Model comparison
Claude Sonnet 4.6 vs GPT-6 Luna
Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 45.1 on the Noometry Index. GPT-6 Luna costs 30× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 7 categories and GPT-6 Luna in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 4.6 leads 51.9 to 35.6.
- The biggest single-benchmark swing is DeepSWE: 29.9% for Claude Sonnet 4.6 and 66.6% for GPT-6 Luna.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
- GPT-6 Luna accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Sonnet 4.6 | GPT-6 Luna | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 50.1 | 45.1 |
| Released | 2026-02-17 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $3 | $0.10 |
| Output $ / M tokens | $15 | $0.50 |
| Results tracked | 57 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Luna leads
Claude Sonnet 4.6: 46.0 (#62), GPT-6 Luna: 54.7 (#24)
| Benchmark | Claude Sonnet 4.6 | GPT-6 Luna |
|---|---|---|
| DeepSWE | 29.9% | 66.6% |
| FrontierCode | 24.3% | 42.4% |
| LMArena WebDev | 1521 | 1583 |
| LMArena Coding | 1504 | 1448 |
| SWE-bench Verified | 75.2% | — |
| SciCode | 46.8% | — |
| WeirdML | 66.1% | — |
| ALE-Bench | 1,327 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4.6: 39.1 (#26), GPT-6 Luna: —
| Benchmark | Claude Sonnet 4.6 | GPT-6 Luna |
|---|---|---|
| Terminal-Bench | 53.4% | — |
| APEX-Agents | 43% | — |
| OSWorld 2.0 | 9.3% | — |
| DeepResearch Bench | 54.9% | — |
| OSWorld | 72.1% | — |
| ExploitBench | 23.6% | — |
| GBAEval | 48.8% | — |
| GDP.pdf | 18% | — |
| LMArena Search | 1221 | — |
| Vending-Bench 2 | 7,204 | — |
Reasoning Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 46.1 (#40), GPT-6 Luna: 31.7 (#68)
| Benchmark | Claude Sonnet 4.6 | GPT-6 Luna |
|---|---|---|
| NYT Connections (extended) | 80.9% | 68.7% |
| LMArena Hard Prompts | 1485 | 1415 |
| ARC-AGI-2 | 60.4% | — |
| ARC-AGI-1 | 86.5% | — |
| CritPt | 3.1% | — |
| Chess Puzzles | 13% | — |
| Thematic Generalization | 76.3% | — |
| Mystery Game Puzzles | 16% | — |
| DTBench | 89.9% | — |
| LMCA | 46.5% | — |
| Epoch Capabilities Index | 152.25 | — |
| ForecastBench | 62 | — |
Math Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 51.9 (#41), GPT-6 Luna: 35.6 (#140)
| Benchmark | Claude Sonnet 4.6 | GPT-6 Luna |
|---|---|---|
| LMArena Math | 1463 | 1396 |
| OTIS Mock AIME 2024-2025 | 85.8% | — |
| ProofBench | 45% | — |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 8.3% | — |
Knowledge Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 51.6 (#60), GPT-6 Luna: 40.1 (#110)
| Benchmark | Claude Sonnet 4.6 | GPT-6 Luna |
|---|---|---|
| LMArena Expert | 1500 | 1458 |
| GPQA Diamond | 87.4% | — |
| SimpleQA Verified | 35.5% | — |
| Vectara Hallucination Rate | 10.6% | — |
Multimodal GPT-6 Luna leads
Claude Sonnet 4.6: 38.0 (#61), GPT-6 Luna: 42.0 (#27)
| Benchmark | Claude Sonnet 4.6 | GPT-6 Luna |
|---|---|---|
| LMArena Vision | 1283 | — |
| Blueprint-Bench 2 | 6.7% | — |
| Furniture Assembly | — | 44.2% |
| LMArena Document | 1482 | — |
Multilingual Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 54.6 (#39), GPT-6 Luna: 51.0 (#111)
| Benchmark | Claude Sonnet 4.6 | GPT-6 Luna |
|---|---|---|
| LMArena Non-English | 1440 | 1390 |
| LMArena Chinese | 1491 | 1425 |
| LMArena Russian | 1440 | 1392 |
| LMArena Spanish | 1465 | 1416 |
| LMArena French | 1465 | — |
| LMArena German | 1428 | — |
| LMArena Japanese | 1419 | — |
| LMArena Korean | 1411 | — |
Instruction Following Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 77.6 (#23), GPT-6 Luna: 74.7 (#85)
| Benchmark | Claude Sonnet 4.6 | GPT-6 Luna |
|---|---|---|
| LMArena Instruction Following | 1476 | 1414 |
Long Context Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 45.3 (#40), GPT-6 Luna: 43.3 (#95)
| Benchmark | Claude Sonnet 4.6 | GPT-6 Luna |
|---|---|---|
| LMArena Longer Query | 1479 | 1417 |
Writing & Preference Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 70.4 (#22), GPT-6 Luna: 58.4 (#115)
| Benchmark | Claude Sonnet 4.6 | GPT-6 Luna |
|---|---|---|
| LMArena Text | 1458 | 1392 |
| LMArena Creative Writing | 1435 | 1357 |
| LMArena Multi-Turn | 1464 | 1400 |
| EQ-Bench Creative Writing | 1810 | — |
| EQ-Bench 4 | 1207 | — |
Frequently asked questions
Is Claude Sonnet 4.6 better than GPT-6 Luna?
Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 45.1 on the Noometry Index. GPT-6 Luna costs 30× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 4.6 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 Sonnet 4.6 lists at $3 and $15.
Is Claude Sonnet 4.6 or GPT-6 Luna better for coding?
GPT-6 Luna scores higher on coding benchmarks: 54.7 versus 46.0 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 Sonnet 4.6 and GPT-6 Luna share?
17 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and GPT-6 Luna has 18.