# Qwen3.8 Max vs Step 3.7 Flash

> Qwen3.8 Max is the stronger model overall, scoring 56.0 to 36.5 on the Noometry Index. Step 3.7 Flash costs 7.2× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/qwen3-8-max-vs-step-3-7-flash
- Last updated: 2026-10-10
- Shared benchmarks: 3

## Summary

- They share 3 benchmarks with published results for both. Qwen3.8 Max scores higher in 3 categories and Step 3.7 Flash in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.8 Max leads 53.4 to 20.9.
- The biggest single-benchmark swing is NYT Connections (extended): 88.3% for Qwen3.8 Max and 39.7% for Step 3.7 Flash.
- Step 3.7 Flash is cheaper at $0.18 / $1.11 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- Qwen3.8 Max accepts more context: 1M tokens versus 256K.
- Step 3.7 Flash has downloadable open weights; the other is API-only.

## Snapshot

| | Qwen3.8 Max | Step 3.7 Flash |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 56.0 | 36.5 |
| Rank | 21 | 207 |
| Context | 1M | 256K |
| Input $/M | $2 | $0.18 |
| Output $/M | $6 | $1.11 |
| Weights | Proprietary | Open |

## Coding

- Qwen3.8 Max: 52.3 (#30)
- Step 3.7 Flash: 39.4 (#147)

| Benchmark | Qwen3.8 Max | Step 3.7 Flash |
|---|---|---|
| SciCode | 52.9% | 40% |
| DeepSWE | 57.5% | — |
| LMArena WebDev | 1671 | — |
| FrontierSWE | 15.8% | — |
| LMArena Coding | 1499 | — |
| ALE-Bench | — | 694.12 |

## Agentic & Tool Use

- Qwen3.8 Max: 42.6 (#17)
- Step 3.7 Flash: —

| Benchmark | Qwen3.8 Max | Step 3.7 Flash |
|---|---|---|
| τ²-bench Banking | 55.1% | — |
| GDP.pdf | 23.2% | — |

## Reasoning

- Qwen3.8 Max: 53.4 (#26)
- Step 3.7 Flash: 20.9 (#211)

| Benchmark | Qwen3.8 Max | Step 3.7 Flash |
|---|---|---|
| NYT Connections (extended) | 88.3% | 39.7% |
| CritPt | 20% | 2.3% |
| Chess Puzzles | 40% | — |
| LMArena Hard Prompts | 1493 | — |
| Mystery Game Puzzles | 38% | — |
| DTBench | 92% | — |
| LMCA | 46.2% | — |
| Epoch Capabilities Index | 156.69 | — |

## Math

- Qwen3.8 Max: 73.1 (#15)
- Step 3.7 Flash: 40.9 (#74)

| Benchmark | Qwen3.8 Max | Step 3.7 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 74.7% | — |
| FrontierMath Tier 4 | 46.3% | — |
| MathArena Final-Answer Competitions | — | 68.5% |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 58% | — |
| LMArena Math | 1498 | — |

## Knowledge

- Qwen3.8 Max: 61.7 (#25)
- Step 3.7 Flash: —

| Benchmark | Qwen3.8 Max | Step 3.7 Flash |
|---|---|---|
| GPQA Diamond | 92.7% | — |
| SimpleQA Verified | 47.3% | — |
| LMArena Expert | 1504 | — |

## Multimodal

- Qwen3.8 Max: 36.9 (#70)
- Step 3.7 Flash: —

| Benchmark | Qwen3.8 Max | Step 3.7 Flash |
|---|---|---|
| LMArena Vision | 1314 | — |
| Furniture Assembly | 20% | — |

## Multilingual

- Qwen3.8 Max: 56.6 (#18)
- Step 3.7 Flash: —

| Benchmark | Qwen3.8 Max | Step 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1468 | — |
| LMArena Chinese | 1537 | — |
| LMArena French | 1502 | — |
| LMArena German | 1489 | — |
| LMArena Japanese | 1466 | — |
| LMArena Korean | 1467 | — |
| LMArena Russian | 1478 | — |
| LMArena Spanish | 1495 | — |

## Instruction Following

- Qwen3.8 Max: 77.7 (#19)
- Step 3.7 Flash: —

| Benchmark | Qwen3.8 Max | Step 3.7 Flash |
|---|---|---|
| LMArena Instruction Following | 1478 | — |

## Long Context

- Qwen3.8 Max: 45.5 (#30)
- Step 3.7 Flash: —

| Benchmark | Qwen3.8 Max | Step 3.7 Flash |
|---|---|---|
| LMArena Longer Query | 1486 | — |

## Writing & Preference

- Qwen3.8 Max: 67.0 (#31)
- Step 3.7 Flash: —

| Benchmark | Qwen3.8 Max | Step 3.7 Flash |
|---|---|---|
| LMArena Text | 1480 | — |
| LMArena Creative Writing | 1478 | — |
| LMArena Multi-Turn | 1487 | — |

## FAQ

### Is Qwen3.8 Max better than Step 3.7 Flash?

Qwen3.8 Max is the stronger model overall, scoring 56.0 to 36.5 on the Noometry Index. Step 3.7 Flash costs 7.2× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.

### Which is cheaper, Qwen3.8 Max or Step 3.7 Flash?

Step 3.7 Flash is cheaper. It lists at $0.18 per million input tokens and $1.11 per million output tokens; Qwen3.8 Max lists at $2 and $6.

### Is Qwen3.8 Max or Step 3.7 Flash better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 52.3 versus 39.4 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.8 Max does, with 1M tokens against 256K.

### How many benchmarks do Qwen3.8 Max and Step 3.7 Flash share?

3 benchmarks have published results for both models. Qwen3.8 Max has 38 scored results on Noometry and Step 3.7 Flash has 5.