Model comparison
Codellama 34b Instruct vs StarCoder 2 7B
Codellama 34b Instruct has enough public results to be ranked (#285); StarCoder 2 7B 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 34b Instruct scores higher in 0 categories and StarCoder 2 7B in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where StarCoder 2 7B leads 34.2 to 28.0.
- The biggest single-benchmark swing is BigCodeBench Complete: 37.1% for Codellama 34b Instruct and 27.7% for StarCoder 2 7B.
Side by side
| Codellama 34b Instruct | StarCoder 2 7B | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 30.2 | 36.5 |
| Released | — | 2024-02-20 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding StarCoder 2 7B leads
Codellama 34b Instruct: 28.0 (#310), StarCoder 2 7B: 34.2
| Benchmark | Codellama 34b Instruct | StarCoder 2 7B |
|---|---|---|
| BigCodeBench Complete | 37.1% | 27.7% |
| HumanEval+ | 43.9% | 29.9% |
| BigCodeBench Instruct | 29% | — |
| LMArena Coding | 1046 | — |
| MBPP+ | 56.3% | — |
Reasoning Not comparable
Codellama 34b Instruct: 18.8 (#250), StarCoder 2 7B: —
| Benchmark | Codellama 34b Instruct | StarCoder 2 7B |
|---|---|---|
| LMArena Hard Prompts | 1032 | — |
| Epoch Capabilities Index | — | 92.92 |
| WinoGrande | — | 57.1% |
Math Not comparable
Codellama 34b Instruct: 28.5 (#227), StarCoder 2 7B: —
| Benchmark | Codellama 34b Instruct | StarCoder 2 7B |
|---|---|---|
| LMArena Math | 1056 | — |
| GSM8K | — | 32.7% |
Knowledge Not comparable
Codellama 34b Instruct: —, StarCoder 2 7B: —
| Benchmark | Codellama 34b Instruct | StarCoder 2 7B |
|---|---|---|
| ARC (AI2) Challenge | — | 38.7% |
| MMLU | — | 38.8% |
Multilingual Not comparable
Codellama 34b Instruct: 25.9 (#279), StarCoder 2 7B: —
| Benchmark | Codellama 34b Instruct | StarCoder 2 7B |
|---|---|---|
| LMArena Non-English | 1011 | — |
| LMArena Chinese | 976 | — |
Instruction Following Not comparable
Codellama 34b Instruct: 52.4 (#286), StarCoder 2 7B: —
| Benchmark | Codellama 34b Instruct | StarCoder 2 7B |
|---|---|---|
| LMArena Instruction Following | 1028 | — |
Long Context Not comparable
Codellama 34b Instruct: 30.8 (#279), StarCoder 2 7B: —
| Benchmark | Codellama 34b Instruct | StarCoder 2 7B |
|---|---|---|
| LMArena Longer Query | 1014 | — |
Writing & Preference Not comparable
Codellama 34b Instruct: 28.4 (#292), StarCoder 2 7B: —
| Benchmark | Codellama 34b Instruct | StarCoder 2 7B |
|---|---|---|
| LMArena Text | 1066 | — |
| LMArena Creative Writing | 1032 | — |
| LMArena Multi-Turn | 1015 | — |
Frequently asked questions
Is Codellama 34b Instruct better than StarCoder 2 7B?
Codellama 34b Instruct has enough public results to be ranked (#285); StarCoder 2 7B does not yet, so treat this comparison as directional.
Is Codellama 34b Instruct or StarCoder 2 7B better for coding?
StarCoder 2 7B scores higher on coding benchmarks: 34.2 versus 28.0 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and StarCoder 2 7B share?
2 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and StarCoder 2 7B has 7.