Noometry

Model comparison

Grok 4 Fast vs Kimi K2.5

Kimi K2.5 is the stronger model overall, scoring 47.8 to 39.0 on the Noometry Index.

Last verified . 25 shared benchmarks.

Grok 4 Fast xAI

39.0

Rank #164 Confirmed

Kimi K2.5 Moonshot AI

47.8

Rank #50 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Grok 4 Fast scores higher in 1 category and Kimi K2.5 in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Kimi K2.5 leads 53.6 to 31.5.
  • The biggest single-benchmark swing is ARC-AGI-1: 48.5% for Grok 4 Fast and 65.3% for Kimi K2.5.
  • Kimi K2.5 has downloadable open weights; the other is API-only.

Side by side

Grok 4 FastKimi K2.5
ProviderxAIMoonshot AI
Noometry Index39.047.8
Released2025-09-192026-01-27
WeightsProprietaryOpen
Context window—262K
Max output—262K
Input $ / M tokens—$0.45
Output $ / M tokens—$2.25
Results tracked3051

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

Category by category

Coding Kimi K2.5 leads

Grok 4 Fast: 32.3 (#264), Kimi K2.5: 48.7 (#48)

BenchmarkGrok 4 FastKimi K2.5
LMArena WebDev11601436
WeirdML42.9%45.6%
LMArena Coding14291474
SWE-bench Verified—73.8%
SWE-bench Verified (bash only)—70.8%
SWE-bench Multilingual—67.3%
SciCode—49%
ALE-Bench—821.65

Agentic & Tool Use Kimi K2.5 leads

Grok 4 Fast: 29.3 (#80), Kimi K2.5: 34.0 (#44)

BenchmarkGrok 4 FastKimi K2.5
Terminal-Bench—43.2%
τ²-bench Banking15.7%—
Cybench30%—
OSWorld—63.3%
LMArena Search1171—
Vending-Bench 2—1,198

Reasoning Kimi K2.5 leads

Grok 4 Fast: 22.5 (#179), Kimi K2.5: 31.2 (#74)

BenchmarkGrok 4 FastKimi K2.5
ARC-AGI-25.3%11.8%
Kagi LLM Benchmark66.1%78.5%
ARC-AGI-148.5%65.3%
LMArena Hard Prompts14131454
Epoch Capabilities Index144.21148.05
SimpleBench—46.8%
NYT Connections (extended)—69.9%
CritPt—3.1%
Chess Puzzles—12%
EnigmaEval—3.4%
Thematic Generalization—69.4%
DTBench82.7%—
ForecastBench60.5—

Math Kimi K2.5 leads

Grok 4 Fast: 36.1 (#126), Kimi K2.5: 50.3 (#46)

BenchmarkGrok 4 FastKimi K2.5
LMArena Math14191470
MathArena Final-Answer Competitions—62.3%
OTIS Mock AIME 2024-2025—92.2%
FrontierMath (Feb 2025 set)—27.9%
FrontierMath Tier 4 (v1)—4.2%

Knowledge Kimi K2.5 leads

Grok 4 Fast: 31.5 (#211), Kimi K2.5: 53.6 (#52)

BenchmarkGrok 4 FastKimi K2.5
Vectara Hallucination Rate19.7%14.2%
LMArena Expert14111466
GPQA Diamond—87.6%
Humanity's Last Exam—24.4%
SimpleQA Verified—34.3%

Multimodal Not comparable

Grok 4 Fast: —, Kimi K2.5: 40.4 (#37)

BenchmarkGrok 4 FastKimi K2.5
LMArena Vision—1269
LMArena Document—1430

Multilingual Kimi K2.5 leads

Grok 4 Fast: 51.5 (#106), Kimi K2.5: 54.1 (#50)

BenchmarkGrok 4 FastKimi K2.5
LMArena Non-English13971433
LMArena Chinese14581495
LMArena French14331454
LMArena German13831441
LMArena Japanese13581422
LMArena Korean13591412
LMArena Russian13871436
LMArena Spanish14141450

Instruction Following Kimi K2.5 leads

Grok 4 Fast: 73.4 (#116), Kimi K2.5: 75.5 (#60)

BenchmarkGrok 4 FastKimi K2.5
LMArena Instruction Following13881431

Long Context Grok 4 Fast leads

Grok 4 Fast: 63.2 (#3), Kimi K2.5: 52.1 (#7)

BenchmarkGrok 4 FastKimi K2.5
Fiction.LiveBench94.4%86.1%
LMArena Longer Query14151445
CL-bench—19.3%
CL-bench Life—13.2%

Writing & Preference Kimi K2.5 leads

Grok 4 Fast: 60.2 (#96), Kimi K2.5: 65.3 (#51)

BenchmarkGrok 4 FastKimi K2.5
LMArena Text14071445
LMArena Creative Writing13881423
LMArena Multi-Turn14141444
EQ-Bench Creative Writing—1579

Frequently asked questions

Is Grok 4 Fast better than Kimi K2.5?

Kimi K2.5 is the stronger model overall, scoring 47.8 to 39.0 on the Noometry Index.

Is Grok 4 Fast or Kimi K2.5 better for coding?

Kimi K2.5 scores higher on coding benchmarks: 48.7 versus 32.3 in the Noometry coding category.

How many benchmarks do Grok 4 Fast and Kimi K2.5 share?

25 benchmarks have published results for both models. Grok 4 Fast has 30 scored results on Noometry and Kimi K2.5 has 51.

Related comparisons

Go deeper