Model comparison
Codellama 70b Instruct vs StarCoder 2 3B
Codellama 70b Instruct has enough public results to be ranked (#237); StarCoder 2 3B 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. Codellama 70b Instruct 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 Codellama 70b Instruct leads 37.6 to 33.5.
- The biggest single-benchmark swing is BigCodeBench Complete: 49.6% for Codellama 70b Instruct and 21.4% for StarCoder 2 3B.
Side by side
| Codellama 70b Instruct | StarCoder 2 3B | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 33.7 | 36.3 |
| Released | — | 2024-02-22 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 70b Instruct leads
Codellama 70b Instruct: 37.6 (#193), StarCoder 2 3B: 33.5
| Benchmark | Codellama 70b Instruct | StarCoder 2 3B |
|---|---|---|
| BigCodeBench Complete | 49.6% | 21.4% |
| HumanEval+ | 65.9% | 27.4% |
| BigCodeBench Instruct | 40.7% | — |
Reasoning Not comparable
Codellama 70b Instruct: 20.1 (#242), StarCoder 2 3B: —
| Benchmark | Codellama 70b Instruct | StarCoder 2 3B |
|---|---|---|
| LMArena Hard Prompts | 1052 | — |
| Epoch Capabilities Index | — | 88.76 |
| WinoGrande | — | 57.1% |
Math Not comparable
Codellama 70b Instruct: —, StarCoder 2 3B: —
| Benchmark | Codellama 70b Instruct | StarCoder 2 3B |
|---|---|---|
| GSM8K | — | 21.6% |
Knowledge Not comparable
Codellama 70b Instruct: —, StarCoder 2 3B: —
| Benchmark | Codellama 70b Instruct | StarCoder 2 3B |
|---|---|---|
| ARC (AI2) Challenge | — | 34.2% |
| MMLU | — | 36.6% |
Multilingual Not comparable
Codellama 70b Instruct: 24.8 (#288), StarCoder 2 3B: —
| Benchmark | Codellama 70b Instruct | StarCoder 2 3B |
|---|---|---|
| LMArena Non-English | 992 | — |
Instruction Following Not comparable
Codellama 70b Instruct: 51.9 (#293), StarCoder 2 3B: —
| Benchmark | Codellama 70b Instruct | StarCoder 2 3B |
|---|---|---|
| LMArena Instruction Following | 1024 | — |
Writing & Preference Not comparable
Codellama 70b Instruct: 33.4 (#277), StarCoder 2 3B: —
| Benchmark | Codellama 70b Instruct | StarCoder 2 3B |
|---|---|---|
| LMArena Text | 1057 | — |
Frequently asked questions
Is Codellama 70b Instruct better than StarCoder 2 3B?
Codellama 70b Instruct has enough public results to be ranked (#237); StarCoder 2 3B does not yet, so treat this comparison as directional.
Is Codellama 70b Instruct or StarCoder 2 3B better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 33.5 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and StarCoder 2 3B share?
2 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and StarCoder 2 3B has 7.