Noometry

Model comparison

Grok-2 (Dec 2024) vs Inkling

Inkling is the stronger model overall, scoring 44.1 to 33.7 on the Noometry Index.

Last verified . 23 shared benchmarks.

Grok-2 (Dec 2024) xAI

33.7

Rank #239 Confirmed

Inkling Thinking Machines Lab

44.1

Rank #80 Confirmed

Summary

  • They share 23 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 0 categories and Inkling in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Inkling leads 55.1 to 29.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 11.5% for Grok-2 (Dec 2024) and 88.9% for Inkling.
  • Inkling has downloadable open weights; the other is API-only.

Side by side

Grok-2 (Dec 2024)Inkling
ProviderxAIThinking Machines Lab
Noometry Index33.744.1
Released2024-08-132026-07-15
WeightsProprietaryOpen
Context window—66K
Max output—66K
Input $ / M tokens—$1.87
Output $ / M tokens—$4.68
Results tracked3441

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

Category by category

Coding Inkling leads

Grok-2 (Dec 2024): 33.3 (#258), Inkling: 34.5 (#234)

BenchmarkGrok-2 (Dec 2024)Inkling
WeirdML22.2%32.3%
LMArena Coding12871464
FrontierCode—14%
LMArena WebDev—1413
FrontierSWE—4.1%
SciCode—47%
LiveBench Coding46.4%—
ALE-Bench—946

Agentic & Tool Use Not comparable

Grok-2 (Dec 2024): —, Inkling: 29.6 (#85)

BenchmarkGrok-2 (Dec 2024)Inkling
APEX-Agents—33.8%
τ²-bench Banking—25%

Reasoning Inkling leads

Grok-2 (Dec 2024): 16.9 (#299), Inkling: 40.4 (#56)

BenchmarkGrok-2 (Dec 2024)Inkling
SimpleBench22.7%50%
LMArena Hard Prompts12721451
DTBench65.2%87.5%
Epoch Capabilities Index130.48148.54
ARC-AGI-2—36.5%
ARC-AGI-1—79.5%
CritPt—5.4%
Chess Puzzles—21%
LiveBench Reasoning54.8%—
LiveBench Data Analysis54.5%—
LMCA—37.6%
LiveBench54.3%—

Math Inkling leads

Grok-2 (Dec 2024): 20.8 (#284), Inkling: 31.3 (#225)

BenchmarkGrok-2 (Dec 2024)Inkling
OTIS Mock AIME 2024-202511.5%88.9%
LMArena Math12831479
FrontierMath (Tiers 1-3)—33.3%
FrontierMath Tier 4—4.9%
ProofBench—0%
LiveBench Math54.9%—
MATH Level 563.5%—
FrontierMath (Feb 2025 set)0.7%—

Knowledge Inkling leads

Grok-2 (Dec 2024): 29.8 (#233), Inkling: 55.1 (#49)

BenchmarkGrok-2 (Dec 2024)Inkling
GPQA Diamond53.8%88.3%
LMArena Expert12541465
SimpleQA Verified—40.3%
Confabulations20.1%—

Multilingual Inkling leads

Grok-2 (Dec 2024): 43.1 (#188), Inkling: 54.0 (#52)

BenchmarkGrok-2 (Dec 2024)Inkling
LMArena Non-English12821434
LMArena Chinese12891490
LMArena French13181458
LMArena German12871446
LMArena Japanese12441429
LMArena Korean12371404
LMArena Russian12861429
LMArena Spanish12811448

Instruction Following Inkling leads

Grok-2 (Dec 2024): 66.9 (#202), Inkling: 75.1 (#71)

BenchmarkGrok-2 (Dec 2024)Inkling
LMArena Instruction Following12701426
LiveBench Instruction Following69.6%—

Long Context Inkling leads

Grok-2 (Dec 2024): 38.8 (#190), Inkling: 43.8 (#86)

BenchmarkGrok-2 (Dec 2024)Inkling
LMArena Longer Query12761434

Writing & Preference Inkling leads

Grok-2 (Dec 2024): 48.6 (#198), Inkling: 65.2 (#51)

BenchmarkGrok-2 (Dec 2024)Inkling
LMArena Text13051441
LMArena Creative Writing12841387
LMArena Multi-Turn12901436
Short-Story Creative Writing63.6%—
EQ-Bench Creative Writing—1611
EQ-Bench 4—1226
LiveBench Language45.6%—

Frequently asked questions

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

Inkling is the stronger model overall, scoring 44.1 to 33.7 on the Noometry Index.

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

Inkling scores higher on coding benchmarks: 34.5 versus 33.3 in the Noometry coding category.

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

23 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Inkling has 41.

Related comparisons

Go deeper