Model comparison

DeepSeek V4 Flash vs Step 3

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 40.5 on the Noometry Index.

Last verified . 16 shared benchmarks.

DeepSeek V4 Flash DeepSeek

53.6

Rank #35 Confirmed

Step 3 StepFun

40.5

Rank #149 Confirmed

Summary

  • They share 16 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 8 categories and Step 3 in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 28.4.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 52.2% for DeepSeek V4 Flash and 62.3% for Step 3.

Side by side

DeepSeek V4 Flash and Step 3 specifications
DeepSeek V4 FlashStep 3
ProviderDeepSeekStepFun
Noometry Index53.640.5
Released2026-04-24—
WeightsOpenOpen
Context window1M—
Max output393K—
Input $ / M tokens$0.15—
Output $ / M tokens$0.60—
Results tracked4117

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

Category by category

Coding DeepSeek V4 Flash leads

DeepSeek V4 Flash: 47.9 (#59), Step 3: 40.1 (#147)

Coding benchmarks
BenchmarkDeepSeek V4 FlashStep 3
LMArena Coding14571367
FrontierCode18.8%—
LMArena WebDev1582—
SciCode49.9%—
WeirdML63%—
ALE-Bench1,306—

Reasoning DeepSeek V4 Flash leads

DeepSeek V4 Flash: 53.7 (#30), Step 3: 28.4 (#105)

Reasoning benchmarks
BenchmarkDeepSeek V4 FlashStep 3
Kagi LLM Benchmark52.2%62.3%
LMArena Hard Prompts14441355
ARC-AGI-261.4%—
SimpleBench61.1%—
NYT Connections (extended)89.6%—
ARC-AGI-189%—
CritPt16.6%—
Chess Puzzles33%—
Mystery Game Puzzles34%—
DTBench90.9%—
LMCA41.7%—
Epoch Capabilities Index154.49—

Math DeepSeek V4 Flash leads

DeepSeek V4 Flash: 60.3 (#37), Step 3: 37.6 (#148)

Math benchmarks
BenchmarkDeepSeek V4 FlashStep 3
LMArena Math14271366
FrontierMath (Tiers 1-3)57.5%—
FrontierMath Tier 424.4%—
MathArena Final-Answer Competitions76.5%—
OTIS Mock AIME 2024-202594.4%—
ProofBench56%—

Knowledge DeepSeek V4 Flash leads

DeepSeek V4 Flash: 55.4 (#48), Step 3: 36.8 (#164)

Knowledge benchmarks
BenchmarkDeepSeek V4 FlashStep 3
LMArena Expert14411333
GPQA Diamond91%—
SimpleQA Verified33.6%—

Multimodal Not comparable

DeepSeek V4 Flash: —, Step 3: 35.5 (#86)

Multimodal benchmarks
BenchmarkDeepSeek V4 FlashStep 3
LMArena Vision—1177

Multilingual DeepSeek V4 Flash leads

DeepSeek V4 Flash: 53.0 (#72), Step 3: 46.3 (#159)

Multilingual benchmarks
BenchmarkDeepSeek V4 FlashStep 3
LMArena Non-English14201327
LMArena Chinese14681397
LMArena German14181371
LMArena Korean13841269
LMArena Russian14281331
LMArena Spanish14361371
LMArena French1439—
LMArena Japanese1406—

Instruction Following DeepSeek V4 Flash leads

DeepSeek V4 Flash: 74.9 (#81), Step 3: 70.4 (#164)

Instruction Following benchmarks
BenchmarkDeepSeek V4 FlashStep 3
LMArena Instruction Following14211332

Long Context DeepSeek V4 Flash leads

DeepSeek V4 Flash: 43.8 (#85), Step 3: 40.3 (#157)

Long Context benchmarks
BenchmarkDeepSeek V4 FlashStep 3
LMArena Longer Query14341326

Writing & Preference DeepSeek V4 Flash leads

DeepSeek V4 Flash: 63.8 (#61), Step 3: 54.3 (#151)

Writing & Preference benchmarks
BenchmarkDeepSeek V4 FlashStep 3
LMArena Text14321350
LMArena Creative Writing14031321
LMArena Multi-Turn14491341
EQ-Bench Creative Writing1559—

Frequently asked questions

Is DeepSeek V4 Flash better than Step 3?

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 40.5 on the Noometry Index.

Is DeepSeek V4 Flash or Step 3 better for coding?

DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 40.1 in the Noometry coding category.

How many benchmarks do DeepSeek V4 Flash and Step 3 share?

16 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Step 3 has 17.

Related comparisons

Go deeper