Model comparison
Codellama 34b Instruct vs DeepSeek-V2 (MoE-236B, May 2024)
Codellama 34b Instruct has enough public results to be ranked (#287); 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 34b Instruct scores higher in 0 categories and DeepSeek-V2 (MoE-236B, May 2024) in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 40.4 to 28.5.
- The biggest single-benchmark swing is BigCodeBench Complete: 37.1% for Codellama 34b Instruct and 59.4% for DeepSeek-V2 (MoE-236B, May 2024).
Side by side
| Codellama 34b Instruct | DeepSeek-V2 (MoE-236B, May 2024) | |
|---|---|---|
| Provider | Meta | DeepSeek |
| Noometry Index | 30.8 | 40.3 |
| Released | — | 2024-05-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 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 34b Instruct: 28.5 (#314), DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139)
| Benchmark | Codellama 34b Instruct | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| BigCodeBench Instruct | 29% | 48.9% |
| BigCodeBench Complete | 37.1% | 59.4% |
| LMArena Coding | 1046 | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning Not comparable
Codellama 34b Instruct: 19.6 (#255), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Codellama 34b Instruct | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Hard Prompts | 1032 | — |
| BIG-Bench Hard | — | 78.8% |
| Epoch Capabilities Index | — | 124.77 |
| HellaSwag | — | 87.1% |
| PIQA | — | 83.9% |
| WinoGrande | — | 86.3% |
Math Not comparable
Codellama 34b Instruct: 31.0 (#230), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Codellama 34b Instruct | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Math | 1056 | — |
Knowledge Not comparable
Codellama 34b Instruct: —, DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Codellama 34b Instruct | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| ARC (AI2) Challenge | — | 92.2% |
| MMLU | — | 78.4% |
| TriviaQA | — | 80% |
Multilingual Not comparable
Codellama 34b Instruct: 25.8 (#284), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Codellama 34b Instruct | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Non-English | 1011 | — |
| LMArena Chinese | 976 | — |
Instruction Following Not comparable
Codellama 34b Instruct: 52.2 (#291), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Codellama 34b Instruct | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Instruction Following | 1028 | — |
Long Context Not comparable
Codellama 34b Instruct: 30.9 (#284), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Codellama 34b Instruct | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Longer Query | 1013 | — |
Writing & Preference Not comparable
Codellama 34b Instruct: 28.2 (#297), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Codellama 34b Instruct | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Text | 1066 | — |
| LMArena Creative Writing | 1032 | — |
| LMArena Multi-Turn | 1015 | — |
Frequently asked questions
Is Codellama 34b Instruct better than DeepSeek-V2 (MoE-236B, May 2024)?
Codellama 34b Instruct has enough public results to be ranked (#287); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is Codellama 34b 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 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and DeepSeek-V2 (MoE-236B, May 2024) share?
2 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and DeepSeek-V2 (MoE-236B, May 2024) has 10.