Model comparison
GPT-5.6 Luna vs StarCoder 2 3B
GPT-5.6 Luna has enough public results to be ranked (#30); StarCoder 2 3B does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
NVIDIASummary
- They share 1 benchmark with published results for both. GPT-5.6 Luna scores higher in 1 category and StarCoder 2 3B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where GPT-5.6 Luna leads 54.5 to 33.5.
- StarCoder 2 3B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.6 Luna | StarCoder 2 3B | |
|---|---|---|
| Provider | OpenAI | NVIDIA |
| Noometry Index | 54.6 | 36.3 |
| Released | 2026-07-09 | 2024-02-22 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.20 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 52 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Luna leads
GPT-5.6 Luna: 54.5 (#28), StarCoder 2 3B: 33.5
| Benchmark | GPT-5.6 Luna | StarCoder 2 3B |
|---|---|---|
| DeepSWE | 67.2% | — |
| FrontierCode | 39.8% | — |
| CursorBench | 35.9% | — |
| LMArena WebDev | 1519 | — |
| SciCode | 53.6% | — |
| WeirdML | 60.9% | — |
| LMArena Coding | 1466 | — |
| BigCodeBench Complete | — | 21.4% |
| ALE-Bench | 1,667 | — |
| HumanEval+ | — | 27.4% |
Agentic & Tool Use Not comparable
GPT-5.6 Luna: 34.4 (#45), StarCoder 2 3B: —
| Benchmark | GPT-5.6 Luna | StarCoder 2 3B |
|---|---|---|
| APEX-Agents | 43% | — |
| BALROG | 45.6% | — |
| GDP.pdf | 22.7% | — |
| Vending-Bench 2 | 4,095 | — |
Reasoning Not comparable
GPT-5.6 Luna: 47.6 (#43), StarCoder 2 3B: —
| Benchmark | GPT-5.6 Luna | StarCoder 2 3B |
|---|---|---|
| Epoch Capabilities Index | 156.39 | 88.76 |
| 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 | 1451 | — |
| Mystery Game Puzzles | 21% | — |
| DTBench | 89.1% | — |
| LMCA | 48.5% | — |
| Surface Evolver Bench | 61.9% | — |
| WinoGrande | — | 57.1% |
Math Not comparable
GPT-5.6 Luna: 77.7 (#14), StarCoder 2 3B: —
| Benchmark | GPT-5.6 Luna | StarCoder 2 3B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.1% | — |
| FrontierMath Tier 4 | 61% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
| ProofBench | 60% | — |
| LMArena Math | 1458 | — |
| GSM8K | — | 21.6% |
Knowledge Not comparable
GPT-5.6 Luna: 58.5 (#34), StarCoder 2 3B: —
| Benchmark | GPT-5.6 Luna | StarCoder 2 3B |
|---|---|---|
| GPQA Diamond | 91.6% | — |
| SimpleQA Verified | 41% | — |
| LMArena Expert | 1478 | — |
| ARC (AI2) Challenge | — | 34.2% |
| MMLU | — | 36.6% |
Multimodal Not comparable
GPT-5.6 Luna: 42.7 (#28), StarCoder 2 3B: —
| Benchmark | GPT-5.6 Luna | StarCoder 2 3B |
|---|---|---|
| LMArena Vision | 1258 | — |
| Blueprint-Bench 2 | 22.6% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1457 | — |
Multilingual Not comparable
GPT-5.6 Luna: 52.8 (#78), StarCoder 2 3B: —
| Benchmark | GPT-5.6 Luna | StarCoder 2 3B |
|---|---|---|
| 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 Not comparable
GPT-5.6 Luna: 75.6 (#57), StarCoder 2 3B: —
| Benchmark | GPT-5.6 Luna | StarCoder 2 3B |
|---|---|---|
| LMArena Instruction Following | 1437 | — |
Long Context Not comparable
GPT-5.6 Luna: 43.9 (#82), StarCoder 2 3B: —
| Benchmark | GPT-5.6 Luna | StarCoder 2 3B |
|---|---|---|
| LMArena Longer Query | 1436 | — |
Writing & Preference Not comparable
GPT-5.6 Luna: 68.0 (#29), StarCoder 2 3B: —
| Benchmark | GPT-5.6 Luna | StarCoder 2 3B |
|---|---|---|
| LMArena Text | 1431 | — |
| LMArena Creative Writing | 1396 | — |
| EQ-Bench Creative Writing | 1829 | — |
| EQ-Bench 4 | 1156 | — |
| LMArena Multi-Turn | 1434 | — |
Frequently asked questions
Is GPT-5.6 Luna better than StarCoder 2 3B?
GPT-5.6 Luna has enough public results to be ranked (#30); StarCoder 2 3B does not yet, so treat this comparison as directional.
Is GPT-5.6 Luna or StarCoder 2 3B better for coding?
GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 33.5 in the Noometry coding category.
How many benchmarks do GPT-5.6 Luna and StarCoder 2 3B share?
1 benchmark has published results for both models. GPT-5.6 Luna has 52 scored results on Noometry and StarCoder 2 3B has 7.