Model comparison
Llama 3.2 3B vs StarCoder 2 3B
Llama 3.2 3B has enough public results to be ranked (#318); StarCoder 2 3B does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
Meta
NVIDIASummary
- They share 1 benchmark with published results for both. Llama 3.2 3B scores higher in 0 categories and StarCoder 2 3B in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where StarCoder 2 3B leads 32.9 to 27.1.
- The biggest single-benchmark swing is BigCodeBench Complete: 28.3% for Llama 3.2 3B and 21.4% for StarCoder 2 3B.
Side by side
| Llama 3.2 3B | StarCoder 2 3B | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 28.4 | 35.8 |
| Released | 2024-09-24 | 2024-02-22 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 118K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 18 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding StarCoder 2 3B leads
Llama 3.2 3B: 27.1 (#314), StarCoder 2 3B: 32.9
| Benchmark | Llama 3.2 3B | StarCoder 2 3B |
|---|---|---|
| BigCodeBench Complete | 28.3% | 21.4% |
| BigCodeBench Instruct | 23.4% | — |
| LMArena Coding | 1098 | — |
| HumanEval+ | — | 27.4% |
Agentic & Tool Use Not comparable
Llama 3.2 3B: 19.9 (#135), StarCoder 2 3B: —
| Benchmark | Llama 3.2 3B | StarCoder 2 3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | — |
| BALROG | 10.1% | — |
Reasoning Not comparable
Llama 3.2 3B: 20.1 (#225), StarCoder 2 3B: —
| Benchmark | Llama 3.2 3B | StarCoder 2 3B |
|---|---|---|
| LMArena Hard Prompts | 1095 | — |
| Epoch Capabilities Index | — | 88.01 |
| WinoGrande | — | 57.1% |
Math Not comparable
Llama 3.2 3B: 29.9 (#213), StarCoder 2 3B: —
| Benchmark | Llama 3.2 3B | StarCoder 2 3B |
|---|---|---|
| LMArena Math | 1126 | — |
| GSM8K | — | 21.6% |
Knowledge Not comparable
Llama 3.2 3B: 29.1 (#232), StarCoder 2 3B: —
| Benchmark | Llama 3.2 3B | StarCoder 2 3B |
|---|---|---|
| LMArena Expert | 1090 | — |
| ARC (AI2) Challenge | — | 34.2% |
| MMLU | — | 36.6% |
Multilingual Not comparable
Llama 3.2 3B: 26.4 (#276), StarCoder 2 3B: —
| Benchmark | Llama 3.2 3B | StarCoder 2 3B |
|---|---|---|
| LMArena Non-English | 1019 | — |
| LMArena Chinese | 1017 | — |
| LMArena German | 1056 | — |
| LMArena Russian | 949 | — |
Instruction Following Not comparable
Llama 3.2 3B: 56.3 (#270), StarCoder 2 3B: —
| Benchmark | Llama 3.2 3B | StarCoder 2 3B |
|---|---|---|
| LMArena Instruction Following | 1089 | — |
Long Context Not comparable
Llama 3.2 3B: 33.4 (#256), StarCoder 2 3B: —
| Benchmark | Llama 3.2 3B | StarCoder 2 3B |
|---|---|---|
| LMArena Longer Query | 1101 | — |
Writing & Preference Not comparable
Llama 3.2 3B: 24.9 (#302), StarCoder 2 3B: —
| Benchmark | Llama 3.2 3B | StarCoder 2 3B |
|---|---|---|
| LMArena Text | 1110 | — |
| LMArena Creative Writing | 1094 | — |
| EQ-Bench Creative Writing | 595 | — |
| LMArena Multi-Turn | 1105 | — |
Frequently asked questions
Is Llama 3.2 3B better than StarCoder 2 3B?
Llama 3.2 3B has enough public results to be ranked (#318); StarCoder 2 3B does not yet, so treat this comparison as directional.
Is Llama 3.2 3B or StarCoder 2 3B better for coding?
StarCoder 2 3B scores higher on coding benchmarks: 32.9 versus 27.1 in the Noometry coding category.
How many benchmarks do Llama 3.2 3B and StarCoder 2 3B share?
1 benchmark has published results for both models. Llama 3.2 3B has 18 scored results on Noometry and StarCoder 2 3B has 7.