Model comparison
Claude Opus 5.5 vs GPT-5.6 Luna
Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 54.6 on the Noometry Index. GPT-5.6 Luna costs 18× less per token, which makes it the better buy when Claude Opus 5.5's lead doesn't matter for your workload.
Last verified . 40 shared benchmarks.
Summary
- They share 40 benchmarks with published results for both. Claude Opus 5.5 scores higher in 10 categories and GPT-5.6 Luna in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 5.5 leads 80.2 to 47.6.
- The biggest single-benchmark swing is Mystery Game Puzzles: 71% for Claude Opus 5.5 and 21% for GPT-5.6 Luna.
- GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $4 / $20 for Claude Opus 5.5.
- GPT-5.6 Luna accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Opus 5.5 | GPT-5.6 Luna | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 68.6 | 54.6 |
| Released | 2026-09-22 | 2026-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $4 | $0.20 |
| Output $ / M tokens | $20 | $1.20 |
| Results tracked | 44 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 5.5 leads
Claude Opus 5.5: 71.9 (#3), GPT-5.6 Luna: 54.5 (#28)
| Benchmark | Claude Opus 5.5 | GPT-5.6 Luna |
|---|---|---|
| FrontierCode | 54.6% | 39.8% |
| CursorBench | 57.8% | 35.9% |
| LMArena WebDev | 1813 | 1519 |
| SciCode | 66.9% | 53.6% |
| LMArena Coding | 1547 | 1466 |
| ALE-Bench | 2,147 | 1,667 |
| DeepSWE | — | 67.2% |
| FrontierSWE | 62.3% | — |
| WeirdML | — | 60.9% |
| MirrorCode | 77.4% | — |
Agentic & Tool Use Claude Opus 5.5 leads
Claude Opus 5.5: 45.3 (#15), GPT-5.6 Luna: 34.4 (#45)
| Benchmark | Claude Opus 5.5 | GPT-5.6 Luna |
|---|---|---|
| APEX-Agents | 73.5% | 43% |
| GDP.pdf | 30.6% | 22.7% |
| Vending-Bench 2 | 9,235 | 4,095 |
| BALROG | — | 45.6% |
Reasoning Claude Opus 5.5 leads
Claude Opus 5.5: 80.2 (#3), GPT-5.6 Luna: 47.6 (#43)
| Benchmark | Claude Opus 5.5 | GPT-5.6 Luna |
|---|---|---|
| ARC-AGI-2 | 93.3% | 59.5% |
| NYT Connections (extended) | 88.5% | 69.4% |
| ARC-AGI-1 | 98.5% | 88% |
| CritPt | 31.7% | 20.6% |
| LMArena Hard Prompts | 1535 | 1451 |
| Mystery Game Puzzles | 71% | 21% |
| DTBench | 98.9% | 89.1% |
| LMCA | 68.2% | 48.5% |
| Epoch Capabilities Index | 167.33 | 156.39 |
| SimpleBench | — | 46.8% |
| Kagi LLM Benchmark | — | 49.1% |
| Chess Puzzles | — | 40% |
| EBR-Bench | 71.4% | — |
| Surface Evolver Bench | — | 61.9% |
Math Claude Opus 5.5 leads
Claude Opus 5.5: 91.8 (#3), GPT-5.6 Luna: 77.7 (#14)
| Benchmark | Claude Opus 5.5 | GPT-5.6 Luna |
|---|---|---|
| FrontierMath (Tiers 1-3) | 91.2% | 82.1% |
| FrontierMath Tier 4 | 95% | 61% |
| OTIS Mock AIME 2024-2025 | 100% | 98.3% |
| ProofBench | 100% | 60% |
| LMArena Math | 1506 | 1458 |
| FrontierMath Erdős | 2.9% | — |
Knowledge Claude Opus 5.5 leads
Claude Opus 5.5: 66.4 (#10), GPT-5.6 Luna: 58.5 (#34)
| Benchmark | Claude Opus 5.5 | GPT-5.6 Luna |
|---|---|---|
| GPQA Diamond | 90.6% | 91.6% |
| SimpleQA Verified | 72.2% | 41% |
| LMArena Expert | 1547 | 1478 |
Multimodal Claude Opus 5.5 leads
Claude Opus 5.5: 57.8 (#1), GPT-5.6 Luna: 42.7 (#28)
| Benchmark | Claude Opus 5.5 | GPT-5.6 Luna |
|---|---|---|
| LMArena Vision | 1321 | 1258 |
| Blueprint-Bench 2 | 51.2% | 22.6% |
| Furniture Assembly | 83.3% | 42.5% |
| LMArena Document | — | 1457 |
Multilingual Claude Opus 5.5 leads
Claude Opus 5.5: 59.1 (#2), GPT-5.6 Luna: 52.8 (#78)
| Benchmark | Claude Opus 5.5 | GPT-5.6 Luna |
|---|---|---|
| LMArena Non-English | 1507 | 1417 |
| LMArena Chinese | 1588 | 1470 |
| LMArena French | 1514 | 1456 |
| LMArena Russian | 1520 | 1428 |
| LMArena Spanish | 1507 | 1448 |
| LMArena German | — | 1454 |
| LMArena Japanese | — | 1411 |
| LMArena Korean | — | 1415 |
Instruction Following Claude Opus 5.5 leads
Claude Opus 5.5: 80.0 (#3), GPT-5.6 Luna: 75.6 (#57)
| Benchmark | Claude Opus 5.5 | GPT-5.6 Luna |
|---|---|---|
| LMArena Instruction Following | 1537 | 1437 |
Long Context Claude Opus 5.5 leads
Claude Opus 5.5: 47.1 (#19), GPT-5.6 Luna: 43.9 (#82)
| Benchmark | Claude Opus 5.5 | GPT-5.6 Luna |
|---|---|---|
| LMArena Longer Query | 1532 | 1436 |
Writing & Preference Claude Opus 5.5 leads
Claude Opus 5.5: 78.2 (#3), GPT-5.6 Luna: 68.0 (#29)
| Benchmark | Claude Opus 5.5 | GPT-5.6 Luna |
|---|---|---|
| LMArena Text | 1515 | 1431 |
| LMArena Creative Writing | 1533 | 1396 |
| EQ-Bench Creative Writing | 2050 | 1829 |
| LMArena Multi-Turn | 1499 | 1434 |
| EQ-Bench 4 | — | 1156 |
Frequently asked questions
Is Claude Opus 5.5 better than GPT-5.6 Luna?
Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 54.6 on the Noometry Index. GPT-5.6 Luna costs 18× less per token, which makes it the better buy when Claude Opus 5.5's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 5.5 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 5.5 lists at $4 and $20.
Is Claude Opus 5.5 or GPT-5.6 Luna better for coding?
Claude Opus 5.5 scores higher on coding benchmarks: 71.9 versus 54.5 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Luna does, with 1.05M tokens against 1M.
How many benchmarks do Claude Opus 5.5 and GPT-5.6 Luna share?
40 benchmarks have published results for both models. Claude Opus 5.5 has 44 scored results on Noometry and GPT-5.6 Luna has 52.