Model comparison
Llama 4 Maverick vs StarCoder 2 15B
Llama 4 Maverick has enough public results to be ranked (#276); StarCoder 2 15B does not yet, so treat this comparison as directional.
Last verified . 2 shared benchmarks.
Meta
NVIDIASummary
- They share 2 benchmarks with published results for both. Llama 4 Maverick scores higher in 0 categories and StarCoder 2 15B in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where StarCoder 2 15B leads 36.0 to 26.3.
- The biggest single-benchmark swing is BigCodeBench Complete: 61.4% for Llama 4 Maverick and 38.4% for StarCoder 2 15B.
Side by side
| Llama 4 Maverick | StarCoder 2 15B | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 30.6 | 37.5 |
| Released | 2025-04-05 | 2024-02-20 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.19 | — |
| Output $ / M tokens | $0.65 | — |
| Results tracked | 54 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding StarCoder 2 15B leads
Llama 4 Maverick: 26.3 (#318), StarCoder 2 15B: 36.0
| Benchmark | Llama 4 Maverick | StarCoder 2 15B |
|---|---|---|
| BigCodeBench Complete | 61.4% | 38.4% |
| SWE-bench Verified (bash only) | 21% | — |
| Aider Polyglot | 15.6% | — |
| SciCode | 33.1% | — |
| WeirdML | 24.5% | — |
| BigCodeBench Instruct | 49.7% | — |
| LMArena Coding | 1302 | — |
| ALE-Bench | 172.97 | — |
| HumanEval+ | — | 37.8% |
Agentic & Tool Use Not comparable
Llama 4 Maverick: 27.9 (#86), StarCoder 2 15B: —
| Benchmark | Llama 4 Maverick | StarCoder 2 15B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.3% | — |
Reasoning Not comparable
Llama 4 Maverick: 10.1 (#337), StarCoder 2 15B: —
| Benchmark | Llama 4 Maverick | StarCoder 2 15B |
|---|---|---|
| Epoch Capabilities Index | 132.2 | 104.61 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 27.7% | — |
| Kagi LLM Benchmark | 55.9% | — |
| NYT Connections (extended) | 8% | — |
| ARC-AGI-1 | 4.4% | — |
| CritPt | 0% | — |
| EnigmaEval | 0.6% | — |
| LMArena Hard Prompts | 1281 | — |
| DTBench | 61.9% | — |
| LMCA | 15.9% | — |
| ForecastBench | 57.5 | — |
| WinoGrande | — | 64.3% |
Math Not comparable
Llama 4 Maverick: 24.6 (#256), StarCoder 2 15B: —
| Benchmark | Llama 4 Maverick | StarCoder 2 15B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 20.6% | — |
| Omni-MATH | 42.2% | — |
| LMArena Math | 1299 | — |
| MATH Level 5 | 73% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
| GSM8K | — | 57.7% |
Knowledge Not comparable
Llama 4 Maverick: 33.3 (#196), StarCoder 2 15B: —
| Benchmark | Llama 4 Maverick | StarCoder 2 15B |
|---|---|---|
| GPQA Diamond | 67% | — |
| Humanity's Last Exam | 5.7% | — |
| MMLU-Pro | 81% | — |
| Confabulations | 22.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
| GPQA (HELM) | 65% | — |
| LMArena Expert | 1259 | — |
| ARC (AI2) Challenge | — | 47.2% |
| MMLU | — | 64.1% |
Multimodal Not comparable
Llama 4 Maverick: 30.9 (#100), StarCoder 2 15B: —
| Benchmark | Llama 4 Maverick | StarCoder 2 15B |
|---|---|---|
| LMArena Vision | 1141 | — |
| GeoBench | 52% | — |
| SpatialViz-Bench | 31.8% | — |
Multilingual Not comparable
Llama 4 Maverick: 42.4 (#190), StarCoder 2 15B: —
| Benchmark | Llama 4 Maverick | StarCoder 2 15B |
|---|---|---|
| LMArena Non-English | 1269 | — |
| LMArena Chinese | 1277 | — |
| LMArena French | 1258 | — |
| LMArena German | 1291 | — |
| LMArena Japanese | 1207 | — |
| LMArena Korean | 1203 | — |
| LMArena Russian | 1286 | — |
| LMArena Spanish | 1293 | — |
Instruction Following Not comparable
Llama 4 Maverick: 71.9 (#140), StarCoder 2 15B: —
| Benchmark | Llama 4 Maverick | StarCoder 2 15B |
|---|---|---|
| IFEval | 90.8% | — |
| LMArena Instruction Following | 1267 | — |
Long Context Not comparable
Llama 4 Maverick: 31.4 (#274), StarCoder 2 15B: —
| Benchmark | Llama 4 Maverick | StarCoder 2 15B |
|---|---|---|
| Fiction.LiveBench | 46.2% | — |
| LMArena Longer Query | 1280 | — |
Writing & Preference Not comparable
Llama 4 Maverick: 39.0 (#247), StarCoder 2 15B: —
| Benchmark | Llama 4 Maverick | StarCoder 2 15B |
|---|---|---|
| LMArena Text | 1287 | — |
| LMArena Creative Writing | 1266 | — |
| Short-Story Creative Writing | 62% | — |
| EQ-Bench Creative Writing | 860 | — |
| WildBench | 80% | — |
| LMArena Multi-Turn | 1289 | — |
Frequently asked questions
Is Llama 4 Maverick better than StarCoder 2 15B?
Llama 4 Maverick has enough public results to be ranked (#276); StarCoder 2 15B does not yet, so treat this comparison as directional.
Is Llama 4 Maverick or StarCoder 2 15B better for coding?
StarCoder 2 15B scores higher on coding benchmarks: 36.0 versus 26.3 in the Noometry coding category.
How many benchmarks do Llama 4 Maverick and StarCoder 2 15B share?
2 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and StarCoder 2 15B has 7.