# DeepSeek-V3.1-Terminus vs Nova 2.0 Pro Preview

> DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 32.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-terminus-vs-nova-2-0-pro-preview
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 2 categories and Nova 2.0 Pro Preview in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-V3.1-Terminus leads 25.7 to 21.7.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V3.1-Terminus | Nova 2.0 Pro Preview |
|---|---|---|
| Provider | DeepSeek | Amazon |
| Noometry Index | 42.6 | 32.8 |
| Rank | 96 | 241 |
| Context | 164K | — |
| Input $/M | $0.30 | — |
| Output $/M | $1 | — |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V3.1-Terminus: 41.5 (#114)
- Nova 2.0 Pro Preview: 40.2 (#130)

| Benchmark | DeepSeek-V3.1-Terminus | Nova 2.0 Pro Preview |
|---|---|---|
| SciCode | 40.6% | 42.7% |
| LMArena Coding | 1426 | — |
| ALE-Bench | 745.17 | — |

## Agentic & Tool Use

- DeepSeek-V3.1-Terminus: —
- Nova 2.0 Pro Preview: 21.9 (#127)

| Benchmark | DeepSeek-V3.1-Terminus | Nova 2.0 Pro Preview |
|---|---|---|
| GDP.pdf | — | 2% |

## Reasoning

- DeepSeek-V3.1-Terminus: 25.7 (#126)
- Nova 2.0 Pro Preview: 21.7 (#189)

| Benchmark | DeepSeek-V3.1-Terminus | Nova 2.0 Pro Preview |
|---|---|---|
| CritPt | 1.7% | 0% |
| Kagi LLM Benchmark | 57.4% | — |
| LMArena Hard Prompts | 1427 | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |

## Math

- DeepSeek-V3.1-Terminus: 35.7 (#138)
- Nova 2.0 Pro Preview: —

| Benchmark | DeepSeek-V3.1-Terminus | Nova 2.0 Pro Preview |
|---|---|---|
| LMArena Math | 1402 | — |

## Multilingual

- DeepSeek-V3.1-Terminus: 52.3 (#87)
- Nova 2.0 Pro Preview: —

| Benchmark | DeepSeek-V3.1-Terminus | Nova 2.0 Pro Preview |
|---|---|---|
| LMArena Non-English | 1407 | — |
| LMArena Russian | 1434 | — |

## Instruction Following

- DeepSeek-V3.1-Terminus: 74.4 (#96)
- Nova 2.0 Pro Preview: —

| Benchmark | DeepSeek-V3.1-Terminus | Nova 2.0 Pro Preview |
|---|---|---|
| LMArena Instruction Following | 1406 | — |

## Long Context

- DeepSeek-V3.1-Terminus: 43.5 (#88)
- Nova 2.0 Pro Preview: —

| Benchmark | DeepSeek-V3.1-Terminus | Nova 2.0 Pro Preview |
|---|---|---|
| LMArena Longer Query | 1426 | — |

## Writing & Preference

- DeepSeek-V3.1-Terminus: 61.3 (#87)
- Nova 2.0 Pro Preview: —

| Benchmark | DeepSeek-V3.1-Terminus | Nova 2.0 Pro Preview |
|---|---|---|
| LMArena Text | 1420 | — |
| LMArena Creative Writing | 1404 | — |
| LMArena Multi-Turn | 1411 | — |

## FAQ

### Is DeepSeek-V3.1-Terminus better than Nova 2.0 Pro Preview?

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 32.8 on the Noometry Index.

### Is DeepSeek-V3.1-Terminus or Nova 2.0 Pro Preview better for coding?

DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 40.2 in the Noometry coding category.

### How many benchmarks do DeepSeek-V3.1-Terminus and Nova 2.0 Pro Preview share?

2 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Nova 2.0 Pro Preview has 3.