Noometry

Model comparison

Grok 4 vs Inkling-Small

Grok 4 is the stronger model overall, scoring 48.1 to 46.5 on the Noometry Index.

Last verified . 24 shared benchmarks.

Grok 4 xAI

48.1

Rank #56 Confirmed

Inkling-Small Thinking Machines Lab

46.5

Rank #63 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Grok 4 scores higher in 6 categories and Inkling-Small in 3 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Grok 4 leads 63.1 to 42.7.
  • The biggest single-benchmark swing is ARC-AGI-2: 16% for Grok 4 and 40.1% for Inkling-Small.
  • Inkling-Small has downloadable open weights; the other is API-only.

Side by side

Grok 4Inkling-Small
ProviderxAIThinking Machines Lab
Noometry Index48.146.5
Released2025-07-092026-07-15
WeightsProprietaryOpen
Context window—524K
Max output—1.05M
Input $ / M tokens—$0.45
Output $ / M tokens—$1.20
Results tracked4833

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

Category by category

Coding Grok 4 leads

Grok 4: 50.3 (#46), Inkling-Small: 43.6 (#85)

BenchmarkGrok 4Inkling-Small
LMArena Coding14081451
Aider Polyglot79.6%—
LMArena WebDev—1409
SciCode—48.7%
WeirdML45.7%—

Agentic & Tool Use Not comparable

Grok 4: 32.3 (#68), Inkling-Small: —

BenchmarkGrok 4Inkling-Small
Terminal-Bench27.2%—
Berkeley Function Calling Leaderboard63%—
GDPval21.1%—
Cybench43%—
DeepResearch Bench47.3%—
BALROG43.6%—
LMArena Search1142—
METR Time Horizons66.6%—

Reasoning Inkling-Small leads

Grok 4: 36.7 (#65), Inkling-Small: 38.6 (#63)

BenchmarkGrok 4Inkling-Small
ARC-AGI-216%40.1%
ARC-AGI-166.7%84%
Chess Puzzles28%18%
LMArena Hard Prompts14091423
Epoch Capabilities Index146.44150.15
SimpleBench60.5%—
Kagi LLM Benchmark73.6%—
CritPt—8.3%
Mystery Game Puzzles—6%
ForecastBench60.9—

Math Grok 4 leads

Grok 4: 48.4 (#64), Inkling-Small: 45.1 (#77)

BenchmarkGrok 4Inkling-Small
OTIS Mock AIME 2024-202584%90%
LMArena Math14221459
FrontierMath (Tiers 1-3)—46.3%
FrontierMath Tier 4—17.1%
ProofBench—6%
Omni-MATH60.3%—
FrontierMath (Feb 2025 set)19.7%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge Grok 4 leads

Grok 4: 53.8 (#55), Inkling-Small: 48.2 (#77)

BenchmarkGrok 4Inkling-Small
GPQA Diamond87%88.5%
LMArena Expert14151442
SimpleQA Verified—19.1%
MMLU-Pro85.1%—
Confabulations12.4%—
GPQA (HELM)72.7%—

Multimodal Inkling-Small leads

Grok 4: 33.7 (#94), Inkling-Small: 39.1 (#62)

BenchmarkGrok 4Inkling-Small
LMArena Vision12101235
GeoBench45%—

Multilingual Too close to call

Grok 4: 51.8 (#103), Inkling-Small: 51.7 (#104)

BenchmarkGrok 4Inkling-Small
LMArena Non-English14031402
LMArena Chinese14271465
LMArena French14181436
LMArena German14291405
LMArena Japanese13941405
LMArena Korean13771363
LMArena Russian14101391
LMArena Spanish14201428

Instruction Following Grok 4 leads

Grok 4: 79.2 (#5), Inkling-Small: 73.8 (#114)

BenchmarkGrok 4Inkling-Small
LMArena Instruction Following13871399
IFEval94.9%—

Long Context Grok 4 leads

Grok 4: 63.1 (#4), Inkling-Small: 42.7 (#118)

BenchmarkGrok 4Inkling-Small
LMArena Longer Query14091401
Fiction.LiveBench94.4%—

Writing & Preference Inkling-Small leads

Grok 4: 58.5 (#116), Inkling-Small: 59.6 (#107)

BenchmarkGrok 4Inkling-Small
LMArena Text14111414
LMArena Creative Writing13971331
LMArena Multi-Turn14161418
Short-Story Creative Writing76.9%—
EQ-Bench Creative Writing—1491
WildBench79.7%—

Frequently asked questions

Is Grok 4 better than Inkling-Small?

Grok 4 is the stronger model overall, scoring 48.1 to 46.5 on the Noometry Index.

Is Grok 4 or Inkling-Small better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 43.6 in the Noometry coding category.

How many benchmarks do Grok 4 and Inkling-Small share?

24 benchmarks have published results for both models. Grok 4 has 48 scored results on Noometry and Inkling-Small has 33.

Related comparisons

Go deeper