# DeepSeek-V2.5 (Sep 2024) vs Nova 2.0 Pro Preview

> DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 33.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v2-5-vs-nova-2-0-pro-preview
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where Nova 2.0 Pro Preview leads 40.8 to 31.7.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V2.5 (Sep 2024) | Nova 2.0 Pro Preview |
|---|---|---|
| Provider | DeepSeek | Amazon |
| Noometry Index | 37.6 | 33.4 |
| Rank | 200 | 244 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V2.5 (Sep 2024): 31.7 (#281)
- Nova 2.0 Pro Preview: 40.8 (#133)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Nova 2.0 Pro Preview |
|---|---|---|
| Aider Polyglot | 17.8% | — |
| SciCode | — | 42.7% |
| BigCodeBench Instruct | 48.6% | — |
| LMArena Coding | 1309 | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |

## Agentic & Tool Use

- DeepSeek-V2.5 (Sep 2024): —
- Nova 2.0 Pro Preview: 21.9 (#136)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Nova 2.0 Pro Preview |
|---|---|---|
| GDP.pdf | — | 2% |

## Reasoning

- DeepSeek-V2.5 (Sep 2024): 25.6 (#145)
- Nova 2.0 Pro Preview: 22.4 (#194)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Nova 2.0 Pro Preview |
|---|---|---|
| CritPt | — | 0% |
| LMArena Hard Prompts | 1289 | — |

## Math

- DeepSeek-V2.5 (Sep 2024): 35.9 (#177)
- Nova 2.0 Pro Preview: —

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Nova 2.0 Pro Preview |
|---|---|---|
| LMArena Math | 1288 | — |

## Knowledge

- DeepSeek-V2.5 (Sep 2024): 34.8 (#193)
- Nova 2.0 Pro Preview: —

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Nova 2.0 Pro Preview |
|---|---|---|
| LMArena Expert | 1266 | — |

## Multilingual

- DeepSeek-V2.5 (Sep 2024): 42.5 (#193)
- Nova 2.0 Pro Preview: —

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Nova 2.0 Pro Preview |
|---|---|---|
| LMArena Non-English | 1273 | — |
| LMArena Chinese | 1318 | — |
| LMArena French | 1289 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Russian | 1289 | — |
| LMArena Spanish | 1248 | — |

## Instruction Following

- DeepSeek-V2.5 (Sep 2024): 67.5 (#194)
- Nova 2.0 Pro Preview: —

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Nova 2.0 Pro Preview |
|---|---|---|
| LMArena Instruction Following | 1280 | — |

## Long Context

- DeepSeek-V2.5 (Sep 2024): 39.5 (#174)
- Nova 2.0 Pro Preview: —

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Nova 2.0 Pro Preview |
|---|---|---|
| LMArena Longer Query | 1301 | — |

## Writing & Preference

- DeepSeek-V2.5 (Sep 2024): 49.8 (#187)
- Nova 2.0 Pro Preview: —

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Nova 2.0 Pro Preview |
|---|---|---|
| LMArena Text | 1294 | — |
| LMArena Creative Writing | 1285 | — |
| LMArena Multi-Turn | 1297 | — |

## FAQ

### Is DeepSeek-V2.5 (Sep 2024) better than Nova 2.0 Pro Preview?

DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 33.4 on the Noometry Index.

### Is DeepSeek-V2.5 (Sep 2024) or Nova 2.0 Pro Preview better for coding?

Nova 2.0 Pro Preview scores higher on coding benchmarks: 40.8 versus 31.7 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Nova 2.0 Pro Preview share?

0 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Nova 2.0 Pro Preview has 3.