Model comparison
DeepSeek-R1 vs GPT-5.6 Luna
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 42.3 on the Noometry Index.
Last verified . 30 shared benchmarks.
DeepSeekSummary
- They share 30 benchmarks with published results for both. DeepSeek-R1 scores higher in 1 category and GPT-5.6 Luna in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 43.8.
- The biggest single-benchmark swing is ARC-AGI-1: 21.2% for DeepSeek-R1 and 88% for GPT-5.6 Luna.
- GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $0.50 / $2.15 for DeepSeek-R1.
- GPT-5.6 Luna accepts more context: 1.05M tokens versus 164K.
Side by side
| DeepSeek-R1 | GPT-5.6 Luna | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 42.3 | 54.6 |
| Released | 2025-01-20 | 2026-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | 164K | 1.05M |
| Max output | 64K | 128K |
| Input $ / M tokens | $0.50 | $0.20 |
| Output $ / M tokens | $2.15 | $1.20 |
| Results tracked | 52 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Luna leads
DeepSeek-R1: 46.3 (#68), GPT-5.6 Luna: 54.5 (#28)
| Benchmark | DeepSeek-R1 | GPT-5.6 Luna |
|---|---|---|
| SciCode | 35.7% | 53.6% |
| WeirdML | 41.6% | 60.9% |
| LMArena Coding | 1427 | 1466 |
| ALE-Bench | 804.12 | 1,667 |
| DeepSWE | — | 67.2% |
| FrontierCode | — | 39.8% |
| Aider Polyglot | 71.4% | — |
| CursorBench | — | 35.9% |
| LMArena WebDev | — | 1519 |
| LiveBench Coding | 66.7% | — |
| AlgoTune | 1.7 | — |
Agentic & Tool Use GPT-5.6 Luna leads
DeepSeek-R1: 30.7 (#75), GPT-5.6 Luna: 34.4 (#45)
| Benchmark | DeepSeek-R1 | GPT-5.6 Luna |
|---|---|---|
| BALROG | 34.9% | 45.6% |
| APEX-Agents | — | 43% |
| DeepResearch Bench | 35.1% | — |
| GDP.pdf | — | 22.7% |
| METR Time Horizons | 53.8% | — |
| Vending-Bench 2 | — | 4,095 |
Reasoning GPT-5.6 Luna leads
DeepSeek-R1: 18.6 (#278), GPT-5.6 Luna: 47.6 (#43)
| Benchmark | DeepSeek-R1 | GPT-5.6 Luna |
|---|---|---|
| ARC-AGI-2 | 1.3% | 59.5% |
| SimpleBench | 40.8% | 46.8% |
| Kagi LLM Benchmark | 69.4% | 49.1% |
| ARC-AGI-1 | 21.2% | 88% |
| CritPt | 1.1% | 20.6% |
| LMArena Hard Prompts | 1416 | 1451 |
| Epoch Capabilities Index | 141.29 | 156.39 |
| NYT Connections (extended) | — | 69.4% |
| Chess Puzzles | — | 40% |
| LiveBench Reasoning | 83.2% | — |
| Mystery Game Puzzles | — | 21% |
| DTBench | — | 89.1% |
| LiveBench Data Analysis | 69.8% | — |
| LMCA | — | 48.5% |
| Surface Evolver Bench | — | 61.9% |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |
Math GPT-5.6 Luna leads
DeepSeek-R1: 43.8 (#79), GPT-5.6 Luna: 77.7 (#14)
| Benchmark | DeepSeek-R1 | GPT-5.6 Luna |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | 98.3% |
| LMArena Math | 1400 | 1458 |
| FrontierMath (Tiers 1-3) | — | 82.1% |
| FrontierMath Tier 4 | — | 61% |
| ProofBench | — | 60% |
| Omni-MATH | 42.4% | — |
| LiveBench Math | 80.7% | — |
| MATH Level 5 | 96.6% | — |
Knowledge GPT-5.6 Luna leads
DeepSeek-R1: 44.5 (#87), GPT-5.6 Luna: 58.5 (#34)
| Benchmark | DeepSeek-R1 | GPT-5.6 Luna |
|---|---|---|
| GPQA Diamond | 76.3% | 91.6% |
| LMArena Expert | 1394 | 1478 |
| SimpleQA Verified | — | 41% |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| Vectara Hallucination Rate | 11.3% | — |
| GPQA (HELM) | 66.6% | — |
Multimodal Not comparable
DeepSeek-R1: —, GPT-5.6 Luna: 42.7 (#28)
| Benchmark | DeepSeek-R1 | GPT-5.6 Luna |
|---|---|---|
| LMArena Vision | — | 1258 |
| Blueprint-Bench 2 | — | 22.6% |
| Furniture Assembly | — | 42.5% |
| LMArena Document | — | 1457 |
Multilingual Too close to call
DeepSeek-R1: 52.4 (#85), GPT-5.6 Luna: 52.8 (#78)
| Benchmark | DeepSeek-R1 | GPT-5.6 Luna |
|---|---|---|
| LMArena Non-English | 1412 | 1417 |
| LMArena Chinese | 1442 | 1470 |
| LMArena French | 1417 | 1456 |
| LMArena German | 1404 | 1454 |
| LMArena Japanese | 1391 | 1411 |
| LMArena Korean | 1360 | 1415 |
| LMArena Russian | 1423 | 1428 |
| LMArena Spanish | 1411 | 1448 |
Instruction Following GPT-5.6 Luna leads
DeepSeek-R1: 72.0 (#143), GPT-5.6 Luna: 75.6 (#57)
| Benchmark | DeepSeek-R1 | GPT-5.6 Luna |
|---|---|---|
| LMArena Instruction Following | 1382 | 1437 |
| LiveBench Instruction Following | 80.5% | — |
| IFEval | 78.4% | — |
Long Context DeepSeek-R1 leads
DeepSeek-R1: 45.4 (#36), GPT-5.6 Luna: 43.9 (#82)
| Benchmark | DeepSeek-R1 | GPT-5.6 Luna |
|---|---|---|
| LMArena Longer Query | 1391 | 1436 |
| Fiction.LiveBench | 75% | — |
Writing & Preference GPT-5.6 Luna leads
DeepSeek-R1: 61.4 (#88), GPT-5.6 Luna: 68.0 (#29)
| Benchmark | DeepSeek-R1 | GPT-5.6 Luna |
|---|---|---|
| LMArena Text | 1428 | 1431 |
| LMArena Creative Writing | 1405 | 1396 |
| EQ-Bench Creative Writing | 1500 | 1829 |
| LMArena Multi-Turn | 1405 | 1434 |
| Short-Story Creative Writing | 83% | — |
| WildBench | 82.8% | — |
| EQ-Bench 4 | — | 1156 |
| LiveBench Language | 48.5% | — |
Frequently asked questions
Is DeepSeek-R1 better than GPT-5.6 Luna?
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 42.3 on the Noometry Index.
Which is cheaper, DeepSeek-R1 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; DeepSeek-R1 lists at $0.50 and $2.15.
Is DeepSeek-R1 or GPT-5.6 Luna better for coding?
GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 46.3 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Luna does, with 1.05M tokens against 164K.
How many benchmarks do DeepSeek-R1 and GPT-5.6 Luna share?
30 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and GPT-5.6 Luna has 52.