Model comparison
Codellama 70b Instruct vs DeepSeek-V2 (MoE-236B, May 2024)
Codellama 70b Instruct has enough public results to be ranked (#237); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 2 shared benchmarks.
Meta
DeepSeekSummary
- They share 2 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and DeepSeek-V2 (MoE-236B, May 2024) in 1 category; one gap is clear of the uncertainty.
- The biggest single-benchmark swing is BigCodeBench Complete: 49.6% for Codellama 70b Instruct and 59.4% for DeepSeek-V2 (MoE-236B, May 2024).
Side by side
| Codellama 70b Instruct | DeepSeek-V2 (MoE-236B, May 2024) | |
|---|---|---|
| Provider | Meta | DeepSeek |
| Noometry Index | 33.7 | 40.3 |
| Released | — | 2024-05-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2 (MoE-236B, May 2024) leads
Codellama 70b Instruct: 37.6 (#193), DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139)
| Benchmark | Codellama 70b Instruct | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 48.9% |
| BigCodeBench Complete | 49.6% | 59.4% |
| HumanEval+ | 65.9% | — |
Reasoning Not comparable
Codellama 70b Instruct: 20.1 (#242), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Codellama 70b Instruct | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Hard Prompts | 1052 | — |
| BIG-Bench Hard | — | 78.8% |
| Epoch Capabilities Index | — | 124.77 |
| HellaSwag | — | 87.1% |
| PIQA | — | 83.9% |
| WinoGrande | — | 86.3% |
Knowledge Not comparable
Codellama 70b Instruct: —, DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Codellama 70b Instruct | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| ARC (AI2) Challenge | — | 92.2% |
| MMLU | — | 78.4% |
| TriviaQA | — | 80% |
Multilingual Not comparable
Codellama 70b Instruct: 24.8 (#288), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Codellama 70b Instruct | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Non-English | 992 | — |
Instruction Following Not comparable
Codellama 70b Instruct: 51.9 (#293), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Codellama 70b Instruct | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Instruction Following | 1024 | — |
Writing & Preference Not comparable
Codellama 70b Instruct: 33.4 (#277), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Codellama 70b Instruct | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Text | 1057 | — |
Frequently asked questions
Is Codellama 70b Instruct better than DeepSeek-V2 (MoE-236B, May 2024)?
Codellama 70b Instruct has enough public results to be ranked (#237); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is Codellama 70b Instruct or DeepSeek-V2 (MoE-236B, May 2024) better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 37.6 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and DeepSeek-V2 (MoE-236B, May 2024) share?
2 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and DeepSeek-V2 (MoE-236B, May 2024) has 10.