# DeepSeek-V2.5 (Sep 2024) vs Nova Premier 1.0

> DeepSeek-V2.5 (Sep 2024) and Nova Premier 1.0 score almost the same on the Noometry Index (37.0 vs 37.7), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/deepseek-v2-5-vs-nova-premier-1-0
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V2.5 (Sep 2024) | Nova Premier 1.0 |
|---|---|---|
| Provider | DeepSeek | Amazon |
| Noometry Index | 37.0 | 37.7 |
| Rank | 197 | 185 |
| Context | — | 1M |
| Input $/M | — | $2.50 |
| Output $/M | — | $12.50 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V2.5 (Sep 2024): 31.3 (#274)
- Nova Premier 1.0: —

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Nova Premier 1.0 |
|---|---|---|
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| LMArena Coding | 1310 | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |

## Reasoning

- DeepSeek-V2.5 (Sep 2024): 24.5 (#145)
- Nova Premier 1.0: 22.3 (#182)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Nova Premier 1.0 |
|---|---|---|
| Kagi LLM Benchmark | — | 44.8% |
| LMArena Hard Prompts | 1289 | — |

## Math

- DeepSeek-V2.5 (Sep 2024): 33.3 (#177)
- Nova Premier 1.0: 31.5 (#194)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Nova Premier 1.0 |
|---|---|---|
| Omni-MATH | — | 35% |
| LMArena Math | 1289 | — |

## Knowledge

- DeepSeek-V2.5 (Sep 2024): 34.2 (#190)
- Nova Premier 1.0: 35.4 (#176)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Nova Premier 1.0 |
|---|---|---|
| MMLU-Pro | — | 72.6% |
| GPQA (HELM) | — | 51.8% |
| LMArena Expert | 1266 | — |

## Multilingual

- DeepSeek-V2.5 (Sep 2024): 42.7 (#188)
- Nova Premier 1.0: —

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Nova Premier 1.0 |
|---|---|---|
| LMArena Non-English | 1273 | — |
| LMArena Chinese | 1317 | — |
| LMArena French | 1288 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Russian | 1289 | — |
| LMArena Spanish | 1248 | — |

## Instruction Following

- DeepSeek-V2.5 (Sep 2024): 67.7 (#189)
- Nova Premier 1.0: 66.9 (#201)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Nova Premier 1.0 |
|---|---|---|
| IFEval | — | 80.3% |
| LMArena Instruction Following | 1280 | — |

## Long Context

- DeepSeek-V2.5 (Sep 2024): 39.5 (#169)
- Nova Premier 1.0: —

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Nova Premier 1.0 |
|---|---|---|
| LMArena Longer Query | 1301 | — |

## Writing & Preference

- DeepSeek-V2.5 (Sep 2024): 50.0 (#182)
- Nova Premier 1.0: 51.0 (#174)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Nova Premier 1.0 |
|---|---|---|
| LMArena Text | 1294 | — |
| LMArena Creative Writing | 1285 | — |
| WildBench | — | 78.8% |
| LMArena Multi-Turn | 1297 | — |

## FAQ

### Is DeepSeek-V2.5 (Sep 2024) better than Nova Premier 1.0?

DeepSeek-V2.5 (Sep 2024) and Nova Premier 1.0 score almost the same on the Noometry Index (37.0 vs 37.7), so choose on price, context window or the category you care about most.

### How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Nova Premier 1.0 share?

0 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Nova Premier 1.0 has 6.