Noometry

Model comparison

GPT-4.1 mini vs Inkling-Small

Inkling-Small is the stronger model overall, scoring 46.5 to 33.5 on the Noometry Index.

Last verified . 30 shared benchmarks.

GPT-4.1 mini OpenAI

33.5

Rank #232 Confirmed

Inkling-Small Thinking Machines Lab

46.5

Rank #57 Confirmed

Summary

  • They share 30 benchmarks with published results for both. GPT-4.1 mini scores higher in 0 categories and Inkling-Small in 9 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Inkling-Small leads 39.0 to 10.9.
  • The biggest single-benchmark swing is ARC-AGI-1: 3.5% for GPT-4.1 mini and 84% for Inkling-Small.
  • Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $0.40 / $1.60 for GPT-4.1 mini.
  • GPT-4.1 mini accepts more context: 1.05M tokens versus 524K.
  • Inkling-Small has downloadable open weights; the other is API-only.

Side by side

GPT-4.1 miniInkling-Small
ProviderOpenAIThinking Machines Lab
Noometry Index33.546.5
Released2025-04-142026-07-15
WeightsProprietaryOpen
Context window1.05M524K
Max output33K1.05M
Input $ / M tokens$0.40$0.45
Output $ / M tokens$1.60$1.20
Results tracked4733

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

Category by category

Coding Inkling-Small leads

GPT-4.1 mini: 30.4 (#286), Inkling-Small: 43.3 (#80)

BenchmarkGPT-4.1 miniInkling-Small
SciCode40.4%48.7%
LMArena Coding13671451
SWE-bench Verified (bash only)23.9%—
Aider Polyglot32.4%—
LMArena WebDev—1408
WeirdML37.6%—
BigCodeBench Instruct48.9%—
CadEval16%—

Agentic & Tool Use Not comparable

GPT-4.1 mini: 33.0 (#52), Inkling-Small: —

BenchmarkGPT-4.1 miniInkling-Small
Berkeley Function Calling Leaderboard50.5%—

Reasoning Inkling-Small leads

GPT-4.1 mini: 10.9 (#335), Inkling-Small: 39.0 (#53)

BenchmarkGPT-4.1 miniInkling-Small
ARC-AGI-20%40.1%
ARC-AGI-13.5%84%
CritPt0%8.3%
Chess Puzzles7%18%
LMArena Hard Prompts13491424
Mystery Game Puzzles7%6%
Epoch Capabilities Index135.01150.13
Kagi LLM Benchmark48.6%—
DTBench68.8%—
LMCA21.1%—

Math Inkling-Small leads

GPT-4.1 mini: 23.1 (#264), Inkling-Small: 44.9 (#65)

BenchmarkGPT-4.1 miniInkling-Small
FrontierMath (Tiers 1-3)6.7%46.3%
OTIS Mock AIME 2024-202544.7%90%
LMArena Math13431453
FrontierMath Tier 4—17.1%
ProofBench—6%
Omni-MATH49.1%—
MATH Level 587.3%—
FrontierMath (Feb 2025 set)4.5%—

Knowledge Inkling-Small leads

GPT-4.1 mini: 34.7 (#183), Inkling-Small: 48.3 (#71)

BenchmarkGPT-4.1 miniInkling-Small
GPQA Diamond65.8%88.5%
SimpleQA Verified12.7%19.1%
LMArena Expert13381442
MMLU-Pro78.3%—
GPQA (HELM)61.4%—

Multimodal Inkling-Small leads

GPT-4.1 mini: 35.2 (#77), Inkling-Small: 38.4 (#59)

BenchmarkGPT-4.1 miniInkling-Small
LMArena Vision11811235

Multilingual Inkling-Small leads

GPT-4.1 mini: 45.9 (#161), Inkling-Small: 51.7 (#102)

BenchmarkGPT-4.1 miniInkling-Small
LMArena Non-English13181400
LMArena Chinese13291458
LMArena French13571438
LMArena German13491412
LMArena Japanese12911399
LMArena Korean12981355
LMArena Russian13241392
LMArena Spanish13191426

Instruction Following Too close to call

GPT-4.1 mini: 73.9 (#113), Inkling-Small: 73.9 (#112)

BenchmarkGPT-4.1 miniInkling-Small
LMArena Instruction Following13321397
IFEval90.4%—

Long Context Inkling-Small leads

GPT-4.1 mini: 31.8 (#270), Inkling-Small: 42.7 (#113)

BenchmarkGPT-4.1 miniInkling-Small
LMArena Longer Query13441401
Fiction.LiveBench44.4%—

Writing & Preference Inkling-Small leads

GPT-4.1 mini: 48.8 (#193), Inkling-Small: 59.8 (#102)

BenchmarkGPT-4.1 miniInkling-Small
LMArena Text13411413
LMArena Creative Writing13001330
EQ-Bench Creative Writing11471491
LMArena Multi-Turn13541420
WildBench83.8%—

Frequently asked questions

Is GPT-4.1 mini better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 33.5 on the Noometry Index.

Which is cheaper, GPT-4.1 mini or Inkling-Small?

Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; GPT-4.1 mini lists at $0.40 and $1.60.

Is GPT-4.1 mini or Inkling-Small better for coding?

Inkling-Small scores higher on coding benchmarks: 43.3 versus 30.4 in the Noometry coding category.

Which has the bigger context window?

GPT-4.1 mini does, with 1.05M tokens against 524K.

How many benchmarks do GPT-4.1 mini and Inkling-Small share?

30 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Inkling-Small has 33.

Related comparisons

Go deeper