Model comparison
Claude Sonnet 5 vs GPT-5.6 Luna
Claude Sonnet 5 and GPT-5.6 Luna score almost the same on the Noometry Index (54.6 vs 54.6), so choose on price, context window or the category you care about most.
Last verified . 46 shared benchmarks.
Summary
- They share 46 benchmarks with published results for both. Claude Sonnet 5 scores higher in 7 categories and GPT-5.6 Luna in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 66.2.
- The biggest single-benchmark swing is FrontierMath Tier 4: 29.3% for Claude Sonnet 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 $2 / $10 for Claude Sonnet 5.
- GPT-5.6 Luna accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Sonnet 5 | GPT-5.6 Luna | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 54.6 | 54.6 |
| Released | 2026-06-29 | 2026-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $2 | $0.20 |
| Output $ / M tokens | $10 | $1.20 |
| Results tracked | 51 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude Sonnet 5: 55.5 (#26), GPT-5.6 Luna: 54.5 (#28)
| Benchmark | Claude Sonnet 5 | GPT-5.6 Luna |
|---|---|---|
| DeepSWE | 53.8% | 67.2% |
| FrontierCode | 42.7% | 39.8% |
| CursorBench | 34.1% | 35.9% |
| LMArena WebDev | 1541 | 1519 |
| SciCode | 54.3% | 53.6% |
| WeirdML | 68.8% | 60.9% |
| LMArena Coding | 1483 | 1466 |
| ALE-Bench | 1,463 | 1,667 |
| GSO | 37.3% | — |
Agentic & Tool Use Claude Sonnet 5 leads
Claude Sonnet 5: 42.8 (#18), GPT-5.6 Luna: 34.4 (#45)
| Benchmark | Claude Sonnet 5 | GPT-5.6 Luna |
|---|---|---|
| APEX-Agents | 54.5% | 43% |
| Vending-Bench 2 | 6,378 | 4,095 |
| BALROG | — | 45.6% |
| GBAEval | 65.3% | — |
| GDP.pdf | — | 22.7% |
| LMArena Search | 1194 | — |
Reasoning Claude Sonnet 5 leads
Claude Sonnet 5: 49.1 (#39), GPT-5.6 Luna: 47.6 (#43)
| Benchmark | Claude Sonnet 5 | GPT-5.6 Luna |
|---|---|---|
| SimpleBench | 60.6% | 46.8% |
| NYT Connections (extended) | 75.1% | 69.4% |
| CritPt | 16.9% | 20.6% |
| Chess Puzzles | 35% | 40% |
| LMArena Hard Prompts | 1461 | 1451 |
| Mystery Game Puzzles | 35% | 21% |
| DTBench | 92.5% | 89.1% |
| LMCA | 50% | 48.5% |
| Surface Evolver Bench | 60% | 61.9% |
| Epoch Capabilities Index | 156.21 | 156.39 |
| ARC-AGI-2 | — | 59.5% |
| Kagi LLM Benchmark | — | 49.1% |
| ARC-AGI-1 | — | 88% |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 61.1 | — |
Math GPT-5.6 Luna leads
Claude Sonnet 5: 66.2 (#27), GPT-5.6 Luna: 77.7 (#14)
| Benchmark | Claude Sonnet 5 | GPT-5.6 Luna |
|---|---|---|
| FrontierMath (Tiers 1-3) | 65.6% | 82.1% |
| FrontierMath Tier 4 | 29.3% | 61% |
| OTIS Mock AIME 2024-2025 | 94.7% | 98.3% |
| ProofBench | 77% | 60% |
| LMArena Math | 1467 | 1458 |
Knowledge GPT-5.6 Luna leads
Claude Sonnet 5: 55.6 (#47), GPT-5.6 Luna: 58.5 (#34)
| Benchmark | Claude Sonnet 5 | GPT-5.6 Luna |
|---|---|---|
| GPQA Diamond | 90.5% | 91.6% |
| SimpleQA Verified | 33.7% | 41% |
| LMArena Expert | 1490 | 1478 |
Multimodal Too close to call
Claude Sonnet 5: 42.4 (#31), GPT-5.6 Luna: 42.7 (#28)
| Benchmark | Claude Sonnet 5 | GPT-5.6 Luna |
|---|---|---|
| LMArena Vision | 1274 | 1258 |
| Blueprint-Bench 2 | 24.9% | 22.6% |
| LMArena Document | 1466 | 1457 |
| Furniture Assembly | — | 42.5% |
Multilingual Claude Sonnet 5 leads
Claude Sonnet 5: 53.8 (#55), GPT-5.6 Luna: 52.8 (#78)
| Benchmark | Claude Sonnet 5 | GPT-5.6 Luna |
|---|---|---|
| LMArena Non-English | 1431 | 1417 |
| LMArena Chinese | 1477 | 1470 |
| LMArena French | 1460 | 1456 |
| LMArena German | 1440 | 1454 |
| LMArena Japanese | 1422 | 1411 |
| LMArena Korean | 1411 | 1415 |
| LMArena Russian | 1451 | 1428 |
| LMArena Spanish | 1437 | 1448 |
Instruction Following Too close to call
Claude Sonnet 5: 76.3 (#41), GPT-5.6 Luna: 75.6 (#57)
| Benchmark | Claude Sonnet 5 | GPT-5.6 Luna |
|---|---|---|
| LMArena Instruction Following | 1452 | 1437 |
Long Context Too close to call
Claude Sonnet 5: 44.8 (#55), GPT-5.6 Luna: 43.9 (#82)
| Benchmark | Claude Sonnet 5 | GPT-5.6 Luna |
|---|---|---|
| LMArena Longer Query | 1463 | 1436 |
Writing & Preference Claude Sonnet 5 leads
Claude Sonnet 5: 69.2 (#25), GPT-5.6 Luna: 68.0 (#29)
| Benchmark | Claude Sonnet 5 | GPT-5.6 Luna |
|---|---|---|
| LMArena Text | 1442 | 1431 |
| LMArena Creative Writing | 1416 | 1396 |
| EQ-Bench Creative Writing | 1794 | 1829 |
| EQ-Bench 4 | 1236 | 1156 |
| LMArena Multi-Turn | 1454 | 1434 |
Frequently asked questions
Is Claude Sonnet 5 better than GPT-5.6 Luna?
Claude Sonnet 5 and GPT-5.6 Luna score almost the same on the Noometry Index (54.6 vs 54.6), so choose on price, context window or the category you care about most.
Which is cheaper, Claude Sonnet 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 Sonnet 5 lists at $2 and $10.
Is Claude Sonnet 5 or GPT-5.6 Luna better for coding?
They score almost the same on coding (55.5 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 1M.
How many benchmarks do Claude Sonnet 5 and GPT-5.6 Luna share?
46 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and GPT-5.6 Luna has 52.