Opus 4.5 |
| LMArena Vision | Not measured | 1257 | Only GPT-5.6 Luna measured |
| LMArena Text: English | 1461 | 1441 | Claude Opus 4.5 |
| LMArena Text: non-English | 1438 | 1417 | Claude Opus 4.5 |
| LMArena Text: Chinese | 1470 | 1470 | GPT-5.6 Luna |
| LMArena Text: German | 1449 | 1455 | GPT-5.6 Luna |
| LMArena Text: Japanese | 1417 | 1415 | Claude Opus 4.5 |
| LMArena Text: Korean | 1424 | 1415 | Claude Opus 4.5 |
| LMArena Text: French | 1471 | 1458 | Claude Opus 4.5 |
| LMArena Text: Spanish | 1457 | 1446 | Claude Opus 4.5 |
| LMArena Text: Russian | 1447 | 1427 | Claude Opus 4.5 |
| LMArena Text: Polish | 1439 | 1405 | Claude Opus 4.5 |
| LMArena Text: multi-turn | 1466 | 1434 | Claude Opus 4.5 |
| LMArena Text: longer queries | 1479 | 1436 | Claude Opus 4.5 |
| LMArena Text: writing and language | 1452 | 1419 | Claude Opus 4.5 |
| LMArena Text: entertainment and media | 1434 | 1402 | Claude Opus 4.5 |
| LMArena Vision: English | Not measured | 1263 | Only GPT-5.6 Luna measured |
| LMArena Vision: Chinese | Not measured | 1294 | Only GPT-5.6 Luna measured |
| LMArena Vision: reading text | Not measured | 1264 | Only GPT-5.6 Luna measured |
| LMArena Vision: humor | Not measured | 1190 | Only GPT-5.6 Luna measured |
| LMArena Vision: creative writing | Not measured | 1257 | Only GPT-5.6 Luna measured |
| LMArena Document | 1462 | 1457 | Claude Opus 4.5 |
| Neither model has a result on the other 10 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Opus 4.5 | GPT-5.6 Luna | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Claude Opus 4.5$0.018Fits in one request
GPT-5.6 Luna$0.0008Fits in one request
GPT-5.6 Luna costs less
Repository review
50K input + 3K output tokens
Claude Opus 4.5$0.325Fits in one request
GPT-5.6 Luna$0.014Fits in one request
GPT-5.6 Luna costs less
Agent loop
200K input + 10K output tokens
Claude Opus 4.5$1.25Exceeds the context window
GPT-5.6 Luna$0.052Fits in one request
GPT-5.6 Luna costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Anthropic Claude Opus 4.5 | OpenAI GPT-5.6 Luna |
|---|---|---|
| Maker | Anthropic | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | November 24, 2025 | July 9, 2026 |
| Context window | 200K | 1.05M |
| Input $/Mtok | $5.00 | $0.20 |
| Output $/Mtok | $25.00 | $1.20 |
| Coding index | 44.0 | 58.0 |
| Independent measurements behind it | 3 | 6 |
| Cost per solved task | $1.37 | $0.04 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Opus 4.5 better than GPT-5.6 Luna for coding?
Pick GPT-5.6 Luna for coding: it scores 58.0 on the Vibe Coding Index against 44.0 for Claude Opus 4.5. Pick Claude Opus 4.5 for work measured by WeirdML or LMArena Text: coding, where it leads.
Which is cheaper, Claude Opus 4.5 or GPT-5.6 Luna?
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. Per solved SWE-bench Verified task, Claude Opus 4.5 costs $1.37 and GPT-5.6 Luna $0.04.
Which has the bigger context window, Claude Opus 4.5 or GPT-5.6 Luna?
GPT-5.6 Luna, with 1.05M tokens against 200K.
How many benchmarks is the Claude Opus 4.5 vs GPT-5.6 Luna comparison based on?
76 benchmarks have a result for both models as of October 22, 2026. Claude Opus 4.5's coding index rests on 3 independent benchmarks and GPT-5.6 Luna's on 6. Where only one model has a result, the page says so instead of naming a winner.