Enter opens the highlighted result. Esc closes.

DeepSeek V4 Flash 0731 vs Step 3.7 Flash

DeepSeek V4 Flash 0731 leads Step 3.7 Flash on the Artificial Analysis Intelligence Index, 34.3 to 19.5, and DeepSeek V4 Flash 0731 costs 4.1x less per output token ($0.28 vs $1.15 per million). Updated October 21, 2026; 15 benchmarks have a result for both.

Replace DeepSeek V4 Flash 0731 Replace Step 3.7 Flash
DeepSeek V4 Flash 0731DeepSeek
Coding
51.8
Overall
55.2
Output $/M
$0.28
14
Step 3.7 FlashStepFun
Coding
No data
Overall
No data
Output $/M
$1.15
1
vs boards won of 15 shared

DeepSeek V4 Flash 0731 or Step 3.7 Flash: which to pick

Only DeepSeek V4 Flash 0731 has a coding score, 51.8 on the Vibe Coding Index; Step 3.7 Flash has none, so the two cannot be ranked on coding.

Pick Step 3.7 Flash for work measured by Design Arena: ASCII art, where it leads.

Model ADeepSeek V4 Flash 0731DeepSeek51.8/1004 independent benchmarks$0.01 per solved taskModel BStep 3.7 FlashStepFunNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
15
DeepSeek V4 Flash 0731 only
40
Step 3.7 Flash only
3
Like-for-like categories
5 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
DeepSeek V4 Flash 0731 51.8 from 4 benchmarks, Step 3.7 Flash not benchmarked.
Widest category
Coding, 18.8 points apart on average over 3 shared benchmarks.
Widest single gap
AA Coding Index: DeepSeek V4 Flash 0731 69.1 against Step 3.7 Flash 39.6, 29.5 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Flash 0731 $0.28 against Step 3.7 Flash $1.15 per million output tokens, 4.1x apart.
Context window
DeepSeek V4 Flash 0731 takes 1.05M tokens, Step 3.7 Flash 262K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryDeepSeek V4 Flash 0731BarsStep 3.7 FlashTies
Coding30
Intelligence10
Reasoning20
Web design71
General10
All shared boards141
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
Coding benchmarks for DeepSeek V4 Flash 0731 and Step 3.7 Flash
BenchmarkDeepSeek V4 Flash 0731Step 3.7 FlashLeader
AA Coding Index69.139.6DeepSeek V4 Flash 0731
LiveCodeBench (Vals AI)87.3%Not measuredOnly DeepSeek V4 Flash 0731 measured
SWE-bench Verified (Vals AI)88.8%Not measuredOnly DeepSeek V4 Flash 0731 measured
Terminal-Bench 4 (Vals AI)18.7%Not measuredOnly DeepSeek V4 Flash 0731 measured
Vibe Code Bench (Vals AI)74.7%Not measuredOnly DeepSeek V4 Flash 0731 measured
Code migration (Vals AI)38.6%Not measuredOnly DeepSeek V4 Flash 0731 measured
ProgramBench (Vals AI)0.0%Not measuredOnly DeepSeek V4 Flash 0731 measured
IOI (Vals AI)32.7%Not measuredOnly DeepSeek V4 Flash 0731 measured
Terminal-Bench 2.1 (Vals AI)67.0%Not measuredOnly DeepSeek V4 Flash 0731 measured
SkillsBench (Vals AI)50.7%Not measuredOnly DeepSeek V4 Flash 0731 measured
CyberBench (Vals AI)72.1%Not measuredOnly DeepSeek V4 Flash 0731 measured
SciCode50.3%43.9%DeepSeek V4 Flash 0731
Terminal-Bench Hard (Artificial Analysis run)Not measured35.6%Only Step 3.7 Flash measured
FrontierCode18.8%Not measuredOnly DeepSeek V4 Flash 0731 measured
WeirdML63.0%Not measuredOnly DeepSeek V4 Flash 0731 measured
ALE-Bench1306.1694.1DeepSeek V4 Flash 0731
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for DeepSeek V4 Flash 0731 and Step 3.7 Flash
BenchmarkDeepSeek V4 Flash 0731Step 3.7 FlashLeader
AA Intelligence Index34.319.5DeepSeek V4 Flash 0731
Epoch Capabilities Index154.8Not measuredOnly DeepSeek V4 Flash 0731 measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Agentic work benchmarks for DeepSeek V4 Flash 0731 and Step 3.7 Flash
BenchmarkDeepSeek V4 Flash 0731Step 3.7 FlashLeader
AA Agentic Index41.0Not measuredOnly DeepSeek V4 Flash 0731 measured
Finance Agent (Vals AI)49.5%Not measuredOnly DeepSeek V4 Flash 0731 measured
Tax Agent Bench (Vals AI)28.1%Not measuredOnly DeepSeek V4 Flash 0731 measured
