Model comparison
Claude Opus 4.5 vs GPT-5.6 Luna
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 50.5 on the Noometry Index.
Last verified . 41 shared benchmarks.
Summary
- They share 41 benchmarks with published results for both. Claude Opus 4.5 scores higher in 6 categories and GPT-5.6 Luna in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 38.6.
- The biggest single-benchmark swing is FrontierMath Tier 4: 4.9% for Claude Opus 4.5 and 61% for GPT-5.6 Luna.
- GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.
- GPT-5.6 Luna accepts more context: 1.05M tokens versus 200K.
Side by side
| Claude Opus 4.5 | GPT-5.6 Luna | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 50.5 | 54.6 |
| Released | 2025-11-01 | 2026-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.05M |
| Max output | 64K | 128K |
| Input $ / M tokens | $5 | $0.20 |
| Output $ / M tokens | $25 | $1.20 |
| Results tracked | 69 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude Opus 4.5: 54.8 (#27), GPT-5.6 Luna: 54.5 (#28)
| Benchmark | Claude Opus 4.5 | GPT-5.6 Luna |
|---|---|---|
| LMArena WebDev | 1494 | 1519 |
| WeirdML | 63.7% | 60.9% |
| LMArena Coding | 1504 | 1466 |
| ALE-Bench | 1,025 | 1,667 |
| SWE-bench Verified | 76.7% | — |
| DeepSWE | — | 67.2% |
| FrontierCode | — | 39.8% |
| SWE-bench Verified (bash only) | 76.8% | — |
| CursorBench | — | 35.9% |
| SWE-bench Multilingual | 70.7% | — |
| SciCode | — | 53.6% |
| GSO | 26.5% | — |
| AlgoTune | 1.77 | — |
Agentic & Tool Use Claude Opus 4.5 leads
Claude Opus 4.5: 47.3 (#12), GPT-5.6 Luna: 34.4 (#45)
| Benchmark | Claude Opus 4.5 | GPT-5.6 Luna |
|---|---|---|
| BALROG | 43.5% | 45.6% |
| Vending-Bench 2 | 4,967 | 4,095 |
| Terminal-Bench | 63.1% | — |
| APEX-Agents | — | 43% |
| Berkeley Function Calling Leaderboard | 77.5% | — |
| GDPval | 45.5% | — |
| Remote Labor Index | 3.8% | — |
| τ²-bench Airline | 84% | — |
| τ²-bench Banking | 24.7% | — |
| τ²-bench Retail | 79.6% | — |
| τ²-bench Telecom | 92.3% | — |
| Cybench | 82% | — |
| DeepResearch Bench | 54.8% | — |
| OSWorld | 66.3% | — |
| GDP.pdf | — | 22.7% |
| LMArena Search | 1180 | — |
| METR Time Horizons | 75% | — |
Reasoning GPT-5.6 Luna leads
Claude Opus 4.5: 42.6 (#51), GPT-5.6 Luna: 47.6 (#43)
| Benchmark | Claude Opus 4.5 | GPT-5.6 Luna |
|---|---|---|
| ARC-AGI-2 | 37.6% | 59.5% |
| SimpleBench | 62% | 46.8% |
| Kagi LLM Benchmark | 80.2% | 49.1% |
| NYT Connections (extended) | 52.5% | 69.4% |
| ARC-AGI-1 | 80% | 88% |
| Chess Puzzles | 12% | 40% |
| LMArena Hard Prompts | 1476 | 1451 |
| Mystery Game Puzzles | 22% | 21% |
| DTBench | 89.9% | 89.1% |
| LMCA | 44.5% | 48.5% |
| Epoch Capabilities Index | 150.09 | 156.39 |
| CritPt | — | 20.6% |
| EnigmaEval | 11.9% | — |
| EBR-Bench | 14.3% | — |
| Surface Evolver Bench | — | 61.9% |
| ForecastBench | 60.7 | — |
Math GPT-5.6 Luna leads
