Noometry

Model comparison

Grok 3 vs Kimi K2.5

Kimi K2.5 is the stronger model overall, scoring 48.1 to 39.9 on the Noometry Index.

Last verified . 30 shared benchmarks.

Grok 3 xAI

39.9

Rank #157 Confirmed

Kimi K2.5 Moonshot AI

48.1

Rank #57 Confirmed

Summary

  • They share 30 benchmarks with published results for both. Grok 3 scores higher in 0 categories and Kimi K2.5 in 9 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Kimi K2.5 leads 31.2 to 13.7.
  • The biggest single-benchmark swing is ARC-AGI-1: 5.5% for Grok 3 and 65.3% for Kimi K2.5.
  • Kimi K2.5 has downloadable open weights; the other is API-only.

Side by side

Grok 3Kimi K2.5
ProviderxAIMoonshot AI
Noometry Index39.948.1
Released2025-04-092026-01-27
WeightsProprietaryOpen
Context window—262K
Max output—262K
Input $ / M tokens—$0.45
Output $ / M tokens—$2.25
Results tracked4051

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

Category by category

Coding Kimi K2.5 leads

Grok 3: 41.9 (#115), Kimi K2.5: 48.8 (#53)

BenchmarkGrok 3Kimi K2.5
WeirdML37.2%45.6%
LMArena Coding14321474
SWE-bench Verified—73.8%
SWE-bench Verified (bash only)—70.8%
Aider Polyglot53.3%—
LMArena WebDev—1437
SWE-bench Multilingual—67.3%
SciCode—49%
ALE-Bench—821.65

Agentic & Tool Use Kimi K2.5 leads

Grok 3: 30.5 (#76), Kimi K2.5: 34.2 (#48)

BenchmarkGrok 3Kimi K2.5
Terminal-Bench—43.2%
OSWorld—63.3%
BALROG29.5%—
Vending-Bench 2—1,198

Reasoning Kimi K2.5 leads

Grok 3: 13.7 (#333), Kimi K2.5: 31.2 (#80)

BenchmarkGrok 3Kimi K2.5
ARC-AGI-20%11.8%
SimpleBench36.1%46.8%
Kagi LLM Benchmark61.3%78.5%
ARC-AGI-15.5%65.3%
LMArena Hard Prompts14341453
Epoch Capabilities Index138.33148.03
NYT Connections (extended)—69.9%
CritPt—3.1%
Chess Puzzles—12%
EnigmaEval—3.4%
Thematic Generalization—69.4%

Math Kimi K2.5 leads

Grok 3: 38.0 (#145), Kimi K2.5: 51.8 (#53)

BenchmarkGrok 3Kimi K2.5
OTIS Mock AIME 2024-202555.6%92.2%
LMArena Math13911470
FrontierMath (Feb 2025 set)3.8%27.9%
FrontierMath Tier 4 (v1)0%4.2%
MathArena Final-Answer Competitions—62.3%
Omni-MATH46.4%—
MATH Level 588.7%—

Knowledge Kimi K2.5 leads

Grok 3: 46.2 (#82), Kimi K2.5: 53.6 (#56)

BenchmarkGrok 3Kimi K2.5
GPQA Diamond75.8%87.6%
Vectara Hallucination Rate5.8%14.2%
LMArena Expert14211466
Humanity's Last Exam—24.4%
SimpleQA Verified—34.3%
MMLU-Pro78.8%—
Confabulations14.2%—
GPQA (HELM)65%—

Multimodal Not comparable

Grok 3: —, Kimi K2.5: 41.1 (#39)

BenchmarkGrok 3Kimi K2.5
LMArena Vision—1269
LMArena Document—1430

Multilingual Kimi K2.5 leads

Grok 3: 52.3 (#87), Kimi K2.5: 53.9 (#53)

BenchmarkGrok 3Kimi K2.5
LMArena Non-English14101433
LMArena Chinese14481495
LMArena French14601454
LMArena German14311441
LMArena Japanese13871421
LMArena Korean13731410
LMArena Russian14161435
LMArena Spanish14171450

Instruction Following Too close to call

Grok 3: 75.0 (#73), Kimi K2.5: 75.3 (#64)

BenchmarkGrok 3Kimi K2.5
LMArena Instruction Following14091431
IFEval88.4%—

Long Context Kimi K2.5 leads

Grok 3: 38.7 (#192), Kimi K2.5: 52.1 (#7)

BenchmarkGrok 3Kimi K2.5
Fiction.LiveBench58.3%86.1%
LMArena Longer Query14391445
CL-bench—19.3%
CL-bench Life—13.2%

Writing & Preference Kimi K2.5 leads

Grok 3: 55.8 (#141), Kimi K2.5: 65.1 (#53)

BenchmarkGrok 3Kimi K2.5
LMArena Text14261445
LMArena Creative Writing14141423
EQ-Bench Creative Writing11861579
LMArena Multi-Turn14251444
Short-Story Creative Writing76.4%—
WildBench84.9%—

Frequently asked questions

Is Grok 3 better than Kimi K2.5?

Kimi K2.5 is the stronger model overall, scoring 48.1 to 39.9 on the Noometry Index.

Is Grok 3 or Kimi K2.5 better for coding?

Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 41.9 in the Noometry coding category.

How many benchmarks do Grok 3 and Kimi K2.5 share?

30 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Kimi K2.5 has 51.

Related comparisons

Go deeper