Legal Research Bench (Vals AI)30.3%Not measuredOnly DeepSeek V4 Flash 0731 measured
Excel Modeling Benchmark (Vals AI)57.0%Not measuredOnly DeepSeek V4 Flash 0731 measured
BioMysteryBench (Vals AI)64.4%Not measuredOnly DeepSeek V4 Flash 0731 measured
Terminal-Bench-Science (Vals AI)4.3%Not measuredOnly DeepSeek V4 Flash 0731 measured
τ²-Bench TelecomNot measured98.5%Only Step 3.7 Flash measured
Neither model has a result on the other 33 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
Reasoning benchmarks for DeepSeek V4 Flash 0731 and Step 3.7 Flash
BenchmarkDeepSeek V4 Flash 0731Step 3.7 FlashLeader
GPQA Diamond89.9%Not measuredOnly DeepSeek V4 Flash 0731 measured
GPQA Diamond (Artificial Analysis run)90.8%80.9%DeepSeek V4 Flash 0731
Humanity's Last Exam (Artificial Analysis run)38.6%21.4%DeepSeek V4 Flash 0731
GPQA Diamond (Epoch AI run)91.0%Not measuredOnly DeepSeek V4 Flash 0731 measured
ARC-AGI89.0%Not measuredOnly DeepSeek V4 Flash 0731 measured
ARC-AGI-261.4%Not measuredOnly DeepSeek V4 Flash 0731 measured
SimpleBench61.1%Not measuredOnly DeepSeek V4 Flash 0731 measured
Chess puzzles32.0%Not measuredOnly DeepSeek V4 Flash 0731 measured
Mystery game puzzles34.0%Not measuredOnly DeepSeek V4 Flash 0731 measured
Neither model has a result on the other 13 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
Math benchmarks for DeepSeek V4 Flash 0731 and Step 3.7 Flash
BenchmarkDeepSeek V4 Flash 0731Step 3.7 FlashLeader
OTIS Mock AIME94.4%Not measuredOnly DeepSeek V4 Flash 0731 measured
FrontierMath, tiers 1 to 357.5%Not measuredOnly DeepSeek V4 Flash 0731 measured
FrontierMath, tier 424.4%Not measuredOnly DeepSeek V4 Flash 0731 measured
ProofBench56.0%Not measuredOnly DeepSeek V4 Flash 0731 measured
Neither model has a result on the other 9 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Knowledge benchmarks for DeepSeek V4 Flash 0731 and Step 3.7 Flash
BenchmarkDeepSeek V4 Flash 0731Step 3.7 FlashLeader
MMLU Pro86.2%Not measuredOnly DeepSeek V4 Flash 0731 measured
LegalBench (Vals AI)77.7%Not measuredOnly DeepSeek V4 Flash 0731 measured
CorpFin (Vals AI)61.9%Not measuredOnly DeepSeek V4 Flash 0731 measured
TaxEval (Vals AI)70.7%Not measuredOnly DeepSeek V4 Flash 0731 measured
MedCode (Vals AI)41.4%Not measuredOnly DeepSeek V4 Flash 0731 measured
SimpleQA Verified33.6%Not measuredOnly DeepSeek V4 Flash 0731 measured
Neither model has a result on the other 12 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index71
Web design benchmarks for DeepSeek V4 Flash 0731 and Step 3.7 Flash
BenchmarkDeepSeek V4 Flash 0731Step 3.7 FlashLeader
Design Arena: websites12381196DeepSeek V4 Flash 0731
Design Arena: UI components12351179DeepSeek V4 Flash 0731
Design Arena: game dev12081158DeepSeek V4 Flash 0731
Design Arena: data viz11801172DeepSeek V4 Flash 0731
Design Arena: 3D12091129DeepSeek V4 Flash 0731
Design Arena: all code categories12301182DeepSeek V4 Flash 0731
Design Arena: SVG11851085DeepSeek V4 Flash 0731
Design Arena: ASCII art10901152Step 3.7 Flash
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index10
General benchmarks for DeepSeek V4 Flash 0731 and Step 3.7 Flash
BenchmarkDeepSeek V4 Flash 0731Step 3.7 FlashLeader
MedScribe (Vals AI)80.4%Not measuredOnly DeepSeek V4 Flash 0731 measured
IFBenchNot measured67.3%Only Step 3.7 Flash measured
Long context reasoning (AA-LCR)79.7%73.7%DeepSeek V4 Flash 0731
DTBench90.9%Not measuredOnly DeepSeek V4 Flash 0731 measured
LMCA41.7%Not measuredOnly DeepSeek V4 Flash 0731 measured
Neither model has a result on the other 41 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V4 Flash 0731 and Step 3.7 Flash
BenchmarkDeepSeek V4 Flash 0731Step 3.7 FlashLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

