# Deepseek Coder v2 vs Step 3.7 Flash

> Step 3.7 Flash is the stronger model overall, scoring 37.3 to 35.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-coder-v2-vs-step-3-7-flash
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where Step 3.7 Flash leads 42.9 to 34.9.

## Snapshot

| | Deepseek Coder v2 | Step 3.7 Flash |
|---|---|---|
| Provider | DeepSeek | StepFun |
| Noometry Index | 35.9 | 37.3 |
| Rank | 220 | 207 |
| Context | — | 256K |
| Input $/M | — | $0.18 |
| Output $/M | — | $1.11 |
| Weights | Open | Open |

## Coding

- Deepseek Coder v2: 38.1 (#183)
- Step 3.7 Flash: 40.0 (#150)

| Benchmark | Deepseek Coder v2 | Step 3.7 Flash |
|---|---|---|
| SciCode | — | 40% |
| BigCodeBench Instruct | 48.2% | — |
| LMArena Coding | 1251 | — |
| BigCodeBench Complete | 59.7% | — |
| ALE-Bench | — | 694.12 |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |

## Reasoning

- Deepseek Coder v2: 23.6 (#176)
- Step 3.7 Flash: 21.6 (#219)

| Benchmark | Deepseek Coder v2 | Step 3.7 Flash |
|---|---|---|
| NYT Connections (extended) | — | 39.7% |
| CritPt | — | 2.3% |
| LMArena Hard Prompts | 1207 | — |
| WinoGrande | 83.7% | — |

## Math

- Deepseek Coder v2: 34.9 (#190)
- Step 3.7 Flash: 42.9 (#82)

| Benchmark | Deepseek Coder v2 | Step 3.7 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 68.5% |
| LMArena Math | 1241 | — |
| GSM8K | 94.5% | — |

## Knowledge

- Deepseek Coder v2: 32.3 (#212)
- Step 3.7 Flash: —

| Benchmark | Deepseek Coder v2 | Step 3.7 Flash |
|---|---|---|
| LMArena Expert | 1181 | — |
| ARC (AI2) Challenge | 64.3% | — |

## Multilingual

- Deepseek Coder v2: 36.3 (#240)
- Step 3.7 Flash: —

| Benchmark | Deepseek Coder v2 | Step 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1182 | — |
| LMArena Chinese | 1201 | — |
| LMArena French | 1185 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Russian | 1188 | — |
| LMArena Spanish | 1153 | — |

## Instruction Following

- Deepseek Coder v2: 61.7 (#242)
- Step 3.7 Flash: —

| Benchmark | Deepseek Coder v2 | Step 3.7 Flash |
|---|---|---|
| LMArena Instruction Following | 1180 | — |

## Long Context

- Deepseek Coder v2: 37.0 (#224)
- Step 3.7 Flash: —

| Benchmark | Deepseek Coder v2 | Step 3.7 Flash |
|---|---|---|
| LMArena Longer Query | 1219 | — |

## Writing & Preference

- Deepseek Coder v2: 38.2 (#253)
- Step 3.7 Flash: —

| Benchmark | Deepseek Coder v2 | Step 3.7 Flash |
|---|---|---|
| LMArena Text | 1191 | — |
| LMArena Creative Writing | 1120 | — |
| LMArena Multi-Turn | 1177 | — |

## FAQ

### Is Deepseek Coder v2 better than Step 3.7 Flash?

Step 3.7 Flash is the stronger model overall, scoring 37.3 to 35.9 on the Noometry Index.

### Is Deepseek Coder v2 or Step 3.7 Flash better for coding?

Step 3.7 Flash scores higher on coding benchmarks: 40.0 versus 38.1 in the Noometry coding category.

### How many benchmarks do Deepseek Coder v2 and Step 3.7 Flash share?

0 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Step 3.7 Flash has 5.