Noometry

Model comparison

Grok 4.3 vs Kimi K2 Thinking Turbo

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 43.6 on the Noometry Index.

Last verified . 21 shared benchmarks.

Grok 4.3 xAI

43.6

Rank #80 Confirmed

Kimi K2 Thinking Turbo Moonshot AI

45.4

Rank #63 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Grok 4.3 scores higher in 4 categories and Kimi K2 Thinking Turbo in 4 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.3 leads 34.9 to 31.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for Grok 4.3 and 83.1% for Kimi K2 Thinking Turbo.
  • Kimi K2 Thinking Turbo has downloadable open weights; the other is API-only.

Side by side

Grok 4.3Kimi K2 Thinking Turbo
ProviderxAIMoonshot AI
Noometry Index43.645.4
Released2026-04-172025-11-06
WeightsProprietaryOpen
Context window1M—
Max output30K—
Input $ / M tokens$1.25—
Output $ / M tokens$2.50—
Results tracked4021

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

Category by category

Coding Grok 4.3 leads

Grok 4.3: 41.3 (#117), Kimi K2 Thinking Turbo: 38.1 (#166)

BenchmarkGrok 4.3Kimi K2 Thinking Turbo
LMArena WebDev13571322
LMArena Coding14151454
SciCode47.3%—
WeirdML49.9%—
ALE-Bench944.17—

Agentic & Tool Use Not comparable

Grok 4.3: 27.6 (#93), Kimi K2 Thinking Turbo: —

BenchmarkGrok 4.3Kimi K2 Thinking Turbo
GDP.pdf8%—
LMArena Search1165—
Vending-Bench 235.26—

Reasoning Grok 4.3 leads

Grok 4.3: 34.9 (#60), Kimi K2 Thinking Turbo: 31.4 (#72)

BenchmarkGrok 4.3Kimi K2 Thinking Turbo
Chess Puzzles25%20%
LMArena Hard Prompts13971428
NYT Connections (extended)55.2%—
CritPt8%—
DTBench90.7%—
LMCA38.3%—
Epoch Capabilities Index149.13—
ForecastBench60.3—

Math Too close to call

Grok 4.3: 45.8 (#60), Kimi K2 Thinking Turbo: 45.5 (#62)

BenchmarkGrok 4.3Kimi K2 Thinking Turbo
OTIS Mock AIME 2024-202593.3%83.1%
LMArena Math13881429
FrontierMath (Tiers 1-3)42.8%—
FrontierMath Tier 414.6%—
ProofBench11%—

Knowledge Grok 4.3 leads

Grok 4.3: 52.5 (#57), Kimi K2 Thinking Turbo: 50.9 (#64)

BenchmarkGrok 4.3Kimi K2 Thinking Turbo
GPQA Diamond88.8%84.2%
LMArena Expert13851439
SimpleQA Verified33.2%—

Multimodal Not comparable

Grok 4.3: 31.6 (#96), Kimi K2 Thinking Turbo: —

BenchmarkGrok 4.3Kimi K2 Thinking Turbo
LMArena Vision1231—
Blueprint-Bench 20%—

Multilingual Too close to call

Grok 4.3: 50.7 (#114), Kimi K2 Thinking Turbo: 51.6 (#104)

BenchmarkGrok 4.3Kimi K2 Thinking Turbo
LMArena Non-English13851398
LMArena Chinese14231457
LMArena French14121425
LMArena German13951390
LMArena Japanese13791356
LMArena Korean13571329
LMArena Russian13991390
LMArena Spanish14021407

Instruction Following Kimi K2 Thinking Turbo leads

Grok 4.3: 72.3 (#135), Kimi K2 Thinking Turbo: 74.2 (#103)

BenchmarkGrok 4.3Kimi K2 Thinking Turbo
LMArena Instruction Following13661403

Long Context Too close to call

Grok 4.3: 42.5 (#118), Kimi K2 Thinking Turbo: 43.2 (#99)

BenchmarkGrok 4.3Kimi K2 Thinking Turbo
LMArena Longer Query13931415

Writing & Preference Kimi K2 Thinking Turbo leads

Grok 4.3: 58.6 (#112), Kimi K2 Thinking Turbo: 60.2 (#99)

BenchmarkGrok 4.3Kimi K2 Thinking Turbo
LMArena Text13971415
LMArena Creative Writing13801373
LMArena Multi-Turn14061414
EQ-Bench 41075—

Frequently asked questions

Is Grok 4.3 better than Kimi K2 Thinking Turbo?

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 43.6 on the Noometry Index.

Is Grok 4.3 or Kimi K2 Thinking Turbo better for coding?

Grok 4.3 scores higher on coding benchmarks: 41.3 versus 38.1 in the Noometry coding category.

How many benchmarks do Grok 4.3 and Kimi K2 Thinking Turbo share?

21 benchmarks have published results for both models. Grok 4.3 has 40 scored results on Noometry and Kimi K2 Thinking Turbo has 21.

Related comparisons

Go deeper