Noometry

Model comparison

GPT-4.5 vs Inkling

Inkling is the stronger model overall, scoring 44.1 to 37.2 on the Noometry Index.

Last verified . 24 shared benchmarks.

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

Inkling Thinking Machines Lab

44.1

Rank #80 Confirmed

Summary

  • They share 24 benchmarks with published results for both. GPT-4.5 scores higher in 2 categories and Inkling in 7 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Inkling leads 40.4 to 13.9.
  • The biggest single-benchmark swing is ARC-AGI-1: 10.3% for GPT-4.5 and 79.5% for Inkling.
  • Inkling has downloadable open weights; the other is API-only.

Side by side

GPT-4.5Inkling
ProviderOpenAIThinking Machines Lab
Noometry Index37.244.1
Released2025-02-272026-07-15
WeightsProprietaryOpen
Context window—66K
Max output—66K
Input $ / M tokens—$1.87
Output $ / M tokens—$4.68
Results tracked4241

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

Category by category

Coding GPT-4.5 leads

GPT-4.5: 42.2 (#109), Inkling: 34.5 (#234)

BenchmarkGPT-4.5Inkling
WeirdML39.4%32.3%
LMArena Coding13961464
FrontierCode—14%
Aider Polyglot44.9%—
LMArena WebDev—1413
FrontierSWE—4.1%
SciCode—47%
LiveBench Coding75.2%—
ALE-Bench—946

Agentic & Tool Use Inkling leads

GPT-4.5: 27.9 (#97), Inkling: 29.6 (#85)

BenchmarkGPT-4.5Inkling
APEX-Agents—33.8%
τ²-bench Banking—25%
Cybench17.5%—

Reasoning Inkling leads

GPT-4.5: 13.9 (#330), Inkling: 40.4 (#56)

BenchmarkGPT-4.5Inkling
ARC-AGI-20.8%36.5%
SimpleBench34.5%50%
ARC-AGI-110.3%79.5%
LMArena Hard Prompts14031451
Epoch Capabilities Index136.74148.54
CritPt—5.4%
Chess Puzzles—21%
EnigmaEval3.2%—
LiveBench Reasoning71.1%—
DTBench—87.5%
LiveBench Data Analysis64.3%—
LMCA—37.6%
ForecastBench61.7—
LiveBench69%—

Math GPT-4.5 leads

GPT-4.5: 32.6 (#211), Inkling: 31.3 (#225)

BenchmarkGPT-4.5Inkling
OTIS Mock AIME 2024-202537.8%88.9%
LMArena Math14121479
FrontierMath (Tiers 1-3)—33.3%
FrontierMath Tier 4—4.9%
ProofBench—0%
LiveBench Math69.3%—
MATH Level 578.6%—

Knowledge Inkling leads

GPT-4.5: 32.5 (#211), Inkling: 55.1 (#49)

BenchmarkGPT-4.5Inkling
GPQA Diamond68.7%88.3%
LMArena Expert13941465
Humanity's Last Exam5.4%—
SimpleQA Verified—40.3%
Confabulations13.6%—

Multimodal Not comparable

GPT-4.5: 37.6 (#71), Inkling: —

BenchmarkGPT-4.5Inkling
LMArena Vision1195—
VPCT45%—

Multilingual Inkling leads

GPT-4.5: 52.5 (#83), Inkling: 54.0 (#52)

BenchmarkGPT-4.5Inkling
LMArena Non-English14131434
LMArena Chinese14211490
LMArena French14181458
LMArena German14571446
LMArena Japanese14161429
LMArena Korean13921404
LMArena Russian14191429
LMArena Spanish—1448

Instruction Following Inkling leads

GPT-4.5: 72.6 (#134), Inkling: 75.1 (#71)

BenchmarkGPT-4.5Inkling
LMArena Instruction Following14041426
LiveBench Instruction Following72.3%—

Long Context Inkling leads

GPT-4.5: 40.4 (#155), Inkling: 43.8 (#86)

BenchmarkGPT-4.5Inkling
LMArena Longer Query14061434
Fiction.LiveBench63.9%—

Writing & Preference Inkling leads

GPT-4.5: 56.9 (#134), Inkling: 65.2 (#51)

BenchmarkGPT-4.5Inkling
LMArena Text14171441
LMArena Creative Writing13941387
EQ-Bench Creative Writing12581611
LMArena Multi-Turn14441436
Short-Story Creative Writing75.6%—
EQ-Bench 4—1226
LiveBench Language61.5%—

Frequently asked questions

Is GPT-4.5 better than Inkling?

Inkling is the stronger model overall, scoring 44.1 to 37.2 on the Noometry Index.

Is GPT-4.5 or Inkling better for coding?

GPT-4.5 scores higher on coding benchmarks: 42.2 versus 34.5 in the Noometry coding category.

How many benchmarks do GPT-4.5 and Inkling share?

24 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Inkling has 41.

Related comparisons

Go deeper