# Qwen3-4B vs Step 3.7 Flash

> Step 3.7 Flash is the stronger model overall, scoring 36.5 to 31.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen3-4b-vs-step-3-7-flash
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Qwen3-4B scores higher in 0 categories and Step 3.7 Flash in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 3.7 Flash leads 40.9 to 28.5.
- The biggest single-benchmark swing is MathArena Final-Answer Competitions: 38.5% for Qwen3-4B and 68.5% for Step 3.7 Flash.

## Snapshot

| | Qwen3-4B | Step 3.7 Flash |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 31.5 | 36.5 |
| Rank | 261 | 207 |
| Context | — | 256K |
| Input $/M | — | $0.18 |
| Output $/M | — | $1.11 |
| Weights | Open | Open |

## Coding

- Qwen3-4B: —
- Step 3.7 Flash: 39.4 (#147)

| Benchmark | Qwen3-4B | Step 3.7 Flash |
|---|---|---|
| SciCode | — | 40% |
| ALE-Bench | — | 694.12 |

## Agentic & Tool Use

- Qwen3-4B: 27.3 (#94)
- Step 3.7 Flash: —

| Benchmark | Qwen3-4B | Step 3.7 Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 35.7% | — |

## Reasoning

- Qwen3-4B: 18.5 (#264)
- Step 3.7 Flash: 20.9 (#211)

| Benchmark | Qwen3-4B | Step 3.7 Flash |
|---|---|---|
| NYT Connections (extended) | — | 39.7% |
| CritPt | — | 2.3% |
| Chess Puzzles | 4% | — |

## Math

- Qwen3-4B: 28.5 (#228)
- Step 3.7 Flash: 40.9 (#74)

| Benchmark | Qwen3-4B | Step 3.7 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | 38.5% | 68.5% |
| OTIS Mock AIME 2024-2025 | 52.2% | — |

## Knowledge

- Qwen3-4B: 33.0 (#198)
- Step 3.7 Flash: —

| Benchmark | Qwen3-4B | Step 3.7 Flash |
|---|---|---|
| GPQA Diamond | 52.3% | — |
| Vectara Hallucination Rate | 5.7% | — |

## FAQ

### Is Qwen3-4B better than Step 3.7 Flash?

Step 3.7 Flash is the stronger model overall, scoring 36.5 to 31.5 on the Noometry Index.

### How many benchmarks do Qwen3-4B and Step 3.7 Flash share?

1 benchmark has published results for both models. Qwen3-4B has 6 scored results on Noometry and Step 3.7 Flash has 5.