# DeepSeek V4.1 Flash vs Step 3.5 Flash

> DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 41.7 on the Noometry Index. Step 3.5 Flash costs 1.7× less per token, which makes it the better buy when DeepSeek V4.1 Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/deepseek-v4-1-flash-vs-step-3-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and Step 3.5 Flash in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4.1 Flash leads 46.2 to 21.2.
- The biggest single-benchmark swing is NYT Connections (extended): 89.6% for DeepSeek V4.1 Flash and 28.4% for Step 3.5 Flash.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.15 / $0.60 for DeepSeek V4.1 Flash.
- DeepSeek V4.1 Flash accepts more context: 1M tokens versus 256K.

## Snapshot

| | DeepSeek V4.1 Flash | Step 3.5 Flash |
|---|---|---|
| Provider | DeepSeek | StepFun |
| Noometry Index | 50.3 | 41.7 |
| Rank | 40 | 116 |
| Context | 1M | 256K |
| Input $/M | $0.15 | $0.10 |
| Output $/M | $0.60 | $0.30 |
| Weights | Open | Open |

## Coding

- DeepSeek V4.1 Flash: 52.8 (#29)
- Step 3.5 Flash: 41.7 (#106)

| Benchmark | DeepSeek V4.1 Flash | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1511 | 1436 |
| LMArena WebDev | 1620 | — |
| SciCode | 51.9% | — |
| ALE-Bench | 1,092 | — |

## Reasoning

- DeepSeek V4.1 Flash: 46.2 (#39)
- Step 3.5 Flash: 21.2 (#202)

| Benchmark | DeepSeek V4.1 Flash | Step 3.5 Flash |
|---|---|---|
| NYT Connections (extended) | 89.6% | 28.4% |
| LMArena Hard Prompts | 1485 | 1411 |
| CritPt | 14.3% | — |
| DTBench | 89.9% | — |
| LMCA | 47% | — |
| Surface Evolver Bench | 46.3% | — |
| Epoch Capabilities Index | 155.01 | — |

## Math

- DeepSeek V4.1 Flash: 48.4 (#52)
- Step 3.5 Flash: 40.6 (#77)

| Benchmark | DeepSeek V4.1 Flash | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1493 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| ProofBench | 54% | — |

## Knowledge

- DeepSeek V4.1 Flash: 41.6 (#97)
- Step 3.5 Flash: 39.0 (#127)

| Benchmark | DeepSeek V4.1 Flash | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1505 | 1422 |

## Multilingual

- DeepSeek V4.1 Flash: 55.5 (#29)
- Step 3.5 Flash: 50.7 (#115)

| Benchmark | DeepSeek V4.1 Flash | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1452 | 1386 |
| LMArena Chinese | 1506 | 1448 |
| LMArena French | 1448 | 1421 |
| LMArena Russian | 1473 | 1385 |
| LMArena Spanish | 1499 | 1419 |
| LMArena German | — | 1404 |
| LMArena Japanese | — | 1353 |
| LMArena Korean | — | 1350 |

## Instruction Following

- DeepSeek V4.1 Flash: 77.6 (#24)
- Step 3.5 Flash: 73.3 (#119)

| Benchmark | DeepSeek V4.1 Flash | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1475 | 1385 |

## Long Context

- DeepSeek V4.1 Flash: 45.2 (#46)
- Step 3.5 Flash: 42.8 (#112)

| Benchmark | DeepSeek V4.1 Flash | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1476 | 1402 |

## Writing & Preference

- DeepSeek V4.1 Flash: 65.8 (#43)
- Step 3.5 Flash: 59.0 (#108)

| Benchmark | DeepSeek V4.1 Flash | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1465 | 1403 |
| LMArena Creative Writing | 1436 | 1357 |
| LMArena Multi-Turn | 1460 | 1405 |
| EQ-Bench Creative Writing | 1540 | — |

## FAQ

### Is DeepSeek V4.1 Flash better than Step 3.5 Flash?

DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 41.7 on the Noometry Index. Step 3.5 Flash costs 1.7× less per token, which makes it the better buy when DeepSeek V4.1 Flash's lead doesn't matter for your workload.

### Which is cheaper, DeepSeek V4.1 Flash or Step 3.5 Flash?

Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; DeepSeek V4.1 Flash lists at $0.15 and $0.60.

### Is DeepSeek V4.1 Flash or Step 3.5 Flash better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.8 versus 41.7 in the Noometry coding category.

### Which has the bigger context window?

DeepSeek V4.1 Flash does, with 1M tokens against 256K.

### How many benchmarks do DeepSeek V4.1 Flash and Step 3.5 Flash share?

15 benchmarks have published results for both models. DeepSeek V4.1 Flash has 25 scored results on Noometry and Step 3.5 Flash has 19.