Model comparison
Codellama 70b Instruct vs DeepSeek Coder 1.3B
Codellama 70b Instruct has enough public results to be ranked (#237); DeepSeek Coder 1.3B does not yet, so treat this comparison as directional.
Last verified . 3 shared benchmarks.
Meta
DeepSeekSummary
- They share 3 benchmarks with published results for both. Codellama 70b Instruct scores higher in 1 category and DeepSeek Coder 1.3B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where Codellama 70b Instruct leads 37.6 to 31.2.
- The biggest single-benchmark swing is BigCodeBench Complete: 49.6% for Codellama 70b Instruct and 29.6% for DeepSeek Coder 1.3B.
Side by side
| Codellama 70b Instruct | DeepSeek Coder 1.3B | |
|---|---|---|
| Provider | Meta | DeepSeek |
| Noometry Index | 33.7 | 35.0 |
| Released | — | 2023-11-02 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 9 |
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), DeepSeek Coder 1.3B: 31.2 (#287)
| Benchmark | Codellama 70b Instruct | DeepSeek Coder 1.3B |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 22.8% |
| BigCodeBench Complete | 49.6% | 29.6% |
| HumanEval+ | 65.9% | 60.4% |
| MBPP+ | — | 54.8% |
Reasoning Not comparable
Codellama 70b Instruct: 20.1 (#242), DeepSeek Coder 1.3B: —
| Benchmark | Codellama 70b Instruct | DeepSeek Coder 1.3B |
|---|---|---|
| LMArena Hard Prompts | 1052 | — |
| Epoch Capabilities Index | — | 63.6 |
| WinoGrande | — | 53.3% |
Math Not comparable
Codellama 70b Instruct: —, DeepSeek Coder 1.3B: —
| Benchmark | Codellama 70b Instruct | DeepSeek Coder 1.3B |
|---|---|---|
| GSM8K | — | 4.4% |
Knowledge Not comparable
Codellama 70b Instruct: —, DeepSeek Coder 1.3B: —
| Benchmark | Codellama 70b Instruct | DeepSeek Coder 1.3B |
|---|---|---|
| ARC (AI2) Challenge | — | 25.4% |
| MMLU | — | 25.8% |
Multilingual Not comparable
Codellama 70b Instruct: 24.8 (#288), DeepSeek Coder 1.3B: —
| Benchmark | Codellama 70b Instruct | DeepSeek Coder 1.3B |
|---|---|---|
| LMArena Non-English | 992 | — |
Instruction Following Not comparable
Codellama 70b Instruct: 51.9 (#293), DeepSeek Coder 1.3B: —
| Benchmark | Codellama 70b Instruct | DeepSeek Coder 1.3B |
|---|---|---|
| LMArena Instruction Following | 1024 | — |
Writing & Preference Not comparable
Codellama 70b Instruct: 33.4 (#277), DeepSeek Coder 1.3B: —
| Benchmark | Codellama 70b Instruct | DeepSeek Coder 1.3B |
|---|---|---|
| LMArena Text | 1057 | — |
Frequently asked questions
Is Codellama 70b Instruct better than DeepSeek Coder 1.3B?
Codellama 70b Instruct has enough public results to be ranked (#237); DeepSeek Coder 1.3B does not yet, so treat this comparison as directional.
Is Codellama 70b Instruct or DeepSeek Coder 1.3B better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 31.2 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and DeepSeek Coder 1.3B share?
3 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and DeepSeek Coder 1.3B has 9.