DeepSeek V4 Flash 0731$0.0003Fits in one request
Step 3.7 Flash$0.0008Fits in one request

DeepSeek V4 Flash 0731 costs less

Repository review

50K input + 3K output tokens

DeepSeek V4 Flash 0731$0.0078Fits in one request
Step 3.7 Flash$0.013Fits in one request

DeepSeek V4 Flash 0731 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Flash 0731$0.031Fits in one request
Step 3.7 Flash$0.051Fits in one request

DeepSeek V4 Flash 0731 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of DeepSeek V4 Flash 0731 and Step 3.7 Flash
SpecificationDeepSeek V4 Flash 0731StepFun Step 3.7 Flash
MakerDeepSeekStepFun
WeightsOpen weightsOpen weights
ReleasedJuly 31, 2026May 28, 2026
Context window1.05M262K
Input $/Mtok$0.14$0.20
Output $/Mtok$0.28$1.15
Coding index51.8Not benchmarked
Independent measurements behind it40
Cost per solved task$0.01Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Flash 0731 better than Step 3.7 Flash for coding?

Only DeepSeek V4 Flash 0731 has a coding score, 51.8 on the Vibe Coding Index; Step 3.7 Flash has none, so the two cannot be ranked on coding. Pick Step 3.7 Flash for work measured by Design Arena: ASCII art, where it leads.

Which is cheaper, DeepSeek V4 Flash 0731 or Step 3.7 Flash?

DeepSeek V4 Flash 0731 costs $0.14 per million input tokens and $0.28 per million output tokens; Step 3.7 Flash costs $0.20 and $1.15. Cost per solved task is known for DeepSeek V4 Flash 0731 only.

Which has the bigger context window, DeepSeek V4 Flash 0731 or Step 3.7 Flash?

DeepSeek V4 Flash 0731, with 1.05M tokens against 262K.

How many benchmarks is the DeepSeek V4 Flash 0731 vs Step 3.7 Flash comparison based on?

15 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Flash 0731's coding index rests on 4 independent benchmarks and Step 3.7 Flash's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next