Model comparison
DeepSeek V4 Pro vs Llama 3.1 Nemotron 70b Instruct
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 37.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeek
NVIDIASummary
- They share 12 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 8 categories and Llama 3.1 Nemotron 70b Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.5 to 25.0.
Side by side
| DeepSeek V4 Pro | Llama 3.1 Nemotron 70b Instruct | |
|---|---|---|
| Provider | DeepSeek | NVIDIA |
| Noometry Index | 54.3 | 37.6 |
| Released | 2026-04-24 | 2024-12-18 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.66 | — |
| Output $ / M tokens | $1.98 | — |
| Results tracked | 48 | 14 |
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 3.1 Nemotron 70b Instruct: 35.9 (#216)
| Benchmark | DeepSeek V4 Pro | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Coding | 1470 | 1272 |
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 51% | — |
| WeirdML | 66.2% | — |
| BigCodeBench Instruct | — | 38.7% |
| BigCodeBench Complete | — | 48.2% |
| ALE-Bench | 1,403 | — |
Agentic & Tool Use Not comparable
DeepSeek V4 Pro: 32.8 (#58), Llama 3.1 Nemotron 70b Instruct: —
| Benchmark | DeepSeek V4 Pro | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| APEX-Agents | 47.3% | — |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.5 (#24), Llama 3.1 Nemotron 70b Instruct: 25.0 (#152)
| Benchmark | DeepSeek V4 Pro | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1461 | 1266 |
| 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% | — |
| Epoch Capabilities Index | 155.31 | — |
| ForecastBench | 56.1 | — |
Math DeepSeek V4 Pro leads
DeepSeek V4 Pro: 64.8 (#30), Llama 3.1 Nemotron 70b Instruct: 35.5 (#182)
| Benchmark | DeepSeek V4 Pro | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Math | 1455 | 1271 |
| 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% | — |
Knowledge DeepSeek V4 Pro leads
DeepSeek V4 Pro: 59.5 (#31), Llama 3.1 Nemotron 70b Instruct: 34.1 (#199)
| Benchmark | DeepSeek V4 Pro | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Expert | 1464 | 1242 |
| GPQA Diamond | 91.7% | — |
| SimpleQA Verified | 52.9% | — |
| Vectara Hallucination Rate | 8.6% | — |
Multilingual DeepSeek V4 Pro leads
DeepSeek V4 Pro: 54.4 (#45), Llama 3.1 Nemotron 70b Instruct: 40.5 (#217)
| Benchmark | DeepSeek V4 Pro | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Non-English | 1439 | 1245 |
| LMArena Chinese | 1486 | 1263 |
| LMArena Russian | 1453 | 1227 |
| LMArena French | 1472 | — |
| LMArena German | 1458 | — |
| LMArena Japanese | 1445 | — |
| LMArena Korean | 1447 | — |
| LMArena Spanish | 1458 | — |
Instruction Following DeepSeek V4 Pro leads
DeepSeek V4 Pro: 76.1 (#47), Llama 3.1 Nemotron 70b Instruct: 65.9 (#213)
| Benchmark | DeepSeek V4 Pro | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Instruction Following | 1448 | 1252 |
Long Context DeepSeek V4 Pro leads
DeepSeek V4 Pro: 45.0 (#51), Llama 3.1 Nemotron 70b Instruct: 37.6 (#215)
| Benchmark | DeepSeek V4 Pro | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Longer Query | 1458 | 1238 |
| CL-bench Life | 13.5% | — |
Writing & Preference DeepSeek V4 Pro leads
DeepSeek V4 Pro: 65.5 (#46), Llama 3.1 Nemotron 70b Instruct: 48.4 (#203)
| Benchmark | DeepSeek V4 Pro | Llama 3.1 Nemotron 70b Instruct |
|---|---|---|
| LMArena Text | 1451 | 1283 |
| LMArena Creative Writing | 1446 | 1269 |
| LMArena Multi-Turn | 1467 | 1275 |
| EQ-Bench Creative Writing | 1553 | — |
| EQ-Bench 4 | 1166 | — |
Frequently asked questions
Is DeepSeek V4 Pro better than Llama 3.1 Nemotron 70b Instruct?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 37.6 on the Noometry Index.
Is DeepSeek V4 Pro or Llama 3.1 Nemotron 70b Instruct better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 35.9 in the Noometry coding category.
How many benchmarks do DeepSeek V4 Pro and Llama 3.1 Nemotron 70b Instruct share?
12 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Llama 3.1 Nemotron 70b Instruct has 14.