# GPT-5.6 Luna vs StarCoder 2 15B

> GPT-5.6 Luna has enough public results to be ranked (#24); StarCoder 2 15B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/gpt-5-6-luna-vs-starcoder-2-15b
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. GPT-5.6 Luna scores higher in 1 category and StarCoder 2 15B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where GPT-5.6 Luna leads 53.9 to 36.0.
- StarCoder 2 15B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.6 Luna | StarCoder 2 15B |
|---|---|---|
| Provider | OpenAI | NVIDIA |
| Noometry Index | 54.7 | 37.5 |
| Rank | 24 | — |
| Context | 1.05M | — |
| Input $/M | $0.20 | — |
| Output $/M | $1.20 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5.6 Luna: 53.9 (#25)
- StarCoder 2 15B: 36.0

| Benchmark | GPT-5.6 Luna | StarCoder 2 15B |
|---|---|---|
| DeepSWE | 67.2% | — |
| FrontierCode | 39.8% | — |
| CursorBench | 35.9% | — |
| LMArena WebDev | 1517 | — |
| SciCode | 53.6% | — |
| WeirdML | 60.9% | — |
| LMArena Coding | 1466 | — |
| BigCodeBench Complete | — | 38.4% |
| ALE-Bench | 1,667 | — |
| HumanEval+ | — | 37.8% |

## Agentic & Tool Use

- GPT-5.6 Luna: 35.3 (#37)
- StarCoder 2 15B: —

| Benchmark | GPT-5.6 Luna | StarCoder 2 15B |
|---|---|---|
| BALROG | 45.6% | — |
| GDP.pdf | 22.7% | — |
| Vending-Bench 2 | 4,095 | — |

## Reasoning

- GPT-5.6 Luna: 47.5 (#38)
- StarCoder 2 15B: —

| Benchmark | GPT-5.6 Luna | StarCoder 2 15B |
|---|---|---|
| Epoch Capabilities Index | 156.32 | 104.61 |
| 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% | — |
| Chess Puzzles | 40% | — |
| LMArena Hard Prompts | 1452 | — |
| Mystery Game Puzzles | 21% | — |
| DTBench | 89.1% | — |
| LMCA | 48.5% | — |
| Surface Evolver Bench | 61.9% | — |
| WinoGrande | — | 64.3% |

## Math

- GPT-5.6 Luna: 77.5 (#12)
- StarCoder 2 15B: —

| Benchmark | GPT-5.6 Luna | StarCoder 2 15B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.1% | — |
| FrontierMath Tier 4 | 61% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
| ProofBench | 60% | — |
| LMArena Math | 1455 | — |
| GSM8K | — | 57.7% |

## Knowledge

- GPT-5.6 Luna: 58.6 (#31)
- StarCoder 2 15B: —

| Benchmark | GPT-5.6 Luna | StarCoder 2 15B |
|---|---|---|
| GPQA Diamond | 91.6% | — |
| SimpleQA Verified | 41% | — |
| LMArena Expert | 1479 | — |
| ARC (AI2) Challenge | — | 47.2% |
| MMLU | — | 64.1% |

## Multimodal

- GPT-5.6 Luna: 43.0 (#22)
- StarCoder 2 15B: —

| Benchmark | GPT-5.6 Luna | StarCoder 2 15B |
|---|---|---|
| LMArena Vision | 1259 | — |
| Blueprint-Bench 2 | 22.6% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1457 | — |

## Multilingual

- GPT-5.6 Luna: 53.0 (#73)
- StarCoder 2 15B: —

| Benchmark | GPT-5.6 Luna | StarCoder 2 15B |
|---|---|---|
| LMArena Non-English | 1418 | — |
| LMArena Chinese | 1469 | — |
| LMArena French | 1457 | — |
| LMArena German | 1459 | — |
| LMArena Japanese | 1416 | — |
| LMArena Korean | 1414 | — |
| LMArena Russian | 1428 | — |
| LMArena Spanish | 1445 | — |

## Instruction Following

- GPT-5.6 Luna: 76.0 (#48)
- StarCoder 2 15B: —

| Benchmark | GPT-5.6 Luna | StarCoder 2 15B |
|---|---|---|
| LMArena Instruction Following | 1440 | — |

## Long Context

- GPT-5.6 Luna: 43.9 (#78)
- StarCoder 2 15B: —

| Benchmark | GPT-5.6 Luna | StarCoder 2 15B |
|---|---|---|
| LMArena Longer Query | 1437 | — |

## Writing & Preference

- GPT-5.6 Luna: 68.3 (#27)
- StarCoder 2 15B: —

| Benchmark | GPT-5.6 Luna | StarCoder 2 15B |
|---|---|---|
| LMArena Text | 1432 | — |
| LMArena Creative Writing | 1397 | — |
| EQ-Bench Creative Writing | 1829 | — |
| EQ-Bench 4 | 1156 | — |
| LMArena Multi-Turn | 1433 | — |

## FAQ

### Is GPT-5.6 Luna better than StarCoder 2 15B?

GPT-5.6 Luna has enough public results to be ranked (#24); StarCoder 2 15B does not yet, so treat this comparison as directional.

### Is GPT-5.6 Luna or StarCoder 2 15B better for coding?

GPT-5.6 Luna scores higher on coding benchmarks: 53.9 versus 36.0 in the Noometry coding category.

### How many benchmarks do GPT-5.6 Luna and StarCoder 2 15B share?

1 benchmark has published results for both models. GPT-5.6 Luna has 51 scored results on Noometry and StarCoder 2 15B has 7.