# Qwen2.5 7B Instruct vs Step 3.7 Flash

> Step 3.7 Flash is the stronger model overall, scoring 36.5 to 28.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen2-5-7b-instruct-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 40.9 to 11.8.
- Qwen2.5 7B Instruct is cheaper at $0.17 / $0.70 per million input/output tokens, against $0.18 / $1.11 for Step 3.7 Flash.
- Step 3.7 Flash accepts more context: 256K tokens versus 131K.

## Snapshot

| | Qwen2.5 7B Instruct | Step 3.7 Flash |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 28.6 | 36.5 |
| Rank | 314 | 207 |
| Context | 131K | 256K |
| Input $/M | $0.17 | $0.18 |
| Output $/M | $0.70 | $1.11 |
| Weights | Open | Open |

## Coding

- Qwen2.5 7B Instruct: 35.9 (#204)
- Step 3.7 Flash: 39.4 (#147)

| Benchmark | Qwen2.5 7B Instruct | Step 3.7 Flash |
|---|---|---|
| SciCode | — | 40% |
| BigCodeBench Instruct | 37.6% | — |
| BigCodeBench Complete | 46.1% | — |
| ALE-Bench | — | 694.12 |

## Agentic & Tool Use

- Qwen2.5 7B Instruct: 23.5 (#117)
- Step 3.7 Flash: —

| Benchmark | Qwen2.5 7B Instruct | Step 3.7 Flash |
|---|---|---|
| BALROG | 7.8% | — |

## Reasoning

- Qwen2.5 7B Instruct: 14.3 (#317)
- Step 3.7 Flash: 20.9 (#211)

| Benchmark | Qwen2.5 7B Instruct | Step 3.7 Flash |
|---|---|---|
| NYT Connections (extended) | — | 39.7% |
| CritPt | — | 2.3% |
| Chess Puzzles | 0% | — |
| DTBench | 47.7% | — |
| LMCA | 6.4% | — |
| Epoch Capabilities Index | 118.44 | — |

## Math

- Qwen2.5 7B Instruct: 11.8 (#300)
- Step 3.7 Flash: 40.9 (#74)

| Benchmark | Qwen2.5 7B Instruct | Step 3.7 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 68.5% |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| Omni-MATH | 29.4% | — |

## Knowledge

- Qwen2.5 7B Instruct: 17.0 (#281)
- Step 3.7 Flash: —

| Benchmark | Qwen2.5 7B Instruct | Step 3.7 Flash |
|---|---|---|
| GPQA Diamond | 35.5% | — |
| MMLU-Pro | 53.9% | — |
| GPQA (HELM) | 34.1% | — |
| MMLU | 72.9% | — |

## Instruction Following

- Qwen2.5 7B Instruct: 63.4 (#226)
- Step 3.7 Flash: —

| Benchmark | Qwen2.5 7B Instruct | Step 3.7 Flash |
|---|---|---|
| IFEval | 74.1% | — |

## Writing & Preference

- Qwen2.5 7B Instruct: 48.8 (#194)
- Step 3.7 Flash: —

| Benchmark | Qwen2.5 7B Instruct | Step 3.7 Flash |
|---|---|---|
| WildBench | 73.1% | — |

## FAQ

### Is Qwen2.5 7B Instruct better than Step 3.7 Flash?

Step 3.7 Flash is the stronger model overall, scoring 36.5 to 28.6 on the Noometry Index.

### Which is cheaper, Qwen2.5 7B Instruct or Step 3.7 Flash?

Qwen2.5 7B Instruct is cheaper. It lists at $0.17 per million input tokens and $0.70 per million output tokens; Step 3.7 Flash lists at $0.18 and $1.11.

### Is Qwen2.5 7B Instruct or Step 3.7 Flash better for coding?

Step 3.7 Flash scores higher on coding benchmarks: 39.4 versus 35.9 in the Noometry coding category.

### Which has the bigger context window?

Step 3.7 Flash does, with 256K tokens against 131K.

### How many benchmarks do Qwen2.5 7B Instruct and Step 3.7 Flash share?

0 benchmarks have published results for both models. Qwen2.5 7B Instruct has 15 scored results on Noometry and Step 3.7 Flash has 5.