# DeepSeek-V3.1 vs Sonar

> DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 37.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-vs-sonar
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.5 to 52.6.
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $1 / $1 for Sonar.
- DeepSeek-V3.1 accepts more context: 164K tokens versus 128K.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V3.1 | Sonar |
|---|---|---|
| Provider | DeepSeek | Perplexity |
| Noometry Index | 42.2 | 37.8 |
| Rank | 106 | 184 |
| Context | 164K | 128K |
| Input $/M | $0.25 | $1 |
| Output $/M | $0.95 | $1 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V3.1: 39.8 (#140)
- Sonar: 35.1 (#217)

| Benchmark | DeepSeek-V3.1 | Sonar |
|---|---|---|
| WeirdML | 38.4% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1417 | — |

## Reasoning

- DeepSeek-V3.1: 27.3 (#109)
- Sonar: 20.3 (#221)

| Benchmark | DeepSeek-V3.1 | Sonar |
|---|---|---|
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1417 | — |
| DTBench | 82.7% | — |
| LiveBench Data Analysis | — | 37.9% |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
| LiveBench | — | 46.9% |

## Math

- DeepSeek-V3.1: 36.1 (#125)
- Sonar: 31.3 (#197)

| Benchmark | DeepSeek-V3.1 | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| LMArena Math | 1420 | — |

## Knowledge

- DeepSeek-V3.1: 43.0 (#86)
- Sonar: —

| Benchmark | DeepSeek-V3.1 | Sonar |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | — |
| LMArena Expert | 1403 | — |

## Multilingual

- DeepSeek-V3.1: 51.8 (#100)
- Sonar: —

| Benchmark | DeepSeek-V3.1 | Sonar |
|---|---|---|
| LMArena Non-English | 1400 | — |
| LMArena Chinese | 1470 | — |
| LMArena French | 1447 | — |
| LMArena German | 1412 | — |
| LMArena Japanese | 1374 | — |
| LMArena Korean | 1337 | — |
| LMArena Russian | 1405 | — |
| LMArena Spanish | 1429 | — |

## Instruction Following

- DeepSeek-V3.1: 74.1 (#105)
- Sonar: 71.5 (#146)

| Benchmark | DeepSeek-V3.1 | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1400 | — |

## Long Context

- DeepSeek-V3.1: 36.3 (#227)
- Sonar: —

| Benchmark | DeepSeek-V3.1 | Sonar |
|---|---|---|
| Fiction.LiveBench | 52.8% | — |
| LMArena Longer Query | 1422 | — |

## Writing & Preference

- DeepSeek-V3.1: 60.5 (#93)
- Sonar: 52.6 (#166)

| Benchmark | DeepSeek-V3.1 | Sonar |
|---|---|---|
| LMArena Text | 1420 | — |
| LMArena Creative Writing | 1401 | — |
| EQ-Bench Creative Writing | 1436 | — |
| LMArena Multi-Turn | 1408 | — |
| LiveBench Language | — | 44.1% |

## FAQ

### Is DeepSeek-V3.1 better than Sonar?

DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 37.8 on the Noometry Index.

### Which is cheaper, DeepSeek-V3.1 or Sonar?

DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Sonar lists at $1 and $1.

### Is DeepSeek-V3.1 or Sonar better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 39.8 versus 35.1 in the Noometry coding category.

### Which has the bigger context window?

DeepSeek-V3.1 does, with 164K tokens against 128K.

### How many benchmarks do DeepSeek-V3.1 and Sonar share?

0 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Sonar has 7.