Noometry

Model comparison

Granite 3.1 8b Instruct vs Kimi K2.6

Kimi K2.6 is the stronger model overall, scoring 47.7 to 32.4 on the Noometry Index.

Last verified . 12 shared benchmarks.

Granite 3.1 8b Instruct IBM

32.4

Rank #258 Confirmed

Kimi K2.6 Moonshot AI

47.7

Rank #60 Confirmed

Summary

  • They share 12 benchmarks with published results for both. Granite 3.1 8b Instruct scores higher in 1 category and Kimi K2.6 in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Kimi K2.6 leads 68.5 to 35.5.

Side by side

Granite 3.1 8b InstructKimi K2.6
ProviderIBMMoonshot AI
Noometry Index32.447.7
Released—2026-04-20
WeightsOpenOpen
Context window—262K
Max output—262K
Input $ / M tokens—$0.95
Output $ / M tokens—$4
Results tracked1351

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

Category by category

Coding Kimi K2.6 leads

Granite 3.1 8b Instruct: 34.5 (#233), Kimi K2.6: 50.7 (#43)

BenchmarkGranite 3.1 8b InstructKimi K2.6
LMArena Coding11861488
SWE-bench Verified—76.7%
LMArena WebDev—1509
SciCode—53.5%
WeirdML—55.9%
ALE-Bench—1,093

Agentic & Tool Use Granite 3.1 8b Instruct leads

Granite 3.1 8b Instruct: 24.1 (#120), Kimi K2.6: 21.9 (#137)

BenchmarkGranite 3.1 8b InstructKimi K2.6
Berkeley Function Calling Leaderboard27.1%—
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 3.1 8b Instruct: 22.1 (#207), Kimi K2.6: 40.5 (#55)

BenchmarkGranite 3.1 8b InstructKimi K2.6
LMArena Hard Prompts11451470
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 3.1 8b Instruct: 33.0 (#209), Kimi K2.6: 57.0 (#41)

BenchmarkGranite 3.1 8b InstructKimi K2.6
LMArena Math11521475
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%
FrontierMath (Feb 2025 set)—39%
FrontierMath Tier 4 (v1)—14.6%

Knowledge Kimi K2.6 leads

Granite 3.1 8b Instruct: 31.1 (#220), Kimi K2.6: 54.0 (#54)

BenchmarkGranite 3.1 8b InstructKimi K2.6
LMArena Expert11421491
GPQA Diamond—90.8%
SimpleQA Verified—34.9%
Vectara Hallucination Rate—10.8%

Multimodal Not comparable

Granite 3.1 8b Instruct: —, Kimi K2.6: 31.6 (#103)

BenchmarkGranite 3.1 8b InstructKimi K2.6
LMArena Vision—1283
Blueprint-Bench 2—3.9%
Furniture Assembly—21.7%
LMArena Document—1451

Multilingual Kimi K2.6 leads

Granite 3.1 8b Instruct: 30.9 (#260), Kimi K2.6: 54.9 (#37)

BenchmarkGranite 3.1 8b InstructKimi K2.6
LMArena Non-English10991446
LMArena Chinese11451521
LMArena Russian10921446
LMArena French—1471
LMArena German—1450
LMArena Japanese—1443
LMArena Korean—1427
LMArena Spanish—1464

Instruction Following Kimi K2.6 leads

Granite 3.1 8b Instruct: 58.6 (#259), Kimi K2.6: 76.3 (#43)

BenchmarkGranite 3.1 8b InstructKimi K2.6
LMArena Instruction Following11311451

Long Context Kimi K2.6 leads

Granite 3.1 8b Instruct: 35.2 (#241), Kimi K2.6: 44.9 (#52)

BenchmarkGranite 3.1 8b InstructKimi K2.6
LMArena Longer Query11621468

Writing & Preference Kimi K2.6 leads

Granite 3.1 8b Instruct: 35.5 (#266), Kimi K2.6: 68.5 (#26)

BenchmarkGranite 3.1 8b InstructKimi K2.6
LMArena Text11501455
LMArena Creative Writing11291434
LMArena Multi-Turn11081453
EQ-Bench Creative Writing—1725
EQ-Bench 4—1202

Frequently asked questions

Is Granite 3.1 8b Instruct better than Kimi K2.6?

Kimi K2.6 is the stronger model overall, scoring 47.7 to 32.4 on the Noometry Index.

Is Granite 3.1 8b Instruct or Kimi K2.6 better for coding?

Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 34.5 in the Noometry coding category.

How many benchmarks do Granite 3.1 8b Instruct and Kimi K2.6 share?

12 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Kimi K2.6 has 51.

Related comparisons

Go deeper