Noometry

Model comparison

GPT-5.5 Instant vs Inkling-Small

Inkling-Small is the stronger model overall, scoring 46.5 to 42.5 on the Noometry Index.

Last verified . 26 shared benchmarks.

GPT-5.5 Instant OpenAI

42.5

Rank #99 Confirmed

Inkling-Small Thinking Machines Lab

46.5

Rank #57 Confirmed

Summary

  • They share 26 benchmarks with published results for both. GPT-5.5 Instant scores higher in 7 categories and Inkling-Small in 2 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in math, where Inkling-Small leads 44.9 to 26.1.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 68.1% for GPT-5.5 Instant and 90% for Inkling-Small.
  • Inkling-Small has downloadable open weights; the other is API-only.

Side by side

GPT-5.5 InstantInkling-Small
ProviderOpenAIThinking Machines Lab
Noometry Index42.546.5
Released2026-05-052026-07-15
WeightsProprietaryOpen
Context window—524K
Max output—1.05M
Input $ / M tokens—$0.45
Output $ / M tokens—$1.20
Results tracked2733

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

Category by category

Coding Too close to call

GPT-5.5 Instant: 43.7 (#73), Inkling-Small: 43.3 (#80)

BenchmarkGPT-5.5 InstantInkling-Small
SciCode48.6%48.7%
LMArena Coding14331451
LMArena WebDev—1408

Reasoning Inkling-Small leads

GPT-5.5 Instant: 24.2 (#149), Inkling-Small: 39.0 (#53)

BenchmarkGPT-5.5 InstantInkling-Small
CritPt0%8.3%
Chess Puzzles12%18%
LMArena Hard Prompts14261424
Epoch Capabilities Index142.48150.13
ARC-AGI-2—40.1%
ARC-AGI-1—84%
Mystery Game Puzzles—6%

Math Inkling-Small leads

GPT-5.5 Instant: 26.1 (#241), Inkling-Small: 44.9 (#65)

BenchmarkGPT-5.5 InstantInkling-Small
FrontierMath (Tiers 1-3)26.3%46.3%
FrontierMath Tier 42.4%17.1%
OTIS Mock AIME 2024-202568.1%90%
LMArena Math14201453
ProofBench—6%

Knowledge Too close to call

GPT-5.5 Instant: 48.9 (#68), Inkling-Small: 48.3 (#71)

BenchmarkGPT-5.5 InstantInkling-Small
GPQA Diamond82.5%88.5%
LMArena Expert14091442
SimpleQA Verified—19.1%

Multimodal Too close to call

GPT-5.5 Instant: 39.3 (#48), Inkling-Small: 38.4 (#59)

BenchmarkGPT-5.5 InstantInkling-Small
LMArena Vision12501235
LMArena Document1403—

Multilingual GPT-5.5 Instant leads

GPT-5.5 Instant: 53.0 (#76), Inkling-Small: 51.7 (#102)

BenchmarkGPT-5.5 InstantInkling-Small
LMArena Non-English14171400
LMArena Chinese14571458
LMArena French14281438
LMArena German14101412
LMArena Japanese14081399
LMArena Korean13931355
LMArena Russian14301392
LMArena Spanish14301426

Instruction Following Too close to call

GPT-5.5 Instant: 74.4 (#94), Inkling-Small: 73.9 (#112)

BenchmarkGPT-5.5 InstantInkling-Small
LMArena Instruction Following14071397

Long Context Too close to call

GPT-5.5 Instant: 43.4 (#92), Inkling-Small: 42.7 (#113)

BenchmarkGPT-5.5 InstantInkling-Small
LMArena Longer Query14221401

Writing & Preference GPT-5.5 Instant leads

GPT-5.5 Instant: 62.0 (#81), Inkling-Small: 59.8 (#102)

BenchmarkGPT-5.5 InstantInkling-Small
LMArena Text14191413
LMArena Creative Writing14201330
LMArena Multi-Turn14341420
EQ-Bench Creative Writing—1491

Frequently asked questions

Is GPT-5.5 Instant better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 42.5 on the Noometry Index.

Is GPT-5.5 Instant or Inkling-Small better for coding?

They score almost the same on coding (43.7 vs 43.3); test both on your own repository before choosing.

How many benchmarks do GPT-5.5 Instant and Inkling-Small share?

26 benchmarks have published results for both models. GPT-5.5 Instant has 27 scored results on Noometry and Inkling-Small has 33.

Related comparisons

Go deeper