Model comparison

DeepSeek V4.1 Flash vs Step 3.7 Flash

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 37.3 on the Noometry Index.

Last verified . 4 shared benchmarks.

DeepSeek V4.1 Flash DeepSeek

52.8

Rank #38 Confirmed

Step 3.7 Flash StepFun

37.3

Rank #207 Reported

Summary

  • They share 4 benchmarks with published results for both. DeepSeek V4.1 Flash 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 DeepSeek V4.1 Flash leads 50.2 to 21.6.
  • The biggest single-benchmark swing is NYT Connections (extended): 89.6% for DeepSeek V4.1 Flash and 39.7% for Step 3.7 Flash.
  • DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.18 / $1.11 for Step 3.7 Flash.
  • DeepSeek V4.1 Flash accepts more context: 1M tokens versus 256K.

Side by side

DeepSeek V4.1 Flash and Step 3.7 Flash specifications
DeepSeek V4.1 FlashStep 3.7 Flash
ProviderDeepSeekStepFun
Noometry Index52.837.3
Released2026-09-092026-05-29
WeightsOpenOpen
Context window1M256K
Max output393K256K
Input $ / M tokens$0.15$0.18
Output $ / M tokens$0.60$1.11
Results tracked375

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

Category by category

Coding DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 52.9 (#32), Step 3.7 Flash: 40.0 (#150)

Coding benchmarks
BenchmarkDeepSeek V4.1 FlashStep 3.7 Flash
SciCode51.9%40%
ALE-Bench1,092694.12
LMArena WebDev1619—
LMArena Coding1506—

Agentic & Tool Use Not comparable

DeepSeek V4.1 Flash: 31.2 (#69), Step 3.7 Flash: —

Agentic & Tool Use benchmarks
BenchmarkDeepSeek V4.1 FlashStep 3.7 Flash
APEX-Agents39.5%—
GDP.pdf19.8%—

Reasoning DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 50.2 (#36), Step 3.7 Flash: 21.6 (#219)

Reasoning benchmarks
BenchmarkDeepSeek V4.1 FlashStep 3.7 Flash
NYT Connections (extended)89.6%39.7%
CritPt14.3%2.3%
LMArena Hard Prompts1483—
Mystery Game Puzzles43%—
DTBench89.9%—
LMCA47%—
Surface Evolver Bench46.3%—
Epoch Capabilities Index154.9—

Math DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 66.7 (#25), Step 3.7 Flash: 42.9 (#82)

Math benchmarks
BenchmarkDeepSeek V4.1 FlashStep 3.7 Flash
FrontierMath (Tiers 1-3)67.4%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions—68.5%
OTIS Mock AIME 2024-202598.3%—
ProofBench54%—
LMArena Math1477—

Knowledge Not comparable

DeepSeek V4.1 Flash: 57.9 (#38), Step 3.7 Flash: —

Knowledge benchmarks
BenchmarkDeepSeek V4.1 FlashStep 3.7 Flash
GPQA Diamond89.8%—
LMArena Expert1506—

Multimodal Not comparable

DeepSeek V4.1 Flash: 39.1 (#61), Step 3.7 Flash: —

Multimodal benchmarks
BenchmarkDeepSeek V4.1 FlashStep 3.7 Flash
LMArena Vision1277—
Furniture Assembly34.2%—

Multilingual Not comparable

DeepSeek V4.1 Flash: 55.0 (#35), Step 3.7 Flash: —

Multilingual benchmarks
BenchmarkDeepSeek V4.1 FlashStep 3.7 Flash
LMArena Non-English1448—
LMArena Chinese1497—
LMArena French1452—
LMArena German1484—
LMArena Japanese1412—
LMArena Korean1452—
LMArena Russian1471—
LMArena Spanish1459—

Instruction Following Not comparable

DeepSeek V4.1 Flash: 77.3 (#26), Step 3.7 Flash: —

Instruction Following benchmarks
BenchmarkDeepSeek V4.1 FlashStep 3.7 Flash
LMArena Instruction Following1474—

Long Context Not comparable

DeepSeek V4.1 Flash: 45.2 (#47), Step 3.7 Flash: —

Long Context benchmarks
BenchmarkDeepSeek V4.1 FlashStep 3.7 Flash
LMArena Longer Query1475—

Writing & Preference Not comparable

DeepSeek V4.1 Flash: 65.4 (#48), Step 3.7 Flash: —

Writing & Preference benchmarks
BenchmarkDeepSeek V4.1 FlashStep 3.7 Flash
LMArena Text1462—
LMArena Creative Writing1435—
EQ-Bench Creative Writing1540—
LMArena Multi-Turn1457—

Frequently asked questions

Is DeepSeek V4.1 Flash better than Step 3.7 Flash?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 37.3 on the Noometry Index.

Which is cheaper, DeepSeek V4.1 Flash or Step 3.7 Flash?

DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Step 3.7 Flash lists at $0.18 and $1.11.

Is DeepSeek V4.1 Flash or Step 3.7 Flash better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 40.0 in the Noometry coding category.

Which has the bigger context window?

DeepSeek V4.1 Flash does, with 1M tokens against 256K.

How many benchmarks do DeepSeek V4.1 Flash and Step 3.7 Flash share?

4 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Step 3.7 Flash has 5.

Related comparisons

Go deeper