Noometry

Model comparison

Qwen3.8 Max vs Step 3.7 Flash

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 37.3 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.

Last verified . 3 shared benchmarks.

Qwen3.8 Max Alibaba (Qwen)

56.8

Rank #22 Confirmed

Step 3.7 Flash StepFun

37.3

Rank #207 Reported

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 54.4 to 21.6.
  • 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.

Side by side

Qwen3.8 MaxStep 3.7 Flash
ProviderAlibaba (Qwen)StepFun
Noometry Index56.837.3
Released2026-08-022026-05-29
WeightsProprietaryOpen
Context window1M256K
Max output131K256K
Input $ / M tokens$2$0.18
Output $ / M tokens$6$1.11
Results tracked395

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Qwen3.8 Max leads

Qwen3.8 Max: 53.5 (#29), Step 3.7 Flash: 40.0 (#150)

BenchmarkQwen3.8 MaxStep 3.7 Flash
SciCode53.2%40%
DeepSWE57.5%—
LMArena WebDev1674—
FrontierSWE17.8%—
LMArena Coding1502—
ALE-Bench—694.12

Agentic & Tool Use Not comparable

Qwen3.8 Max: 45.4 (#14), Step 3.7 Flash: —

BenchmarkQwen3.8 MaxStep 3.7 Flash
APEX-Agents63.3%—
τ²-bench Banking55.1%—
GDP.pdf23.2%—

Reasoning Qwen3.8 Max leads

Qwen3.8 Max: 54.4 (#26), Step 3.7 Flash: 21.6 (#219)

BenchmarkQwen3.8 MaxStep 3.7 Flash
NYT Connections (extended)88.3%39.7%
CritPt20%2.3%
Chess Puzzles40%—
LMArena Hard Prompts1496—
Mystery Game Puzzles38%—
DTBench92%—
LMCA46.2%—
Epoch Capabilities Index156.41—

Math Qwen3.8 Max leads

Qwen3.8 Max: 73.2 (#20), Step 3.7 Flash: 42.9 (#82)

BenchmarkQwen3.8 MaxStep 3.7 Flash
FrontierMath (Tiers 1-3)74.7%—
FrontierMath Tier 446.3%—
MathArena Final-Answer Competitions—68.5%
OTIS Mock AIME 2024-2025100%—
ProofBench58%—
LMArena Math1499—

Knowledge Not comparable

Qwen3.8 Max: 61.7 (#27), Step 3.7 Flash: —

BenchmarkQwen3.8 MaxStep 3.7 Flash
GPQA Diamond92.7%—
SimpleQA Verified47.3%—
LMArena Expert1507—

Multimodal Not comparable

Qwen3.8 Max: 37.2 (#75), Step 3.7 Flash: —

BenchmarkQwen3.8 MaxStep 3.7 Flash
LMArena Vision1314—
Furniture Assembly20%—

Multilingual Not comparable

Qwen3.8 Max: 56.7 (#18), Step 3.7 Flash: —

BenchmarkQwen3.8 MaxStep 3.7 Flash
LMArena Non-English1472—
LMArena Chinese1538—
LMArena French1503—
LMArena German1483—
LMArena Japanese1467—
LMArena Korean1461—
LMArena Russian1481—
LMArena Spanish1492—

Instruction Following Not comparable

Qwen3.8 Max: 77.6 (#17), Step 3.7 Flash: —

BenchmarkQwen3.8 MaxStep 3.7 Flash
LMArena Instruction Following1479—

Long Context Not comparable

Qwen3.8 Max: 45.6 (#31), Step 3.7 Flash: —

BenchmarkQwen3.8 MaxStep 3.7 Flash
LMArena Longer Query1489—

Writing & Preference Not comparable

Qwen3.8 Max: 67.1 (#30), Step 3.7 Flash: —

BenchmarkQwen3.8 MaxStep 3.7 Flash
LMArena Text1483—
LMArena Creative Writing1479—
LMArena Multi-Turn1489—

Frequently asked questions

Is Qwen3.8 Max better than Step 3.7 Flash?

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 37.3 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: 53.5 versus 40.0 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 39 scored results on Noometry and Step 3.7 Flash has 5.

Related comparisons

Go deeper