# DeepSeek-R1-Distill-Qwen-14B vs GPT-5.6 Luna

> GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 32.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-r1-distill-qwen-14b-vs-gpt-5-6-luna
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. DeepSeek-R1-Distill-Qwen-14B scores higher in 0 categories and GPT-5.6 Luna in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 35.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 50.6% for DeepSeek-R1-Distill-Qwen-14B and 98.3% for GPT-5.6 Luna.
- DeepSeek-R1-Distill-Qwen-14B has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-R1-Distill-Qwen-14B | GPT-5.6 Luna |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 32.7 | 54.6 |
| Rank | 252 | 30 |
| Context | — | 1.05M |
| Input $/M | — | $0.20 |
| Output $/M | — | $1.20 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-R1-Distill-Qwen-14B: 36.9 (#200)
- GPT-5.6 Luna: 54.5 (#28)

| Benchmark | DeepSeek-R1-Distill-Qwen-14B | GPT-5.6 Luna |
|---|---|---|
| DeepSWE | — | 67.2% |
| FrontierCode | — | 39.8% |
| CursorBench | — | 35.9% |
| LMArena WebDev | — | 1519 |
| SciCode | — | 53.6% |
| WeirdML | — | 60.9% |
| BigCodeBench Instruct | 38.1% | — |
| LMArena Coding | — | 1466 |
| BigCodeBench Complete | 48.4% | — |
| ALE-Bench | — | 1,667 |

## Agentic & Tool Use

- DeepSeek-R1-Distill-Qwen-14B: —
- GPT-5.6 Luna: 34.4 (#45)

| Benchmark | DeepSeek-R1-Distill-Qwen-14B | GPT-5.6 Luna |
|---|---|---|
| APEX-Agents | — | 43% |
| BALROG | — | 45.6% |
| GDP.pdf | — | 22.7% |
| Vending-Bench 2 | — | 4,095 |

## Reasoning

- DeepSeek-R1-Distill-Qwen-14B: 19.2 (#263)
- GPT-5.6 Luna: 47.6 (#43)

| Benchmark | DeepSeek-R1-Distill-Qwen-14B | GPT-5.6 Luna |
|---|---|---|
| Chess Puzzles | 1% | 40% |
| Epoch Capabilities Index | 135.43 | 156.39 |
| ARC-AGI-2 | — | 59.5% |
| SimpleBench | — | 46.8% |
| Kagi LLM Benchmark | — | 49.1% |
| NYT Connections (extended) | — | 69.4% |
| ARC-AGI-1 | — | 88% |
| CritPt | — | 20.6% |
| LMArena Hard Prompts | — | 1451 |
| Mystery Game Puzzles | — | 21% |
| DTBench | — | 89.1% |
| LMCA | — | 48.5% |
| Surface Evolver Bench | — | 61.9% |

## Math

- DeepSeek-R1-Distill-Qwen-14B: 35.5 (#184)
- GPT-5.6 Luna: 77.7 (#14)

| Benchmark | DeepSeek-R1-Distill-Qwen-14B | GPT-5.6 Luna |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 50.6% | 98.3% |
| FrontierMath (Tiers 1-3) | — | 82.1% |
| FrontierMath Tier 4 | — | 61% |
| ProofBench | — | 60% |
| LMArena Math | — | 1458 |
| MATH Level 5 | 87.1% | — |

## Knowledge

- DeepSeek-R1-Distill-Qwen-14B: 24.1 (#270)
- GPT-5.6 Luna: 58.5 (#34)

| Benchmark | DeepSeek-R1-Distill-Qwen-14B | GPT-5.6 Luna |
|---|---|---|
| GPQA Diamond | 44.7% | 91.6% |
| SimpleQA Verified | — | 41% |
| LMArena Expert | — | 1478 |

## Multimodal

- DeepSeek-R1-Distill-Qwen-14B: —
- GPT-5.6 Luna: 42.7 (#28)

| Benchmark | DeepSeek-R1-Distill-Qwen-14B | GPT-5.6 Luna |
|---|---|---|
| LMArena Vision | — | 1258 |
| Blueprint-Bench 2 | — | 22.6% |
| Furniture Assembly | — | 42.5% |
| LMArena Document | — | 1457 |

## Multilingual

- DeepSeek-R1-Distill-Qwen-14B: —
- GPT-5.6 Luna: 52.8 (#78)

| Benchmark | DeepSeek-R1-Distill-Qwen-14B | GPT-5.6 Luna |
|---|---|---|
| LMArena Non-English | — | 1417 |
| LMArena Chinese | — | 1470 |
| LMArena French | — | 1456 |
| LMArena German | — | 1454 |
| LMArena Japanese | — | 1411 |
| LMArena Korean | — | 1415 |
| LMArena Russian | — | 1428 |
| LMArena Spanish | — | 1448 |

## Instruction Following

- DeepSeek-R1-Distill-Qwen-14B: —
- GPT-5.6 Luna: 75.6 (#57)

| Benchmark | DeepSeek-R1-Distill-Qwen-14B | GPT-5.6 Luna |
|---|---|---|
| LMArena Instruction Following | — | 1437 |

## Long Context

- DeepSeek-R1-Distill-Qwen-14B: —
- GPT-5.6 Luna: 43.9 (#82)

| Benchmark | DeepSeek-R1-Distill-Qwen-14B | GPT-5.6 Luna |
|---|---|---|
| LMArena Longer Query | — | 1436 |

## Writing & Preference

- DeepSeek-R1-Distill-Qwen-14B: —
- GPT-5.6 Luna: 68.0 (#29)

| Benchmark | DeepSeek-R1-Distill-Qwen-14B | GPT-5.6 Luna |
|---|---|---|
| LMArena Text | — | 1431 |
| LMArena Creative Writing | — | 1396 |
| EQ-Bench Creative Writing | — | 1829 |
| EQ-Bench 4 | — | 1156 |
| LMArena Multi-Turn | — | 1434 |

## FAQ

### Is DeepSeek-R1-Distill-Qwen-14B better than GPT-5.6 Luna?

GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 32.7 on the Noometry Index.

### Is DeepSeek-R1-Distill-Qwen-14B or GPT-5.6 Luna better for coding?

GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 36.9 in the Noometry coding category.

### How many benchmarks do DeepSeek-R1-Distill-Qwen-14B and GPT-5.6 Luna share?

4 benchmarks have published results for both models. DeepSeek-R1-Distill-Qwen-14B has 7 scored results on Noometry and GPT-5.6 Luna has 52.