Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

DeepSeek-V4.1-Flash vs Inkling 2 Mini

DeepSeek · released

Wins 4 of 5 areas

Coding · Agents · Images and charts · Long documents

Thinking Machines · released

Wins 0 of 5 areas

—

DeepSeek-V4.1-Flash is the stronger all-rounder.Inkling 2 Mini is cheaper.

Scores updated · 19 tests both models report · How we compare

Where each one wins

Tests won in each of the five 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.

Coding, agents, images and charts and long documents 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-V4.1-Flash$0.30 to read · $1.20 to write$1.50Price from Artificial Analysis
Inkling 2 Mini$0.15 to read · $0.50 to write$0.65Price from Artificial Analysis

Inkling 2 Mini costs 57% 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-V4.1-Flash pulls ahead

  • Abstract visual puzzles that people can solveARC-AGI-2+28.8points aheadDeepSeek-V4.1-Flash78.1Inkling 2 Mini49.3
  • Complex command-line tasks across many fieldsTerminal-Bench 4.0+28.2points aheadDeepSeek-V4.1-Flash33.8Inkling 2 Mini5.6
  • Command-line tasks in a real terminalTerminal-Bench 2.1+19points aheadDeepSeek-V4.1-Flash90.6Inkling 2 Mini71.6

Where Inkling 2 Mini pulls ahead

  • Research-level physics problemsCritPt+7.4points aheadInkling 2 Mini31.4DeepSeek-V4.1-Flash24

Every test, side by side

All 19 tests both models report. The winning score is in its model's colour; marks a score checked independently.

CodingDeepSeek-V4.1-Flash

Full coding ranking

AgentsDeepSeek-V4.1-Flash
  • Terminal-Bench 4.0DeepSeek-V4.1-Flash by 28.233.85.6+28.2

Full agents ranking

ReasoningEven
  • ARC-AGI-2DeepSeek-V4.1-Flash by 28.878.149.3+28.8
  • CritPtInkling 2 Mini by 7.42431.4+7.4

Full reasoning ranking

Images and chartsDeepSeek-V4.1-Flash
  • MMMU-ProDeepSeek-V4.1-Flash by 5.780.674.9+5.7

Full images and charts ranking

Long documentsDeepSeek-V4.1-Flash

Full long documents ranking

Other results13 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.

  • GDPval-AA 2.1DeepSeek-V4.1-Flash by 427 rating points17461319+427 rating
  • ZeroBenchDeepSeek-V4.1-Flash by 324917+32
  • DeepSWE 1.1DeepSeek-V4.1-Flash by 2674.248.2+26
  • Terminal-Bench 4.0DeepSeek-V4.1-Flash by 25.631.25.6+25.6
  • CritPt v2 FullDeepSeek-V4.1-Flash by 19.250.631.4+19.2
  • JobBenchDeepSeek-V4.1-Flash by 18.968.549.6+18.9
  • Vals Finance IndexDeepSeek-V4.1-Flash by 10.860.950.1+10.8
  • HLE-DiamondDeepSeek-V4.1-Flash by 10.125.315.2+10.1
  • ARC-AGI-1DeepSeek-V4.1-Flash by 993.584.5+9
  • CritPt v2 HardDeepSeek-V4.1-Flash by 82517+8
  • SWEBench Pro v2 (Hard)DeepSeek-V4.1-Flash by 4.582.477.9+4.5
  • Chartography originalInkling 2 Mini by 4.217.922.1+4.2
  • GDP (Surge AI)tie17.216.8tie

Questions people ask

Which is better, DeepSeek-V4.1-Flash or Inkling 2 Mini?

DeepSeek-V4.1-Flash wins four of the five areas where both have results: coding, agents, images and charts and long documents. Inkling 2 Mini wins none, but costs 57% less. They are level on reasoning.

Which is better for coding?

DeepSeek-V4.1-Flash. It wins the one coding test both models report.

Which is cheaper?

DeepSeek-V4.1-Flash costs $0.30 per million input tokens and $1.20 per million output tokens; Inkling 2 Mini costs $0.15 and $0.50. That makes Inkling 2 Mini about 57% cheaper for the same work.

How do you compare the two?

We use the 19 benchmark tests both models have published scores on. The verdict counts the 6 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 13 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.