Noometry

Model comparison

Grok 4.6 vs Kimi K2 Thinking Turbo

Grok 4.6 is the stronger model overall, scoring 56.9 to 45.8 on the Noometry Index.

Last verified . 21 shared benchmarks.

Grok 4.6 xAI

56.9

Rank #21 Confirmed

Kimi K2 Thinking Turbo Moonshot AI

45.8

Rank #70 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Grok 4.6 scores higher in 8 categories and Kimi K2 Thinking Turbo in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.6 leads 61.4 to 32.5.
  • The biggest single-benchmark swing is Chess Puzzles: 40% for Grok 4.6 and 20% for Kimi K2 Thinking Turbo.
  • Kimi K2 Thinking Turbo has downloadable open weights; the other is API-only.

Side by side

Grok 4.6Kimi K2 Thinking Turbo
ProviderxAIMoonshot AI
Noometry Index56.945.8
Released2026-08-122025-11-06
WeightsProprietaryOpen
Context window500K—
Max output500K—
Input $ / M tokens$2—
Output $ / M tokens$6—
Results tracked4921

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

Category by category

Coding Grok 4.6 leads

Grok 4.6: 58.5 (#16), Kimi K2 Thinking Turbo: 38.4 (#178)

BenchmarkGrok 4.6Kimi K2 Thinking Turbo
LMArena WebDev16171322
LMArena Coding14651454
DeepSWE67.5%—
FrontierCode48%—
CursorBench41.4%—
FrontierSWE25.3%—
SciCode56.5%—
WeirdML67.3%—
ALE-Bench1,508—

Agentic & Tool Use Not comparable

Grok 4.6: 39.4 (#27), Kimi K2 Thinking Turbo: —

BenchmarkGrok 4.6Kimi K2 Thinking Turbo
APEX-Agents65.3%—
GDP.pdf17.2%—
Vending-Bench 29,047—

Reasoning Grok 4.6 leads

Grok 4.6: 61.4 (#20), Kimi K2 Thinking Turbo: 32.5 (#75)

BenchmarkGrok 4.6Kimi K2 Thinking Turbo
Chess Puzzles40%20%
LMArena Hard Prompts14471428
ARC-AGI-267.1%—
SimpleBench75.9%—
NYT Connections (extended)80%—
ARC-AGI-187.5%—
CritPt19.7%—
EBR-Bench30.5%—
Mystery Game Puzzles34%—
DTBench97.3%—
LMCA48.5%—
Epoch Capabilities Index156.44—

Math Grok 4.6 leads

Grok 4.6: 67.0 (#24), Kimi K2 Thinking Turbo: 47.4 (#68)

BenchmarkGrok 4.6Kimi K2 Thinking Turbo
OTIS Mock AIME 2024-202599.2%83.1%
LMArena Math14231429
FrontierMath (Tiers 1-3)66%—
FrontierMath Tier 431.7%—
ProofBench51%—

Knowledge Grok 4.6 leads

Grok 4.6: 63.3 (#20), Kimi K2 Thinking Turbo: 50.9 (#69)

BenchmarkGrok 4.6Kimi K2 Thinking Turbo
GPQA Diamond94%84.2%
LMArena Expert14671439
SimpleQA Verified49.3%—

Multimodal Not comparable

Grok 4.6: 43.6 (#23), Kimi K2 Thinking Turbo: —

BenchmarkGrok 4.6Kimi K2 Thinking Turbo
LMArena Vision1263—
Blueprint-Bench 233.2%—
Furniture Assembly40%—
LMArena Document1452—

Multilingual Grok 4.6 leads

Grok 4.6: 53.0 (#74), Kimi K2 Thinking Turbo: 51.4 (#109)

BenchmarkGrok 4.6Kimi K2 Thinking Turbo
LMArena Non-English14201398
LMArena Chinese14801456
LMArena French14611425
LMArena German14311390
LMArena Japanese13761357
LMArena Korean13971330
LMArena Russian14221391
LMArena Spanish14041406

Instruction Following Grok 4.6 leads

Grok 4.6: 75.4 (#63), Kimi K2 Thinking Turbo: 74.0 (#109)

BenchmarkGrok 4.6Kimi K2 Thinking Turbo
LMArena Instruction Following14311403

Long Context Grok 4.6 leads

Grok 4.6: 44.5 (#66), Kimi K2 Thinking Turbo: 43.2 (#102)

BenchmarkGrok 4.6Kimi K2 Thinking Turbo
LMArena Longer Query14541415

Writing & Preference Grok 4.6 leads

Grok 4.6: 62.3 (#80), Kimi K2 Thinking Turbo: 60.0 (#104)

BenchmarkGrok 4.6Kimi K2 Thinking Turbo
LMArena Text14281415
LMArena Creative Writing14281374
LMArena Multi-Turn14251414

Frequently asked questions

Is Grok 4.6 better than Kimi K2 Thinking Turbo?

Grok 4.6 is the stronger model overall, scoring 56.9 to 45.8 on the Noometry Index.

Is Grok 4.6 or Kimi K2 Thinking Turbo better for coding?

Grok 4.6 scores higher on coding benchmarks: 58.5 versus 38.4 in the Noometry coding category.

How many benchmarks do Grok 4.6 and Kimi K2 Thinking Turbo share?

21 benchmarks have published results for both models. Grok 4.6 has 49 scored results on Noometry and Kimi K2 Thinking Turbo has 21.

Related comparisons

Go deeper