Noometry

Model comparison

Grok-2 (Dec 2024) vs Inkling-Small

Inkling-Small is the stronger model overall, scoring 46.5 to 33.7 on the Noometry Index.

Last verified . 20 shared benchmarks.

Grok-2 (Dec 2024) xAI

33.7

Rank #239 Confirmed

Inkling-Small Thinking Machines Lab

46.5

Rank #63 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 0 categories and Inkling-Small in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Inkling-Small leads 45.1 to 20.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 11.5% for Grok-2 (Dec 2024) and 90% for Inkling-Small.
  • Inkling-Small has downloadable open weights; the other is API-only.

Side by side

Grok-2 (Dec 2024)Inkling-Small
ProviderxAIThinking Machines Lab
Noometry Index33.746.5
Released2024-08-132026-07-15
WeightsProprietaryOpen
Context window—524K
Max output—1.05M
Input $ / M tokens—$0.45
Output $ / M tokens—$1.20
Results tracked3433

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

Category by category

Coding Inkling-Small leads

Grok-2 (Dec 2024): 33.3 (#258), Inkling-Small: 43.6 (#85)

BenchmarkGrok-2 (Dec 2024)Inkling-Small
LMArena Coding12871451
LMArena WebDev—1409
SciCode—48.7%
WeirdML22.2%—
LiveBench Coding46.4%—

Reasoning Inkling-Small leads

Grok-2 (Dec 2024): 16.9 (#299), Inkling-Small: 38.6 (#63)

BenchmarkGrok-2 (Dec 2024)Inkling-Small
LMArena Hard Prompts12721423
Epoch Capabilities Index130.48150.15
ARC-AGI-2—40.1%
SimpleBench22.7%—
ARC-AGI-1—84%
CritPt—8.3%
Chess Puzzles—18%
LiveBench Reasoning54.8%—
Mystery Game Puzzles—6%
DTBench65.2%—
LiveBench Data Analysis54.5%—
LiveBench54.3%—

Math Inkling-Small leads

Grok-2 (Dec 2024): 20.8 (#284), Inkling-Small: 45.1 (#77)

BenchmarkGrok-2 (Dec 2024)Inkling-Small
OTIS Mock AIME 2024-202511.5%90%
LMArena Math12831459
FrontierMath (Tiers 1-3)—46.3%
FrontierMath Tier 4—17.1%
ProofBench—6%
LiveBench Math54.9%—
MATH Level 563.5%—
FrontierMath (Feb 2025 set)0.7%—

Knowledge Inkling-Small leads

Grok-2 (Dec 2024): 29.8 (#233), Inkling-Small: 48.2 (#77)

BenchmarkGrok-2 (Dec 2024)Inkling-Small
GPQA Diamond53.8%88.5%
LMArena Expert12541442
SimpleQA Verified—19.1%
Confabulations20.1%—

Multimodal Not comparable

Grok-2 (Dec 2024): —, Inkling-Small: 39.1 (#62)

BenchmarkGrok-2 (Dec 2024)Inkling-Small
LMArena Vision—1235

Multilingual Inkling-Small leads

Grok-2 (Dec 2024): 43.1 (#188), Inkling-Small: 51.7 (#104)

BenchmarkGrok-2 (Dec 2024)Inkling-Small
LMArena Non-English12821402
LMArena Chinese12891465
LMArena French13181436
LMArena German12871405
LMArena Japanese12441405
LMArena Korean12371363
LMArena Russian12861391
LMArena Spanish12811428

Instruction Following Inkling-Small leads

Grok-2 (Dec 2024): 66.9 (#202), Inkling-Small: 73.8 (#114)

BenchmarkGrok-2 (Dec 2024)Inkling-Small
LMArena Instruction Following12701399
LiveBench Instruction Following69.6%—

Long Context Inkling-Small leads

Grok-2 (Dec 2024): 38.8 (#190), Inkling-Small: 42.7 (#118)

BenchmarkGrok-2 (Dec 2024)Inkling-Small
LMArena Longer Query12761401

Writing & Preference Inkling-Small leads

Grok-2 (Dec 2024): 48.6 (#198), Inkling-Small: 59.6 (#107)

BenchmarkGrok-2 (Dec 2024)Inkling-Small
LMArena Text13051414
LMArena Creative Writing12841331
LMArena Multi-Turn12901418
Short-Story Creative Writing63.6%—
EQ-Bench Creative Writing—1491
LiveBench Language45.6%—

Frequently asked questions

Is Grok-2 (Dec 2024) better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 33.7 on the Noometry Index.

Is Grok-2 (Dec 2024) or Inkling-Small better for coding?

Inkling-Small scores higher on coding benchmarks: 43.6 versus 33.3 in the Noometry coding category.

How many benchmarks do Grok-2 (Dec 2024) and Inkling-Small share?

20 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Inkling-Small has 33.

Related comparisons

Go deeper