Model comparison
Claude Opus 5.5 vs GPT-6 Luna
Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 53.3 on the Noometry Index. GPT-6 Luna costs 40× less per token, which makes it the better buy when Claude Opus 5.5's lead doesn't matter for your workload.
Last verified . 37 shared benchmarks.
Summary
- They share 37 benchmarks with published results for both. Claude Opus 5.5 scores higher in 10 categories and GPT-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 48.2.
- The biggest single-benchmark swing is Mystery Game Puzzles: 71% for Claude Opus 5.5 and 7% for GPT-6 Luna.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $4 / $20 for Claude Opus 5.5.
- GPT-6 Luna accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Opus 5.5 | GPT-6 Luna | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 68.6 | 53.3 |
| Released | 2026-09-22 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $4 | $0.10 |
| Output $ / M tokens | $20 | $0.50 |
| Results tracked | 44 | 42 |
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-6 Luna: 55.5 (#25)
| Benchmark | Claude Opus 5.5 | GPT-6 Luna |
|---|---|---|
| FrontierCode | 54.6% | 42.4% |
| LMArena WebDev | 1813 | 1581 |
| SciCode | 66.9% | 54.6% |
| LMArena Coding | 1547 | 1439 |
| ALE-Bench | 2,147 | 1,577 |
| DeepSWE | — | 66.6% |
| CursorBench | 57.8% | — |
| FrontierSWE | 62.3% | — |
| MirrorCode | 77.4% | — |
Agentic & Tool Use Claude Opus 5.5 leads
Claude Opus 5.5: 45.3 (#15), GPT-6 Luna: 33.3 (#54)
| Benchmark | Claude Opus 5.5 | GPT-6 Luna |
|---|---|---|
| APEX-Agents | 73.5% | 44.3% |
| GDP.pdf | 30.6% | 23% |
| Vending-Bench 2 | 9,235 | — |
Reasoning Claude Opus 5.5 leads
Claude Opus 5.5: 80.2 (#3), GPT-6 Luna: 48.2 (#41)
| Benchmark | Claude Opus 5.5 | GPT-6 Luna |
|---|---|---|
| ARC-AGI-2 | 93.3% | 59.3% |
| NYT Connections (extended) | 88.5% | 68.7% |
| ARC-AGI-1 | 98.5% | 86.7% |
| CritPt | 31.7% | 19.4% |
| LMArena Hard Prompts | 1535 | 1411 |
| Mystery Game Puzzles | 71% | 7% |
| DTBench | 98.9% | 90.1% |
| LMCA | 68.2% | 44.5% |
| Epoch Capabilities Index | 167.33 | 156.28 |
| Chess Puzzles | — | 31% |
| EBR-Bench | 71.4% | — |
Math Claude Opus 5.5 leads
Claude Opus 5.5: 91.8 (#3), GPT-6 Luna: 76.1 (#15)
| Benchmark | Claude Opus 5.5 | GPT-6 Luna |
|---|---|---|
| FrontierMath (Tiers 1-3) | 91.2% | 78.9% |
| FrontierMath Tier 4 | 95% | 56.1% |
| OTIS Mock AIME 2024-2025 | 100% | 98.9% |
| ProofBench | 100% | 64% |
| LMArena Math | 1506 | 1416 |
| FrontierMath Erdős | 2.9% | — |
Knowledge Claude Opus 5.5 leads
Claude Opus 5.5: 66.4 (#10), GPT-6 Luna: 57.0 (#41)
| Benchmark | Claude Opus 5.5 | GPT-6 Luna |
|---|---|---|
| GPQA Diamond | 90.6% | 90.5% |
| SimpleQA Verified | 72.2% | 41.4% |
| LMArena Expert | 1547 | 1444 |
Multimodal Claude Opus 5.5 leads
Claude Opus 5.5: 57.8 (#1), GPT-6 Luna: 42.4 (#30)
| Benchmark | Claude Opus 5.5 | GPT-6 Luna |
|---|---|---|
| LMArena Vision | 1321 | 1217 |
| Blueprint-Bench 2 | 51.2% | 31.2% |
| Furniture Assembly | 83.3% | 44.2% |
Multilingual Claude Opus 5.5 leads
Claude Opus 5.5: 59.1 (#2), GPT-6 Luna: 50.5 (#117)
| Benchmark | Claude Opus 5.5 | GPT-6 Luna |
|---|---|---|
| LMArena Non-English | 1507 | 1386 |
| LMArena Chinese | 1588 | 1433 |
| LMArena French | 1514 | 1420 |
| LMArena Russian | 1520 | 1394 |
| LMArena Spanish | 1507 | 1393 |
| LMArena German | — | 1369 |
| LMArena Japanese | — | 1369 |
| LMArena Korean | — | 1360 |
Instruction Following Claude Opus 5.5 leads
Claude Opus 5.5: 80.0 (#3), GPT-6 Luna: 74.3 (#99)
| Benchmark | Claude Opus 5.5 | GPT-6 Luna |
|---|---|---|
| LMArena Instruction Following | 1537 | 1409 |
Long Context Claude Opus 5.5 leads
Claude Opus 5.5: 47.1 (#19), GPT-6 Luna: 43.0 (#111)
| Benchmark | Claude Opus 5.5 | GPT-6 Luna |
|---|---|---|
| LMArena Longer Query | 1532 | 1409 |
Writing & Preference Claude Opus 5.5 leads
Claude Opus 5.5: 78.2 (#3), GPT-6 Luna: 58.3 (#119)
| Benchmark | Claude Opus 5.5 | GPT-6 Luna |
|---|---|---|
| LMArena Text | 1515 | 1391 |
| LMArena Creative Writing | 1533 | 1363 |
| LMArena Multi-Turn | 1499 | 1396 |
| EQ-Bench Creative Writing | 2050 | — |
Frequently asked questions
Is Claude Opus 5.5 better than GPT-6 Luna?
Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 53.3 on the Noometry Index. GPT-6 Luna costs 40× 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-6 Luna?
GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Claude Opus 5.5 lists at $4 and $20.
Is Claude Opus 5.5 or GPT-6 Luna better for coding?
Claude Opus 5.5 scores higher on coding benchmarks: 71.9 versus 55.5 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Luna does, with 1.05M tokens against 1M.
How many benchmarks do Claude Opus 5.5 and GPT-6 Luna share?
37 benchmarks have published results for both models. Claude Opus 5.5 has 44 scored results on Noometry and GPT-6 Luna has 42.