Noometry

Model comparison

Granite 4.1 8b vs Kimi K2.5

Kimi K2.5 is the stronger model overall, scoring 48.1 to 37.4 on the Noometry Index.

Last verified . 13 shared benchmarks.

Granite 4.1 8b IBM

37.4

Rank #205 Confirmed

Kimi K2.5 Moonshot AI

48.1

Rank #57 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Granite 4.1 8b scores higher in 0 categories and Kimi K2.5 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Kimi K2.5 leads 48.8 to 30.1.

Side by side

Granite 4.1 8bKimi K2.5
ProviderIBMMoonshot AI
Noometry Index37.448.1
Released—2026-01-27
WeightsOpenOpen
Context window—262K
Max output—262K
Input $ / M tokens—$0.45
Output $ / M tokens—$2.25
Results tracked1351

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

Category by category

Coding Kimi K2.5 leads

Granite 4.1 8b: 30.1 (#297), Kimi K2.5: 48.8 (#53)

BenchmarkGranite 4.1 8bKimi K2.5
LMArena WebDev11921437
LMArena Coding13121474
SWE-bench Verified—73.8%
SWE-bench Verified (bash only)—70.8%
SWE-bench Multilingual—67.3%
SciCode—49%
WeirdML—45.6%
ALE-Bench—821.65

Agentic & Tool Use Not comparable

Granite 4.1 8b: —, Kimi K2.5: 34.2 (#48)

BenchmarkGranite 4.1 8bKimi K2.5
Terminal-Bench—43.2%
OSWorld—63.3%
Vending-Bench 2—1,198

Reasoning Kimi K2.5 leads

Granite 4.1 8b: 25.7 (#143), Kimi K2.5: 31.2 (#80)

BenchmarkGranite 4.1 8bKimi K2.5
LMArena Hard Prompts12931453
ARC-AGI-2—11.8%
SimpleBench—46.8%
Kagi LLM Benchmark—78.5%
NYT Connections (extended)—69.9%
ARC-AGI-1—65.3%
CritPt—3.1%
Chess Puzzles—12%
EnigmaEval—3.4%
Thematic Generalization—69.4%
Epoch Capabilities Index—148.03

Math Kimi K2.5 leads

Granite 4.1 8b: 36.4 (#166), Kimi K2.5: 51.8 (#53)

BenchmarkGranite 4.1 8bKimi K2.5
LMArena Math13121470
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

Granite 4.1 8b: 36.1 (#174), Kimi K2.5: 53.6 (#56)

BenchmarkGranite 4.1 8bKimi K2.5
LMArena Expert13091466
GPQA Diamond—87.6%
Humanity's Last Exam—24.4%
SimpleQA Verified—34.3%
Vectara Hallucination Rate—14.2%

Multimodal Not comparable

Granite 4.1 8b: —, Kimi K2.5: 41.1 (#39)

BenchmarkGranite 4.1 8bKimi K2.5
LMArena Vision—1269
LMArena Document—1430

Multilingual Kimi K2.5 leads

Granite 4.1 8b: 41.7 (#204), Kimi K2.5: 53.9 (#53)

BenchmarkGranite 4.1 8bKimi K2.5
LMArena Non-English12611433
LMArena Chinese13371495
LMArena Russian12401435
LMArena French—1454
LMArena German—1441
LMArena Japanese—1421
LMArena Korean—1410
LMArena Spanish—1450

Instruction Following Kimi K2.5 leads

Granite 4.1 8b: 66.9 (#203), Kimi K2.5: 75.3 (#64)

BenchmarkGranite 4.1 8bKimi K2.5
LMArena Instruction Following12691431

Long Context Kimi K2.5 leads

Granite 4.1 8b: 38.7 (#193), Kimi K2.5: 52.1 (#7)

BenchmarkGranite 4.1 8bKimi K2.5
LMArena Longer Query12751445
Fiction.LiveBench—86.1%
CL-bench—19.3%
CL-bench Life—13.2%

Writing & Preference Kimi K2.5 leads

Granite 4.1 8b: 48.1 (#204), Kimi K2.5: 65.1 (#53)

BenchmarkGranite 4.1 8bKimi K2.5
LMArena Text12901445
LMArena Creative Writing12511423
LMArena Multi-Turn12681444
EQ-Bench Creative Writing—1579

Frequently asked questions

Is Granite 4.1 8b better than Kimi K2.5?

Kimi K2.5 is the stronger model overall, scoring 48.1 to 37.4 on the Noometry Index.

Is Granite 4.1 8b or Kimi K2.5 better for coding?

Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 30.1 in the Noometry coding category.

How many benchmarks do Granite 4.1 8b and Kimi K2.5 share?

13 benchmarks have published results for both models. Granite 4.1 8b has 13 scored results on Noometry and Kimi K2.5 has 51.

Related comparisons

Go deeper