Model comparison
Codellama 34b Instruct vs DeepSeek Coder 33B
Codellama 34b Instruct has enough public results to be ranked (#287); DeepSeek Coder 33B 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 33B in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek Coder 33B leads 38.0 to 28.5.
- The biggest single-benchmark swing is BigCodeBench Complete: 37.1% for Codellama 34b Instruct and 51.1% for DeepSeek Coder 33B.
Side by side
| Codellama 34b Instruct | DeepSeek Coder 33B | |
|---|---|---|
| Provider | Meta | DeepSeek |
| Noometry Index | 30.8 | 38.9 |
| 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 33B leads
Codellama 34b Instruct: 28.5 (#314), DeepSeek Coder 33B: 38.0 (#184)
| Benchmark | Codellama 34b Instruct | DeepSeek Coder 33B |
|---|---|---|
| BigCodeBench Instruct | 29% | 42% |
| BigCodeBench Complete | 37.1% | 51.1% |
| HumanEval+ | 43.9% | 75% |
| MBPP+ | 56.3% | 70.1% |
| LMArena Coding | 1046 | — |
Reasoning Not comparable
Codellama 34b Instruct: 19.6 (#255), DeepSeek Coder 33B: —
| Benchmark | Codellama 34b Instruct | DeepSeek Coder 33B |
|---|---|---|
| LMArena Hard Prompts | 1032 | — |
| Epoch Capabilities Index | — | 96.32 |
| WinoGrande | — | 62% |
Math Not comparable
Codellama 34b Instruct: 31.0 (#230), DeepSeek Coder 33B: —
| Benchmark | Codellama 34b Instruct | DeepSeek Coder 33B |
|---|---|---|
| LMArena Math | 1056 | — |
| GSM8K | — | 35.4% |
Knowledge Not comparable
Codellama 34b Instruct: —, DeepSeek Coder 33B: —
| Benchmark | Codellama 34b Instruct | DeepSeek Coder 33B |
|---|---|---|
| ARC (AI2) Challenge | — | 42.2% |
| MMLU | — | 39.4% |
Multilingual Not comparable
Codellama 34b Instruct: 25.8 (#284), DeepSeek Coder 33B: —
| Benchmark | Codellama 34b Instruct | DeepSeek Coder 33B |
|---|---|---|
| LMArena Non-English | 1011 | — |
| LMArena Chinese | 976 | — |
Instruction Following Not comparable
Codellama 34b Instruct: 52.2 (#291), DeepSeek Coder 33B: —
| Benchmark | Codellama 34b Instruct | DeepSeek Coder 33B |
|---|---|---|
| LMArena Instruction Following | 1028 | — |
Long Context Not comparable
Codellama 34b Instruct: 30.9 (#284), DeepSeek Coder 33B: —
| Benchmark | Codellama 34b Instruct | DeepSeek Coder 33B |
|---|---|---|
| LMArena Longer Query | 1013 | — |
Writing & Preference Not comparable
Codellama 34b Instruct: 28.2 (#297), DeepSeek Coder 33B: —
| Benchmark | Codellama 34b Instruct | DeepSeek Coder 33B |
|---|---|---|
| LMArena Text | 1066 | — |
| LMArena Creative Writing | 1032 | — |
| LMArena Multi-Turn | 1015 | — |
Frequently asked questions
Is Codellama 34b Instruct better than DeepSeek Coder 33B?
Codellama 34b Instruct has enough public results to be ranked (#287); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Is Codellama 34b Instruct or DeepSeek Coder 33B better for coding?
DeepSeek Coder 33B scores higher on coding benchmarks: 38.0 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and DeepSeek Coder 33B share?
4 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and DeepSeek Coder 33B has 9.