Model comparison
DeepSeek V4 Pro vs Llama 13b
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 24.4 on the Noometry Index.
Last verified . 9 shared benchmarks.
DeepSeek
MetaSummary
- They share 9 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 6 categories and Llama 13b in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek V4 Pro leads 65.5 to 13.8.
Side by side
| DeepSeek V4 Pro | Llama 13b | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 54.3 | 24.4 |
| Released | 2026-04-24 | 2023-02-24 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.66 | — |
| Output $ / M tokens | $1.98 | — |
| Results tracked | 48 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Pro leads
DeepSeek V4 Pro: 52.4 (#34), Llama 13b: 21.4 (#337)
| Benchmark | DeepSeek V4 Pro | Llama 13b |
|---|---|---|
| LMArena Coding | 1470 | 683 |
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 51% | — |
| WeirdML | 66.2% | — |
| ALE-Bench | 1,403 | — |
Agentic & Tool Use Not comparable
DeepSeek V4 Pro: 32.8 (#58), Llama 13b: —
| Benchmark | DeepSeek V4 Pro | Llama 13b |
|---|---|---|
| APEX-Agents | 47.3% | — |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.5 (#24), Llama 13b: 14.0 (#329)
| Benchmark | DeepSeek V4 Pro | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1461 | 728 |
| Epoch Capabilities Index | 155.31 | 100.58 |
| ARC-AGI-2 | 61.3% | — |
| Kagi LLM Benchmark | 53.5% | — |
| NYT Connections (extended) | 91.3% | — |
| ARC-AGI-1 | 90.5% | — |
| CritPt | 18% | — |
| Chess Puzzles | 47% | — |
| Mystery Game Puzzles | 43% | — |
| DTBench | 93.9% | — |
| LMCA | 45.5% | — |
| Surface Evolver Bench | 40% | — |
| BIG-Bench Hard | — | 37.9% |
| ForecastBench | 56.1 | — |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |
Math DeepSeek V4 Pro leads
DeepSeek V4 Pro: 64.8 (#30), Llama 13b: 26.7 (#256)
| Benchmark | DeepSeek V4 Pro | Llama 13b |
|---|---|---|
| LMArena Math | 1455 | 838 |
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| OTIS Mock AIME 2024-2025 | 98.6% | — |
| ProofBench | 50% | — |
| GSM8K | — | 20.6% |
Knowledge Not comparable
DeepSeek V4 Pro: 59.5 (#31), Llama 13b: —
| Benchmark | DeepSeek V4 Pro | Llama 13b |
|---|---|---|
| GPQA Diamond | 91.7% | — |
| SimpleQA Verified | 52.9% | — |
| Vectara Hallucination Rate | 8.6% | — |
| LMArena Expert | 1464 | — |
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| MMLU | — | 47.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |
Multimodal Not comparable
DeepSeek V4 Pro: —, Llama 13b: —
| Benchmark | DeepSeek V4 Pro | Llama 13b |
|---|---|---|
| ScienceQA | — | 43.3% |
Multilingual DeepSeek V4 Pro leads
DeepSeek V4 Pro: 54.4 (#45), Llama 13b: 16.6 (#297)
| Benchmark | DeepSeek V4 Pro | Llama 13b |
|---|---|---|
| LMArena Non-English | 1439 | 819 |
| LMArena Chinese | 1486 | — |
| LMArena French | 1472 | — |
| LMArena German | 1458 | — |
| LMArena Japanese | 1445 | — |
| LMArena Korean | 1447 | — |
| LMArena Russian | 1453 | — |
| LMArena Spanish | 1458 | — |
Instruction Following DeepSeek V4 Pro leads
DeepSeek V4 Pro: 76.1 (#47), Llama 13b: 36.7 (#305)
| Benchmark | DeepSeek V4 Pro | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1448 | 781 |
Long Context Not comparable
DeepSeek V4 Pro: 45.0 (#51), Llama 13b: —
| Benchmark | DeepSeek V4 Pro | Llama 13b |
|---|---|---|
| CL-bench Life | 13.5% | — |
| LMArena Longer Query | 1458 | — |
Writing & Preference DeepSeek V4 Pro leads
DeepSeek V4 Pro: 65.5 (#46), Llama 13b: 13.8 (#312)
| Benchmark | DeepSeek V4 Pro | Llama 13b |
|---|---|---|
| LMArena Text | 1451 | 834 |
| LMArena Creative Writing | 1446 | 794 |
| LMArena Multi-Turn | 1467 | 753 |
| EQ-Bench Creative Writing | 1553 | — |
| EQ-Bench 4 | 1166 | — |
Frequently asked questions
Is DeepSeek V4 Pro better than Llama 13b?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 24.4 on the Noometry Index.
Is DeepSeek V4 Pro or Llama 13b better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 21.4 in the Noometry coding category.
How many benchmarks do DeepSeek V4 Pro and Llama 13b share?
9 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Llama 13b has 21.