Model comparison
Codellama 34b Instruct vs DeepSeek Coder 1.3B
Codellama 34b Instruct has enough public results to be ranked (#285); DeepSeek Coder 1.3B does not yet, so treat this comparison as directional.
Last verified . 4 shared benchmarks.
Meta
DeepSeekSummary
- They share 4 benchmarks with published results for both. Codellama 34b Instruct scores higher in 0 categories and DeepSeek Coder 1.3B in 1 category; one gap is clear of the uncertainty.
- The biggest single-benchmark swing is BigCodeBench Complete: 37.1% for Codellama 34b Instruct and 29.6% for DeepSeek Coder 1.3B.
Side by side
| Codellama 34b Instruct | DeepSeek Coder 1.3B | |
|---|---|---|
| Provider | Meta | DeepSeek |
| Noometry Index | 30.2 | 34.5 |
| Released | — | 2023-11-02 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek Coder 1.3B leads
Codellama 34b Instruct: 28.0 (#310), DeepSeek Coder 1.3B: 30.7 (#282)
| Benchmark | Codellama 34b Instruct | DeepSeek Coder 1.3B |
|---|---|---|
| BigCodeBench Instruct | 29% | 22.8% |
| BigCodeBench Complete | 37.1% | 29.6% |
| HumanEval+ | 43.9% | 60.4% |
| MBPP+ | 56.3% | 54.8% |
| LMArena Coding | 1046 | — |
Reasoning Not comparable
Codellama 34b Instruct: 18.8 (#250), DeepSeek Coder 1.3B: —
| Benchmark | Codellama 34b Instruct | DeepSeek Coder 1.3B |
|---|---|---|
| LMArena Hard Prompts | 1032 | — |
| Epoch Capabilities Index | — | 62.18 |
| WinoGrande | — | 53.3% |
Math Not comparable
Codellama 34b Instruct: 28.5 (#227), DeepSeek Coder 1.3B: —
| Benchmark | Codellama 34b Instruct | DeepSeek Coder 1.3B |
|---|---|---|
| LMArena Math | 1056 | — |
| GSM8K | — | 4.4% |
Knowledge Not comparable
Codellama 34b Instruct: —, DeepSeek Coder 1.3B: —
| Benchmark | Codellama 34b Instruct | DeepSeek Coder 1.3B |
|---|---|---|
| ARC (AI2) Challenge | — | 25.4% |
| MMLU | — | 25.8% |
Multilingual Not comparable
Codellama 34b Instruct: 25.9 (#279), DeepSeek Coder 1.3B: —
| Benchmark | Codellama 34b Instruct | DeepSeek Coder 1.3B |
|---|---|---|
| LMArena Non-English | 1011 | — |
| LMArena Chinese | 976 | — |
Instruction Following Not comparable
Codellama 34b Instruct: 52.4 (#286), DeepSeek Coder 1.3B: —
| Benchmark | Codellama 34b Instruct | DeepSeek Coder 1.3B |
|---|---|---|
| LMArena Instruction Following | 1028 | — |
Long Context Not comparable
Codellama 34b Instruct: 30.8 (#279), DeepSeek Coder 1.3B: —
| Benchmark | Codellama 34b Instruct | DeepSeek Coder 1.3B |
|---|---|---|
| LMArena Longer Query | 1014 | — |
Writing & Preference Not comparable
Codellama 34b Instruct: 28.4 (#292), DeepSeek Coder 1.3B: —
| Benchmark | Codellama 34b Instruct | DeepSeek Coder 1.3B |
|---|---|---|
| LMArena Text | 1066 | — |
| LMArena Creative Writing | 1032 | — |
| LMArena Multi-Turn | 1015 | — |
Frequently asked questions
Is Codellama 34b Instruct better than DeepSeek Coder 1.3B?
Codellama 34b Instruct has enough public results to be ranked (#285); DeepSeek Coder 1.3B does not yet, so treat this comparison as directional.
Is Codellama 34b Instruct or DeepSeek Coder 1.3B better for coding?
DeepSeek Coder 1.3B scores higher on coding benchmarks: 30.7 versus 28.0 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and DeepSeek Coder 1.3B share?
4 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and DeepSeek Coder 1.3B has 9.