Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Llama 4 Maverick
Llama 4 Maverick has enough public results to be ranked (#282); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 3 shared benchmarks.
DeepSeek
MetaSummary
- They share 3 benchmarks with published results for both. DeepSeek-V2 (MoE-236B, May 2024) scores higher in 1 category and Llama 4 Maverick 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 26.6.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Llama 4 Maverick | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 40.3 | 30.9 |
| Released | 2024-05-07 | 2025-04-05 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.19 |
| Output $ / M tokens | — | $0.65 |
| Results tracked | 10 | 54 |
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 4 Maverick: 26.6 (#324)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama 4 Maverick |
|---|---|---|
| BigCodeBench Instruct | 48.9% | 49.7% |
| BigCodeBench Complete | 59.4% | 61.4% |
| SWE-bench Verified (bash only) | — | 21% |
| Aider Polyglot | — | 15.6% |
| SciCode | — | 33.1% |
| WeirdML | — | 24.5% |
| LMArena Coding | — | 1302 |
| ALE-Bench | — | 172.97 |
Agentic & Tool Use Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama 4 Maverick: 28.2 (#91)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama 4 Maverick |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.3% |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama 4 Maverick: 10.1 (#342)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama 4 Maverick |
|---|---|---|
| Epoch Capabilities Index | 124.77 | 132.2 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 27.7% |
| Kagi LLM Benchmark | — | 55.9% |
| NYT Connections (extended) | — | 8% |
| ARC-AGI-1 | — | 4.4% |
| CritPt | — | 0% |
| EnigmaEval | — | 0.6% |
| LMArena Hard Prompts | — | 1281 |
| DTBench | — | 61.9% |
| LMCA | — | 15.9% |
| BIG-Bench Hard | 78.8% | — |
| ForecastBench | — | 57.5 |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama 4 Maverick: 26.0 (#262)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama 4 Maverick |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 20.6% |
| Omni-MATH | — | 42.2% |
| LMArena Math | — | 1299 |
| MATH Level 5 | — | 73% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama 4 Maverick: 33.4 (#204)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama 4 Maverick |
|---|---|---|
| GPQA Diamond | — | 67% |
| Humanity's Last Exam | — | 5.7% |
| MMLU-Pro | — | 81% |
| Confabulations | — | 22.6% |
| Vectara Hallucination Rate | — | 8.2% |
| GPQA (HELM) | — | 65% |
| LMArena Expert | — | 1259 |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |
Multimodal Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama 4 Maverick: 31.6 (#105)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | — | 1142 |
| GeoBench | — | 52% |
| SpatialViz-Bench | — | 31.8% |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama 4 Maverick: 42.2 (#195)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | — | 1269 |
| LMArena Chinese | — | 1277 |
| LMArena French | — | 1259 |
| LMArena German | — | 1291 |
| LMArena Japanese | — | 1207 |
| LMArena Korean | — | 1203 |
| LMArena Russian | — | 1286 |
| LMArena Spanish | — | 1293 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama 4 Maverick: 71.7 (#146)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama 4 Maverick |
|---|---|---|
| IFEval | — | 90.8% |
| LMArena Instruction Following | — | 1267 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama 4 Maverick: 31.4 (#279)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama 4 Maverick |
|---|---|---|
| Fiction.LiveBench | — | 46.2% |
| LMArena Longer Query | — | 1280 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Llama 4 Maverick: 38.8 (#252)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Llama 4 Maverick |
|---|---|---|
| LMArena Text | — | 1287 |
| LMArena Creative Writing | — | 1267 |
| Short-Story Creative Writing | — | 62% |
| EQ-Bench Creative Writing | — | 860 |
| WildBench | — | 80% |
| LMArena Multi-Turn | — | 1289 |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Llama 4 Maverick?
Llama 4 Maverick has enough public results to be ranked (#282); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or Llama 4 Maverick better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 26.6 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Llama 4 Maverick share?
3 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Llama 4 Maverick has 54.