Noometry

Model comparison

DeepSeek V4.1 Flash vs Inkling

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 44.1 on the Noometry Index.

Last verified . 31 shared benchmarks.

DeepSeek V4.1 Flash DeepSeek

52.8

Rank #38 Confirmed

Inkling Thinking Machines Lab

44.1

Rank #80 Confirmed

Summary

  • They share 31 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 9 categories and Inkling in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 31.3.
  • The biggest single-benchmark swing is ProofBench: 54% for DeepSeek V4.1 Flash and 0% for Inkling.
  • DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.87 / $4.68 for Inkling.
  • DeepSeek V4.1 Flash accepts more context: 1M tokens versus 66K.

Side by side

DeepSeek V4.1 FlashInkling
ProviderDeepSeekThinking Machines Lab
Noometry Index52.844.1
Released2026-09-092026-07-15
WeightsOpenOpen
Context window1M66K
Max output393K66K
Input $ / M tokens$0.15$1.87
Output $ / M tokens$0.60$4.68
Results tracked3741

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), Inkling: 34.5 (#234)

BenchmarkDeepSeek V4.1 FlashInkling
LMArena WebDev16191413
SciCode51.9%47%
LMArena Coding15061464
ALE-Bench1,092946
FrontierCode—14%
FrontierSWE—4.1%
WeirdML—32.3%

Agentic & Tool Use DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 31.2 (#69), Inkling: 29.6 (#85)

BenchmarkDeepSeek V4.1 FlashInkling
APEX-Agents39.5%33.8%
τ²-bench Banking—25%
GDP.pdf19.8%—

Reasoning DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 50.2 (#36), Inkling: 40.4 (#56)

BenchmarkDeepSeek V4.1 FlashInkling
CritPt14.3%5.4%
LMArena Hard Prompts14831451
DTBench89.9%87.5%
LMCA47%37.6%
Epoch Capabilities Index154.9148.54
ARC-AGI-2—36.5%
SimpleBench—50%
NYT Connections (extended)89.6%—
ARC-AGI-1—79.5%
Chess Puzzles—21%
Mystery Game Puzzles43%—
Surface Evolver Bench46.3%—

Math DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 66.7 (#25), Inkling: 31.3 (#225)

BenchmarkDeepSeek V4.1 FlashInkling
FrontierMath (Tiers 1-3)67.4%33.3%
FrontierMath Tier 426.8%4.9%
OTIS Mock AIME 2024-202598.3%88.9%
ProofBench54%0%
LMArena Math14771479

Knowledge DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 57.9 (#38), Inkling: 55.1 (#49)

BenchmarkDeepSeek V4.1 FlashInkling
GPQA Diamond89.8%88.3%
LMArena Expert15061465
SimpleQA Verified—40.3%

Multimodal Not comparable

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

BenchmarkDeepSeek V4.1 FlashInkling
LMArena Vision1277—
Furniture Assembly34.2%—

Multilingual DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 55.0 (#35), Inkling: 54.0 (#52)

BenchmarkDeepSeek V4.1 FlashInkling
LMArena Non-English14481434
LMArena Chinese14971490
LMArena French14521458
LMArena German14841446
LMArena Japanese14121429
LMArena Korean14521404
LMArena Russian14711429
LMArena Spanish14591448

Instruction Following DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 77.3 (#26), Inkling: 75.1 (#71)

BenchmarkDeepSeek V4.1 FlashInkling
LMArena Instruction Following14741426

Long Context DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 45.2 (#47), Inkling: 43.8 (#86)

BenchmarkDeepSeek V4.1 FlashInkling
LMArena Longer Query14751434

Writing & Preference Too close to call

DeepSeek V4.1 Flash: 65.4 (#48), Inkling: 65.2 (#51)

BenchmarkDeepSeek V4.1 FlashInkling
LMArena Text14621441
LMArena Creative Writing14351387
EQ-Bench Creative Writing15401611
LMArena Multi-Turn14571436
EQ-Bench 4—1226

Frequently asked questions

Is DeepSeek V4.1 Flash better than Inkling?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 44.1 on the Noometry Index.

Which is cheaper, DeepSeek V4.1 Flash or Inkling?

DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Inkling lists at $1.87 and $4.68.

Is DeepSeek V4.1 Flash or Inkling better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 34.5 in the Noometry coding category.

Which has the bigger context window?

DeepSeek V4.1 Flash does, with 1M tokens against 66K.

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

31 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Inkling has 41.

Related comparisons

Go deeper