# DeepSeek-V2 (MoE-236B, May 2024) vs Nemotron 4 340b Instruct

> Nemotron 4 340b Instruct has enough public results to be ranked (#218); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-v2-vs-nemotron-4-340b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 39.8 to 34.6.

## Snapshot

| | DeepSeek-V2 (MoE-236B, May 2024) | Nemotron 4 340b Instruct |
|---|---|---|
| Provider | DeepSeek | NVIDIA |
| Noometry Index | 39.7 | 35.3 |
| Rank | — | 218 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DeepSeek-V2 (MoE-236B, May 2024): 39.8 (#141)
- Nemotron 4 340b Instruct: 34.6 (#223)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Nemotron 4 340b Instruct |
|---|---|---|
| BigCodeBench Instruct | 48.9% | — |
| LMArena Coding | — | 1209 |
| BigCodeBench Complete | 59.4% | — |

## Reasoning

- DeepSeek-V2 (MoE-236B, May 2024): —
- Nemotron 4 340b Instruct: 22.4 (#180)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Hard Prompts | — | 1202 |
| BIG-Bench Hard | 78.8% | — |
| Epoch Capabilities Index | 124.78 | — |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |

## Math

- DeepSeek-V2 (MoE-236B, May 2024): —
- Nemotron 4 340b Instruct: 31.7 (#193)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Math | — | 1216 |

## Knowledge

- DeepSeek-V2 (MoE-236B, May 2024): —
- Nemotron 4 340b Instruct: 31.4 (#212)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Expert | — | 1171 |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |

## Multilingual

- DeepSeek-V2 (MoE-236B, May 2024): —
- Nemotron 4 340b Instruct: 38.0 (#228)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Non-English | — | 1206 |
| LMArena Chinese | — | 1214 |
| LMArena French | — | 1196 |
| LMArena German | — | 1192 |
| LMArena Japanese | — | 1128 |
| LMArena Korean | — | 1148 |
| LMArena Russian | — | 1219 |
| LMArena Spanish | — | 1195 |

## Instruction Following

- DeepSeek-V2 (MoE-236B, May 2024): —
- Nemotron 4 340b Instruct: 63.3 (#227)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1203 |

## Long Context

- DeepSeek-V2 (MoE-236B, May 2024): —
- Nemotron 4 340b Instruct: 37.1 (#216)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1225 |

## Writing & Preference

- DeepSeek-V2 (MoE-236B, May 2024): —
- Nemotron 4 340b Instruct: 42.9 (#229)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Text | — | 1225 |
| LMArena Creative Writing | — | 1203 |
| LMArena Multi-Turn | — | 1214 |

## FAQ

### Is DeepSeek-V2 (MoE-236B, May 2024) better than Nemotron 4 340b Instruct?

Nemotron 4 340b Instruct has enough public results to be ranked (#218); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.

### Is DeepSeek-V2 (MoE-236B, May 2024) or Nemotron 4 340b Instruct better for coding?

DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 39.8 versus 34.6 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Nemotron 4 340b Instruct share?

0 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Nemotron 4 340b Instruct has 17.