Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Llama 3.1-8B
Llama 3.1-8B has enough public results to be ranked (#352); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 5 shared benchmarks.
DeepSeek
MetaSummary
- They share 5 benchmarks with published results for both. DeepSeek-V2 (MoE-236B, May 2024) scores higher in 1 category and Llama 3.1-8B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 40.4 to 20.2.
- The biggest single-benchmark swing is BigCodeBench Complete: 59.4% for DeepSeek-V2 (MoE-236B, May 2024) and 40.5% for Llama 3.1-8B.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Llama 3.1-8B | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 40.3 | 23.0 |
| Released | 2024-05-07 | 2024-07-23 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.08 |
| Results tracked | 10 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2 (MoE-236B, May 2024) leads
DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139), Llama 3.1-8B: 20.2 (#340)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama 3.1-8B |
|---|---|---|
| BigCodeBench Instruct | 48.9% | 32.8% |
| BigCodeBench Complete | 59.4% | 40.5% |
| SciCode | — | 13.2% |
| WeirdML | — | 1.7% |
| LMArena Coding | — | 1195 |
| HumanEval+ | — | 62.8% |
| MBPP+ | — | 55.6% |
Agentic & Tool Use Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama 3.1-8B: 22.5 (#131)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama 3.1-8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 25.8% |
| BALROG | — | 15.1% |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama 3.1-8B: 14.9 (#321)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama 3.1-8B |
|---|---|---|
| Epoch Capabilities Index | 124.77 | 116.57 |
| PIQA | 83.9% | 81.2% |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1175 |
| DTBench | — | 50.9% |
| LMCA | — | 5.4% |
| BIG-Bench Hard | 78.8% | — |
| HellaSwag | 87.1% | — |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama 3.1-8B: 10.2 (#317)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama 3.1-8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 1.7% |
| Omni-MATH | — | 13.7% |
| LMArena Math | — | 1179 |
| MATH Level 5 | — | 22.9% |
| GSM8K | — | 82.4% |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama 3.1-8B: 8.0 (#307)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama 3.1-8B |
|---|---|---|
| MMLU | 78.4% | 56.1% |
| GPQA Diamond | — | 27% |
| MMLU-Pro | — | 40.6% |
| GPQA (HELM) | — | 24.7% |
| LMArena Expert | — | 1144 |
| ARC (AI2) Challenge | 92.2% | — |
| BoolQ | — | 82.8% |
| TriviaQA | 80% | — |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama 3.1-8B: 34.0 (#249)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama 3.1-8B |
|---|---|---|
| LMArena Non-English | — | 1148 |
| LMArena Chinese | — | 1151 |
| LMArena French | — | 1177 |
| LMArena German | — | 1144 |
| LMArena Japanese | — | 1061 |
| LMArena Korean | — | 1053 |
| LMArena Russian | — | 1158 |
| LMArena Spanish | — | 1169 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama 3.1-8B: 58.9 (#258)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama 3.1-8B |
|---|---|---|
| IFEval | — | 74.3% |
| LMArena Instruction Following | — | 1159 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama 3.1-8B: 35.8 (#238)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama 3.1-8B |
|---|---|---|
| LMArena Longer Query | — | 1182 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama 3.1-8B: 29.7 (#290)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama 3.1-8B |
|---|---|---|
| LMArena Text | — | 1187 |
| LMArena Creative Writing | — | 1154 |
| EQ-Bench Creative Writing | — | 713 |
| WildBench | — | 68.7% |
| LMArena Multi-Turn | — | 1172 |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Llama 3.1-8B?
Llama 3.1-8B has enough public results to be ranked (#352); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or Llama 3.1-8B better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 20.2 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Llama 3.1-8B share?
5 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Llama 3.1-8B has 43.