# DeepSeek-V3.1 vs DeepSeek V4.1 Flash

> DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 42.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-vs-deepseek-v4-1-flash
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 1 category and DeepSeek V4.1 Flash in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4.1 Flash leads 46.2 to 27.3.
- The biggest single-benchmark swing is LMCA: 24.3% for DeepSeek-V3.1 and 47% for DeepSeek V4.1 Flash.
- DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.25 / $0.95 for DeepSeek-V3.1.
- DeepSeek V4.1 Flash accepts more context: 1M tokens versus 164K.

## Snapshot

| | DeepSeek-V3.1 | DeepSeek V4.1 Flash |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Noometry Index | 42.2 | 50.3 |
| Rank | 106 | 40 |
| Context | 164K | 1M |
| Input $/M | $0.25 | $0.15 |
| Output $/M | $0.95 | $0.60 |
| Weights | Open | Open |

## Coding

- DeepSeek-V3.1: 39.8 (#140)
- DeepSeek V4.1 Flash: 52.8 (#29)

| Benchmark | DeepSeek-V3.1 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Coding | 1417 | 1511 |
| LMArena WebDev | — | 1620 |
| SciCode | — | 51.9% |
| WeirdML | 38.4% | — |
| ALE-Bench | — | 1,092 |

## Reasoning

- DeepSeek-V3.1: 27.3 (#109)
- DeepSeek V4.1 Flash: 46.2 (#39)

| Benchmark | DeepSeek-V3.1 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1485 |
| DTBench | 82.7% | 89.9% |
| LMCA | 24.3% | 47% |
| Epoch Capabilities Index | 139.92 | 155.01 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| NYT Connections (extended) | — | 89.6% |
| CritPt | — | 14.3% |
| Surface Evolver Bench | — | 46.3% |
| ForecastBench | 58 | — |

## Math

- DeepSeek-V3.1: 36.1 (#125)
- DeepSeek V4.1 Flash: 48.4 (#52)

| Benchmark | DeepSeek-V3.1 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Math | 1420 | 1493 |
| ProofBench | — | 54% |

## Knowledge

- DeepSeek-V3.1: 43.0 (#86)
- DeepSeek V4.1 Flash: 41.6 (#97)

| Benchmark | DeepSeek-V3.1 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Expert | 1403 | 1505 |
| Vectara Hallucination Rate | 5.5% | — |

## Multilingual

- DeepSeek-V3.1: 51.8 (#100)
- DeepSeek V4.1 Flash: 55.5 (#29)

| Benchmark | DeepSeek-V3.1 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Non-English | 1400 | 1452 |
| LMArena Chinese | 1470 | 1506 |
| LMArena French | 1447 | 1448 |
| LMArena Russian | 1405 | 1473 |
| LMArena Spanish | 1429 | 1499 |
| LMArena German | 1412 | — |
| LMArena Japanese | 1374 | — |
| LMArena Korean | 1337 | — |

## Instruction Following

- DeepSeek-V3.1: 74.1 (#105)
- DeepSeek V4.1 Flash: 77.6 (#24)

| Benchmark | DeepSeek-V3.1 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Instruction Following | 1400 | 1475 |

## Long Context

- DeepSeek-V3.1: 36.3 (#227)
- DeepSeek V4.1 Flash: 45.2 (#46)

| Benchmark | DeepSeek-V3.1 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Longer Query | 1422 | 1476 |
| Fiction.LiveBench | 52.8% | — |

## Writing & Preference

- DeepSeek-V3.1: 60.5 (#93)
- DeepSeek V4.1 Flash: 65.8 (#43)

| Benchmark | DeepSeek-V3.1 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Text | 1420 | 1465 |
| LMArena Creative Writing | 1401 | 1436 |
| EQ-Bench Creative Writing | 1436 | 1540 |
| LMArena Multi-Turn | 1408 | 1460 |

## FAQ

### Is DeepSeek-V3.1 better than DeepSeek V4.1 Flash?

DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 42.2 on the Noometry Index.

### Which is cheaper, DeepSeek-V3.1 or DeepSeek V4.1 Flash?

DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; DeepSeek-V3.1 lists at $0.25 and $0.95.

### Is DeepSeek-V3.1 or DeepSeek V4.1 Flash better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.8 versus 39.8 in the Noometry coding category.

### Which has the bigger context window?

DeepSeek V4.1 Flash does, with 1M tokens against 164K.

### How many benchmarks do DeepSeek-V3.1 and DeepSeek V4.1 Flash share?

18 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and DeepSeek V4.1 Flash has 25.