Claude Opus 4.5: 38.6 (#132), GPT-5.6 Luna: 77.7 (#14)
| Benchmark | Claude Opus 4.5 | GPT-5.6 Luna |
|---|---|---|
| FrontierMath (Tiers 1-3) | 34.4% | 82.1% |
| FrontierMath Tier 4 | 4.9% | 61% |
| OTIS Mock AIME 2024-2025 | 86.1% | 98.3% |
| ProofBench | 36% | 60% |
| LMArena Math | 1463 | 1458 |
| FrontierMath (Feb 2025 set) | 20.7% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge GPT-5.6 Luna leads
Claude Opus 4.5: 56.5 (#44), GPT-5.6 Luna: 58.5 (#34)
| Benchmark | Claude Opus 4.5 | GPT-5.6 Luna |
|---|---|---|
| GPQA Diamond | 86% | 91.6% |
| SimpleQA Verified | 45.7% | 41% |
| LMArena Expert | 1487 | 1478 |
| Humanity's Last Exam | 25.2% | — |
| Vectara Hallucination Rate | 10.9% | — |
Multimodal GPT-5.6 Luna leads
Claude Opus 4.5: 31.4 (#107), GPT-5.6 Luna: 42.7 (#28)
| Benchmark | Claude Opus 4.5 | GPT-5.6 Luna |
|---|---|---|
| Furniture Assembly | 28.3% | 42.5% |
| LMArena Document | 1462 | 1457 |
| LMArena Vision | — | 1258 |
| GeoBench | 75% | — |
| VPCT | 40% | — |
| Blueprint-Bench 2 | — | 22.6% |
Multilingual Claude Opus 4.5 leads
Claude Opus 4.5: 54.3 (#47), GPT-5.6 Luna: 52.8 (#78)
| Benchmark | Claude Opus 4.5 | GPT-5.6 Luna |
|---|---|---|
| LMArena Non-English | 1438 | 1417 |
| LMArena Chinese | 1470 | 1470 |
| LMArena French | 1471 | 1456 |
| LMArena German | 1449 | 1454 |
| LMArena Japanese | 1416 | 1411 |
| LMArena Korean | 1424 | 1415 |
| LMArena Russian | 1447 | 1428 |
| LMArena Spanish | 1458 | 1448 |
Instruction Following Claude Opus 4.5 leads
Claude Opus 4.5: 77.5 (#19), GPT-5.6 Luna: 75.6 (#57)
| Benchmark | Claude Opus 4.5 | GPT-5.6 Luna |
|---|---|---|
| LMArena Instruction Following | 1478 | 1437 |
Long Context Claude Opus 4.5 leads
Claude Opus 4.5: 46.5 (#22), GPT-5.6 Luna: 43.9 (#82)
| Benchmark | Claude Opus 4.5 | GPT-5.6 Luna |
|---|---|---|
| LMArena Longer Query | 1480 | 1436 |
| CL-bench | 21.1% | — |
Writing & Preference Too close to call
Claude Opus 4.5: 68.1 (#28), GPT-5.6 Luna: 68.0 (#29)
| Benchmark | Claude Opus 4.5 | GPT-5.6 Luna |
|---|---|---|
| LMArena Text | 1451 | 1431 |
| LMArena Creative Writing | 1445 | 1396 |
| EQ-Bench Creative Writing | 1687 | 1829 |
| LMArena Multi-Turn | 1466 | 1434 |
| EQ-Bench 4 | — | 1156 |
Frequently asked questions
Is Claude Opus 4.5 better than GPT-5.6 Luna?
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 50.5 on the Noometry Index.
Which is cheaper, Claude Opus 4.5 or GPT-5.6 Luna?
GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; Claude Opus 4.5 lists at $5 and $25.
Is Claude Opus 4.5 or GPT-5.6 Luna better for coding?
They score almost the same on coding (54.8 vs 54.5); test both on your own repository before choosing.
Which has the bigger context window?
GPT-5.6 Luna does, with 1.05M tokens against 200K.
How many benchmarks do Claude Opus 4.5 and GPT-5.6 Luna share?
41 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and GPT-5.6 Luna has 52.