Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d272Policy30d66, 14 pendingSources1,015

DeepSeek-V4-Flash vs Step 3.7 Flash

DeepSeek · released

Wins 6 of 7 areas

Coding · Agents · Reasoning · Math · Long documents · Following instructions

StepFun · released

Wins 0 of 7 areas

—

DeepSeek-V4-Flash is the stronger all-rounder.Step 3.7 Flash is cheaper.

Scores updated · 21 tests both models report · How we compare

Where each one wins

Tests won in each of the seven areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.

Long documents and following instructions rest on a single test each.

What it costs

Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.

DeepSeek-V4-Flash$0.44 to read · $1.32 to write$1.76Price from Artificial Analysis
Step 3.7 Flash$0.20 to read · $1.15 to write$1.35Price from Artificial Analysis

Step 3.7 Flash costs 23% less for the same work.

The biggest differences

The tests each model wins by the widest margin, up to three each. Scores are out of 100.

Where DeepSeek-V4-Flash pulls ahead

  • Command-line tasks in a real terminalTerminal-Bench 2.1+39.4points aheadDeepSeek-V4-Flash78.7Step 3.7 Flash39.3
  • Real work tasks from 44 professionsGDPVal+28.9points aheadDeepSeek-V4-Flash46.9Step 3.7 Flash18
  • Customer-service tasks in a simulated bankτ-Bench V3 · Banking+27.4points aheadDeepSeek-V4-Flash39.4Step 3.7 Flash12

Where Step 3.7 Flash pulls ahead

  • Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+6.7points aheadStep 3.7 Flash15DeepSeek-V4-Flash8.3
  • Long, multi-file coding tasks in real codebasesSWE-bench Pro+3.7points aheadStep 3.7 Flash56.3DeepSeek-V4-Flash52.6

Every test, side by side

All 21 tests both models report. The winning score is in its model's colour; marks a score checked independently.

CodingDeepSeek-V4-Flash

Full coding ranking

AgentsDeepSeek-V4-Flash

Full agents ranking

ReasoningDeepSeek-V4-Flash

Full reasoning ranking

FactsEven

Full facts ranking

MathDeepSeek-V4-Flash

Full math ranking

Long documentsDeepSeek-V4-Flash
  • AA-LCRDeepSeek-V4-Flash by 679.773.7+6

Full long documents ranking

Following instructionsDeepSeek-V4-Flash
  • IFBenchDeepSeek-V4-Flash by 11.979.267.3+11.9

Full following instructions ranking

Other results5 tests, not counted

Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.

Questions people ask

Which is better, DeepSeek-V4-Flash or Step 3.7 Flash?

DeepSeek-V4-Flash wins six of the seven areas where both have results: coding, agents, reasoning, math, long documents and following instructions. Step 3.7 Flash wins none, but costs 23% less. They are level on facts.

Which is better for coding?

DeepSeek-V4-Flash. It wins 2 of the 4 coding tests both models report; Step 3.7 Flash wins 1, and 1 is a tie.

Which is cheaper?

DeepSeek-V4-Flash costs $0.44 per million input tokens and $1.32 per million output tokens; Step 3.7 Flash costs $0.20 and $1.15. That makes Step 3.7 Flash about 23% cheaper for the same work.

How do you compare the two?

We use the 21 benchmark tests both models have published scores on. The verdict counts the 16 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 5 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.

Compare DeepSeek-V4-Flash with

DeepSeek

Across the field

All comparisons