Noometry

Model comparison

Grok 4.7 vs Kimi K2 Thinking Turbo

Grok 4.7 is the stronger model overall, scoring 53.1 to 45.8 on the Noometry Index.

Last verified . 18 shared benchmarks.

Grok 4.7 xAI

53.1

Rank #37 Confirmed

Kimi K2 Thinking Turbo Moonshot AI

45.8

Rank #70 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Grok 4.7 scores higher in 6 categories and Kimi K2 Thinking Turbo in 2 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Grok 4.7 leads 58.0 to 38.4.
  • The biggest single-benchmark swing is Chess Puzzles: 38% for Grok 4.7 and 20% for Kimi K2 Thinking Turbo.
  • Kimi K2 Thinking Turbo has downloadable open weights; the other is API-only.

Side by side

Grok 4.7Kimi K2 Thinking Turbo
ProviderxAIMoonshot AI
Noometry Index53.145.8
Released2026-09-212025-11-06
WeightsProprietaryOpen
Context window500K—
Max output500K—
Input $ / M tokens$2—
Output $ / M tokens$6—
Results tracked3921

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

Category by category

Coding Grok 4.7 leads

Grok 4.7: 58.0 (#18), Kimi K2 Thinking Turbo: 38.4 (#178)

BenchmarkGrok 4.7Kimi K2 Thinking Turbo
LMArena WebDev16391322
LMArena Coding14271454
FrontierCode47.6%—
CursorBench46.3%—
FrontierSWE29.5%—
SciCode57.8%—

Agentic & Tool Use Not comparable

Grok 4.7: 36.7 (#37), Kimi K2 Thinking Turbo: —

BenchmarkGrok 4.7Kimi K2 Thinking Turbo
APEX-Agents54.6%—
GDP.pdf22.8%—
Vending-Bench 210,537—

Reasoning Grok 4.7 leads

Grok 4.7: 49.1 (#40), Kimi K2 Thinking Turbo: 32.5 (#75)

BenchmarkGrok 4.7Kimi K2 Thinking Turbo
Chess Puzzles38%20%
LMArena Hard Prompts14131428
NYT Connections (extended)76.8%—
CritPt18%—
Mystery Game Puzzles29%—
DTBench96%—
LMCA49.4%—
Epoch Capabilities Index153.53—

Math Grok 4.7 leads

Grok 4.7: 57.8 (#39), Kimi K2 Thinking Turbo: 47.4 (#68)

BenchmarkGrok 4.7Kimi K2 Thinking Turbo
OTIS Mock AIME 2024-202598.1%83.1%
LMArena Math14071429
FrontierMath (Tiers 1-3)53%—
FrontierMath Tier 417.1%—
ProofBench34%—

Knowledge Grok 4.7 leads

Grok 4.7: 62.8 (#22), Kimi K2 Thinking Turbo: 50.9 (#69)

BenchmarkGrok 4.7Kimi K2 Thinking Turbo
GPQA Diamond92.7%84.2%
LMArena Expert14221439
SimpleQA Verified56%—

Multimodal Not comparable

Grok 4.7: 35.5 (#87), Kimi K2 Thinking Turbo: —

BenchmarkGrok 4.7Kimi K2 Thinking Turbo
LMArena Vision1228—
Blueprint-Bench 232.5%—
Furniture Assembly20.8%—

Multilingual Too close to call

Grok 4.7: 50.8 (#116), Kimi K2 Thinking Turbo: 51.4 (#109)

BenchmarkGrok 4.7Kimi K2 Thinking Turbo
LMArena Non-English13891398
LMArena Chinese14551456
LMArena French14551425
LMArena Russian13971391
LMArena Spanish14001406
LMArena German—1390
LMArena Japanese—1357
LMArena Korean—1330

Instruction Following Too close to call

Grok 4.7: 74.1 (#105), Kimi K2 Thinking Turbo: 74.0 (#109)

BenchmarkGrok 4.7Kimi K2 Thinking Turbo
LMArena Instruction Following14041403

Long Context Too close to call

Grok 4.7: 43.1 (#104), Kimi K2 Thinking Turbo: 43.2 (#102)

BenchmarkGrok 4.7Kimi K2 Thinking Turbo
LMArena Longer Query14131415

Writing & Preference Grok 4.7 leads

Grok 4.7: 70.0 (#24), Kimi K2 Thinking Turbo: 60.0 (#104)

BenchmarkGrok 4.7Kimi K2 Thinking Turbo
LMArena Text13991415
LMArena Creative Writing13911374
LMArena Multi-Turn13931414
EQ-Bench Creative Writing2007—

Frequently asked questions

Is Grok 4.7 better than Kimi K2 Thinking Turbo?

Grok 4.7 is the stronger model overall, scoring 53.1 to 45.8 on the Noometry Index.

Is Grok 4.7 or Kimi K2 Thinking Turbo better for coding?

Grok 4.7 scores higher on coding benchmarks: 58.0 versus 38.4 in the Noometry coding category.

How many benchmarks do Grok 4.7 and Kimi K2 Thinking Turbo share?

18 benchmarks have published results for both models. Grok 4.7 has 39 scored results on Noometry and Kimi K2 Thinking Turbo has 21.

Related comparisons

Go deeper