Noometry

Model comparison

Inkling vs Kimi K2 Thinking Turbo

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 44.1 on the Noometry Index.

Last verified . 21 shared benchmarks.

Inkling Thinking Machines Lab

44.1

Rank #80 Confirmed

Kimi K2 Thinking Turbo Moonshot AI

45.8

Rank #70 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Inkling scores higher in 6 categories and Kimi K2 Thinking Turbo in 2 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K2 Thinking Turbo leads 47.4 to 31.3.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for Inkling and 83.1% for Kimi K2 Thinking Turbo.

Side by side

InklingKimi K2 Thinking Turbo
ProviderThinking Machines LabMoonshot AI
Noometry Index44.145.8
Released2026-07-152025-11-06
WeightsOpenOpen
Context window66K—
Max output66K—
Input $ / M tokens$1.87—
Output $ / M tokens$4.68—
Results tracked4121

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

Category by category

Coding Kimi K2 Thinking Turbo leads

Inkling: 34.5 (#234), Kimi K2 Thinking Turbo: 38.4 (#178)

BenchmarkInklingKimi K2 Thinking Turbo
LMArena WebDev14131322
LMArena Coding14641454
FrontierCode14%—
FrontierSWE4.1%—
SciCode47%—
WeirdML32.3%—
ALE-Bench946—

Agentic & Tool Use Not comparable

Inkling: 29.6 (#85), Kimi K2 Thinking Turbo: —

BenchmarkInklingKimi K2 Thinking Turbo
APEX-Agents33.8%—
τ²-bench Banking25%—

Reasoning Inkling leads

Inkling: 40.4 (#56), Kimi K2 Thinking Turbo: 32.5 (#75)

BenchmarkInklingKimi K2 Thinking Turbo
Chess Puzzles21%20%
LMArena Hard Prompts14511428
ARC-AGI-236.5%—
SimpleBench50%—
ARC-AGI-179.5%—
CritPt5.4%—
DTBench87.5%—
LMCA37.6%—
Epoch Capabilities Index148.54—

Math Kimi K2 Thinking Turbo leads

Inkling: 31.3 (#225), Kimi K2 Thinking Turbo: 47.4 (#68)

BenchmarkInklingKimi K2 Thinking Turbo
OTIS Mock AIME 2024-202588.9%83.1%
LMArena Math14791429
FrontierMath (Tiers 1-3)33.3%—
FrontierMath Tier 44.9%—
ProofBench0%—

Knowledge Inkling leads

Inkling: 55.1 (#49), Kimi K2 Thinking Turbo: 50.9 (#69)

BenchmarkInklingKimi K2 Thinking Turbo
GPQA Diamond88.3%84.2%
LMArena Expert14651439
SimpleQA Verified40.3%—

Multilingual Inkling leads

Inkling: 54.0 (#52), Kimi K2 Thinking Turbo: 51.4 (#109)

BenchmarkInklingKimi K2 Thinking Turbo
LMArena Non-English14341398
LMArena Chinese14901456
LMArena French14581425
LMArena German14461390
LMArena Japanese14291357
LMArena Korean14041330
LMArena Russian14291391
LMArena Spanish14481406

Instruction Following Inkling leads

Inkling: 75.1 (#71), Kimi K2 Thinking Turbo: 74.0 (#109)

BenchmarkInklingKimi K2 Thinking Turbo
LMArena Instruction Following14261403

Long Context Too close to call

Inkling: 43.8 (#86), Kimi K2 Thinking Turbo: 43.2 (#102)

BenchmarkInklingKimi K2 Thinking Turbo
LMArena Longer Query14341415

Writing & Preference Inkling leads

Inkling: 65.2 (#51), Kimi K2 Thinking Turbo: 60.0 (#104)

BenchmarkInklingKimi K2 Thinking Turbo
LMArena Text14411415
LMArena Creative Writing13871374
LMArena Multi-Turn14361414
EQ-Bench Creative Writing1611—
EQ-Bench 41226—

Frequently asked questions

Is Inkling better than Kimi K2 Thinking Turbo?

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 44.1 on the Noometry Index.

Is Inkling or Kimi K2 Thinking Turbo better for coding?

Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.4 versus 34.5 in the Noometry coding category.

How many benchmarks do Inkling and Kimi K2 Thinking Turbo share?

21 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Kimi K2 Thinking Turbo has 21.

Related comparisons

Go deeper