Noometry

Model comparison

Grok 4 vs Kimi K2 (Jul 2025)

Grok 4 is the stronger model overall, scoring 48.1 to 41.2 on the Noometry Index.

Last verified . 36 shared benchmarks.

Grok 4 xAI

48.1

Rank #56 Confirmed

Kimi K2 (Jul 2025) Moonshot AI

41.2

Rank #140 Confirmed

Summary

  • They share 36 benchmarks with published results for both. Grok 4 scores higher in 7 categories and Kimi K2 (Jul 2025) in 2 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Grok 4 leads 63.1 to 41.2.
  • The biggest single-benchmark swing is SimpleBench: 60.5% for Grok 4 and 26.3% for Kimi K2 (Jul 2025).
  • Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.

Side by side

Grok 4Kimi K2 (Jul 2025)
ProviderxAIMoonshot AI
Noometry Index48.141.2
Released2025-07-092025-07-12
WeightsProprietaryOpen
Context window—262K
Max output—262K
Input $ / M tokens—$0.57
Output $ / M tokens—$2.30
Results tracked4842

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

Category by category

Coding Grok 4 leads

Grok 4: 50.3 (#46), Kimi K2 (Jul 2025): 42.4 (#102)

BenchmarkGrok 4Kimi K2 (Jul 2025)
Aider Polyglot79.6%59.1%
WeirdML45.7%42.8%
LMArena Coding14081399
SWE-bench Verified (bash only)—63.4%
GSO—4.9%
ALE-Bench—597.5

Agentic & Tool Use Too close to call

Grok 4: 32.3 (#68), Kimi K2 (Jul 2025): 32.4 (#64)

BenchmarkGrok 4Kimi K2 (Jul 2025)
Terminal-Bench27.2%35.7%
Berkeley Function Calling Leaderboard63%59.1%
METR Time Horizons66.6%59.2%
GDPval21.1%—
Cybench43%—
DeepResearch Bench47.3%—
BALROG43.6%—
LMArena Search1142—

Reasoning Grok 4 leads

Grok 4: 36.7 (#65), Kimi K2 (Jul 2025): 23.3 (#179)

BenchmarkGrok 4Kimi K2 (Jul 2025)
SimpleBench60.5%26.3%
Kagi LLM Benchmark73.6%64.4%
LMArena Hard Prompts14091384
Epoch Capabilities Index146.44146.01
ForecastBench60.960.2
ARC-AGI-216%—
ARC-AGI-166.7%—
Chess Puzzles28%—

Math Grok 4 leads

Grok 4: 48.4 (#64), Kimi K2 (Jul 2025): 42.7 (#83)

BenchmarkGrok 4Kimi K2 (Jul 2025)
Omni-MATH60.3%65.4%
LMArena Math14221397
FrontierMath (Feb 2025 set)19.7%21.4%
FrontierMath Tier 4 (v1)2.1%0%
OTIS Mock AIME 2024-202584%—

Knowledge Grok 4 leads

Grok 4: 53.8 (#55), Kimi K2 (Jul 2025): 37.3 (#157)

BenchmarkGrok 4Kimi K2 (Jul 2025)
MMLU-Pro85.1%81.9%
Confabulations12.4%20.4%
GPQA (HELM)72.7%65.3%
LMArena Expert14151365
GPQA Diamond87%—
Vectara Hallucination Rate—17.9%

Multimodal Not comparable

Grok 4: 33.7 (#94), Kimi K2 (Jul 2025): —

BenchmarkGrok 4Kimi K2 (Jul 2025)
LMArena Vision1210—
GeoBench45%—

Multilingual Grok 4 leads

Grok 4: 51.8 (#103), Kimi K2 (Jul 2025): 49.6 (#130)

BenchmarkGrok 4Kimi K2 (Jul 2025)
LMArena Non-English14031372
LMArena Chinese14271415
LMArena French14181379
LMArena German14291387
LMArena Japanese13941349
LMArena Korean13771325
LMArena Russian14101385
LMArena Spanish14201386

Instruction Following Grok 4 leads

Grok 4: 79.2 (#5), Kimi K2 (Jul 2025): 71.1 (#156)

BenchmarkGrok 4Kimi K2 (Jul 2025)
IFEval94.9%85%
LMArena Instruction Following13871348

Long Context Grok 4 leads

Grok 4: 63.1 (#4), Kimi K2 (Jul 2025): 41.2 (#145)

BenchmarkGrok 4Kimi K2 (Jul 2025)
Fiction.LiveBench94.4%66.7%
LMArena Longer Query14091353
CL-bench—17.6%

Writing & Preference Kimi K2 (Jul 2025) leads

Grok 4: 58.5 (#116), Kimi K2 (Jul 2025): 62.3 (#78)

BenchmarkGrok 4Kimi K2 (Jul 2025)
LMArena Text14111380
LMArena Creative Writing13971350
Short-Story Creative Writing76.9%85.6%
WildBench79.7%86.2%
LMArena Multi-Turn14161371
EQ-Bench Creative Writing—1666

Frequently asked questions

Is Grok 4 better than Kimi K2 (Jul 2025)?

Grok 4 is the stronger model overall, scoring 48.1 to 41.2 on the Noometry Index.

Is Grok 4 or Kimi K2 (Jul 2025) better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 42.4 in the Noometry coding category.

How many benchmarks do Grok 4 and Kimi K2 (Jul 2025) share?

36 benchmarks have published results for both models. Grok 4 has 48 scored results on Noometry and Kimi K2 (Jul 2025) has 42.

Related comparisons

Go deeper