Noometry

Model comparison

Granite 4.0 H Small vs Kimi K2.6

Kimi K2.6 is the stronger model overall, scoring 47.7 to 36.5 on the Noometry Index.

Last verified . 14 shared benchmarks.

Granite 4.0 H Small IBM

36.5

Rank #214 Confirmed

Kimi K2.6 Moonshot AI

47.7

Rank #60 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Granite 4.0 H Small scores higher in 0 categories and Kimi K2.6 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K2.6 leads 57.0 to 31.4.
  • The biggest single-benchmark swing is Vectara Hallucination Rate: 5.2% for Granite 4.0 H Small and 10.8% for Kimi K2.6.

Side by side

Granite 4.0 H SmallKimi K2.6
ProviderIBMMoonshot AI
Noometry Index36.547.7
Released—2026-04-20
WeightsOpenOpen
Context window—262K
Max output—262K
Input $ / M tokens—$0.95
Output $ / M tokens—$4
Results tracked1951

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

Category by category

Coding Kimi K2.6 leads

Granite 4.0 H Small: 36.4 (#209), Kimi K2.6: 50.7 (#43)

BenchmarkGranite 4.0 H SmallKimi K2.6
LMArena Coding12491488
SWE-bench Verified—76.7%
LMArena WebDev—1509
SciCode—53.5%
WeirdML—55.9%
ALE-Bench—1,093

Agentic & Tool Use Not comparable

Granite 4.0 H Small: —, Kimi K2.6: 21.9 (#137)

BenchmarkGranite 4.0 H SmallKimi K2.6
OSWorld 2.0—4.6%
ExploitBench—18.4%
GBAEval—0.9%
GDP.pdf—12%
Vending-Bench 2—6,205

Reasoning Kimi K2.6 leads

Granite 4.0 H Small: 24.4 (#163), Kimi K2.6: 40.5 (#55)

BenchmarkGranite 4.0 H SmallKimi K2.6
LMArena Hard Prompts12401470
NYT Connections (extended)—87.2%
CritPt—8%
Chess Puzzles—26%
EBR-Bench—2.4%
Mystery Game Puzzles—18%
DTBench—90.9%
LMCA—37.3%
Epoch Capabilities Index—151.05

Math Kimi K2.6 leads

Granite 4.0 H Small: 31.4 (#223), Kimi K2.6: 57.0 (#41)

BenchmarkGranite 4.0 H SmallKimi K2.6
LMArena Math12471475
FrontierMath (Tiers 1-3)—57.2%
FrontierMath Tier 4—25.6%
MathArena Final-Answer Competitions—72.9%
OTIS Mock AIME 2024-2025—96.1%
ProofBench—16%
Omni-MATH29.6%—
FrontierMath (Feb 2025 set)—39%
FrontierMath Tier 4 (v1)—14.6%

Knowledge Kimi K2.6 leads

Granite 4.0 H Small: 32.0 (#215), Kimi K2.6: 54.0 (#54)

BenchmarkGranite 4.0 H SmallKimi K2.6
Vectara Hallucination Rate5.2%10.8%
LMArena Expert12511491
GPQA Diamond—90.8%
SimpleQA Verified—34.9%
MMLU-Pro56.9%—
GPQA (HELM)38.3%—

Multimodal Not comparable

Granite 4.0 H Small: —, Kimi K2.6: 31.6 (#103)

BenchmarkGranite 4.0 H SmallKimi K2.6
LMArena Vision—1283
Blueprint-Bench 2—3.9%
Furniture Assembly—21.7%
LMArena Document—1451

Multilingual Kimi K2.6 leads

Granite 4.0 H Small: 38.6 (#228), Kimi K2.6: 54.9 (#37)

BenchmarkGranite 4.0 H SmallKimi K2.6
LMArena Non-English12161446
LMArena Chinese12491521
LMArena Russian12011446
LMArena Spanish12581464
LMArena French—1471
LMArena German—1450
LMArena Japanese—1443
LMArena Korean—1427

Instruction Following Kimi K2.6 leads

Granite 4.0 H Small: 68.7 (#183), Kimi K2.6: 76.3 (#43)

BenchmarkGranite 4.0 H SmallKimi K2.6
LMArena Instruction Following12221451
IFEval89%—

Long Context Kimi K2.6 leads

Granite 4.0 H Small: 37.7 (#213), Kimi K2.6: 44.9 (#52)

BenchmarkGranite 4.0 H SmallKimi K2.6
LMArena Longer Query12421468

Writing & Preference Kimi K2.6 leads

Granite 4.0 H Small: 43.8 (#227), Kimi K2.6: 68.5 (#26)

BenchmarkGranite 4.0 H SmallKimi K2.6
LMArena Text12411455
LMArena Creative Writing12111434
LMArena Multi-Turn12421453
EQ-Bench Creative Writing—1725
WildBench73.9%—
EQ-Bench 4—1202

Frequently asked questions

Is Granite 4.0 H Small better than Kimi K2.6?

Kimi K2.6 is the stronger model overall, scoring 47.7 to 36.5 on the Noometry Index.

Is Granite 4.0 H Small or Kimi K2.6 better for coding?

Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 36.4 in the Noometry coding category.

How many benchmarks do Granite 4.0 H Small and Kimi K2.6 share?

14 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Kimi K2.6 has 51.

Related comparisons

Go deeper