Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Llama-3.3-70B-Instruct
Llama-3.3-70B-Instruct has enough public results to be ranked (#291); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 4 shared benchmarks.
DeepSeek
MetaSummary
- They share 4 benchmarks with published results for both. DeepSeek-V2 (MoE-236B, May 2024) scores higher in 1 category and Llama-3.3-70B-Instruct 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 31.0.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Llama-3.3-70B-Instruct | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 40.3 | 30.6 |
| Released | 2024-05-07 | 2024-12-06 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.32 |
| 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-3.3-70B-Instruct: 31.0 (#290)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama-3.3-70B-Instruct |
|---|---|---|
| BigCodeBench Instruct | 48.9% | 46.9% |
| BigCodeBench Complete | 59.4% | 57.5% |
| SciCode | — | 26% |
| WeirdML | — | 14.4% |
| LiveBench Coding | — | 36.6% |
| LMArena Coding | — | 1268 |
Agentic & Tool Use Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama-3.3-70B-Instruct: 25.8 (#105)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama-3.3-70B-Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 31.9% |
| BALROG | — | 23% |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama-3.3-70B-Instruct: 14.1 (#327)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama-3.3-70B-Instruct |
|---|---|---|
| Epoch Capabilities Index | 124.77 | 127.33 |
| SimpleBench | — | 19.9% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 50.8% |
| LMArena Hard Prompts | — | 1257 |
| DTBench | — | 59.5% |
| LiveBench Data Analysis | — | 49.5% |
| LMCA | — | 17.5% |
| BIG-Bench Hard | 78.8% | — |
| ForecastBench | — | 58.6 |
| HellaSwag | 87.1% | — |
| LiveBench | — | 50.2% |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama-3.3-70B-Instruct: 15.3 (#298)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama-3.3-70B-Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 5.1% |
| LiveBench Math | — | 42.2% |
| LMArena Math | — | 1267 |
| MATH Level 5 | — | 41.6% |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama-3.3-70B-Instruct: 30.6 (#226)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama-3.3-70B-Instruct |
|---|---|---|
| MMLU | 78.4% | 86.3% |
| GPQA Diamond | — | 47.4% |
| Confabulations | — | 22.8% |
| Vectara Hallucination Rate | — | 4.1% |
| LMArena Expert | — | 1225 |
| ARC (AI2) Challenge | 92.2% | — |
| TriviaQA | 80% | — |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama-3.3-70B-Instruct: 39.9 (#220)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Non-English | — | 1236 |
| LMArena Chinese | — | 1217 |
| LMArena French | — | 1281 |
| LMArena German | — | 1251 |
| LMArena Japanese | — | 1150 |
| LMArena Korean | — | 1143 |
| LMArena Russian | — | 1252 |
| LMArena Spanish | — | 1270 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama-3.3-70B-Instruct: 71.1 (#157)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama-3.3-70B-Instruct |
|---|---|---|
| LiveBench Instruction Following | — | 82.7% |
| LMArena Instruction Following | — | 1242 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama-3.3-70B-Instruct: 26.4 (#295)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama-3.3-70B-Instruct |
|---|---|---|
| Fiction.LiveBench | — | 33.3% |
| LMArena Longer Query | — | 1256 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama-3.3-70B-Instruct: 47.6 (#207)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Text | — | 1274 |
| LMArena Creative Writing | — | 1250 |
| LMArena Multi-Turn | — | 1280 |
| LiveBench Language | — | 39.2% |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Llama-3.3-70B-Instruct?
Llama-3.3-70B-Instruct has enough public results to be ranked (#291); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or Llama-3.3-70B-Instruct better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 31.0 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Llama-3.3-70B-Instruct share?
4 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Llama-3.3-70B-Instruct has 43.