# Deepseek Coder v2 vs Nemotron 3.5 Lightning

> Nemotron 3.5 Lightning is the stronger model overall, scoring 40.0 to 35.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-coder-v2-vs-nemotron-3-5-lightning
- Last updated: 2026-10-11
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and Nemotron 3.5 Lightning in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nemotron 3.5 Lightning leads 48.5 to 38.2.

## Snapshot

| | Deepseek Coder v2 | Nemotron 3.5 Lightning |
|---|---|---|
| Provider | DeepSeek | NVIDIA |
| Noometry Index | 35.9 | 40.0 |
| Rank | 220 | 155 |
| Context | — | 262K |
| Input $/M | — | $0.05 |
| Output $/M | — | $0.20 |
| Weights | Open | Open |

## Coding

- Deepseek Coder v2: 38.1 (#183)
- Nemotron 3.5 Lightning: 40.4 (#141)

| Benchmark | Deepseek Coder v2 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Coding | 1251 | 1375 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |

## Reasoning

- Deepseek Coder v2: 23.6 (#176)
- Nemotron 3.5 Lightning: 26.8 (#127)

| Benchmark | Deepseek Coder v2 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1337 |
| WinoGrande | 83.7% | — |

## Math

- Deepseek Coder v2: 34.9 (#190)
- Nemotron 3.5 Lightning: 37.5 (#155)

| Benchmark | Deepseek Coder v2 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Math | 1241 | 1359 |
| GSM8K | 94.5% | — |

## Knowledge

- Deepseek Coder v2: 32.3 (#212)
- Nemotron 3.5 Lightning: 37.5 (#154)

| Benchmark | Deepseek Coder v2 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Expert | 1181 | 1356 |
| ARC (AI2) Challenge | 64.3% | — |

## Multilingual

- Deepseek Coder v2: 36.3 (#240)
- Nemotron 3.5 Lightning: 44.0 (#180)

| Benchmark | Deepseek Coder v2 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Non-English | 1182 | 1295 |
| LMArena Chinese | 1201 | 1359 |
| LMArena French | 1185 | 1366 |
| LMArena German | 1164 | 1282 |
| LMArena Japanese | 1126 | 1206 |
| LMArena Korean | 1104 | 1238 |
| LMArena Russian | 1188 | 1253 |
| LMArena Spanish | 1153 | 1345 |

## Instruction Following

- Deepseek Coder v2: 61.7 (#242)
- Nemotron 3.5 Lightning: 69.6 (#170)

| Benchmark | Deepseek Coder v2 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Instruction Following | 1180 | 1318 |

## Long Context

- Deepseek Coder v2: 37.0 (#224)
- Nemotron 3.5 Lightning: 39.9 (#165)

| Benchmark | Deepseek Coder v2 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Longer Query | 1219 | 1314 |

## Writing & Preference

- Deepseek Coder v2: 38.2 (#253)
- Nemotron 3.5 Lightning: 48.5 (#201)

| Benchmark | Deepseek Coder v2 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Text | 1191 | 1327 |
| LMArena Creative Writing | 1120 | 1254 |
| LMArena Multi-Turn | 1177 | 1328 |
| EQ-Bench Creative Writing | — | 1280 |

## FAQ

### Is Deepseek Coder v2 better than Nemotron 3.5 Lightning?

Nemotron 3.5 Lightning is the stronger model overall, scoring 40.0 to 35.9 on the Noometry Index.

### Is Deepseek Coder v2 or Nemotron 3.5 Lightning better for coding?

Nemotron 3.5 Lightning scores higher on coding benchmarks: 40.4 versus 38.1 in the Noometry coding category.

### How many benchmarks do Deepseek Coder v2 and Nemotron 3.5 Lightning share?

17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Nemotron 3.5 Lightning has 18.