Model comparison

Granite 3.0 8b Instruct vs Inkling

Inkling is the stronger model overall, scoring 44.1 to 31.6 on the Noometry Index.

Last verified . 12 shared benchmarks.

Granite 3.0 8b Instruct IBM

31.6

Rank #270 Confirmed

Inkling Thinking Machines Lab

44.1

Rank #80 Confirmed

Summary

  • They share 12 benchmarks with published results for both. Granite 3.0 8b Instruct scores higher in 1 category and Inkling in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Inkling leads 65.2 to 31.1.

Side by side

Granite 3.0 8b Instruct and Inkling specifications
Granite 3.0 8b InstructInkling
ProviderIBMThinking Machines Lab
Noometry Index31.644.1
Released—2026-07-15
WeightsOpenOpen
Context window—66K
Max output—66K
Input $ / M tokens—$1.87
Output $ / M tokens—$4.68
Results tracked1441

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

Category by category

Coding Inkling leads

Granite 3.0 8b Instruct: 29.7 (#301), Inkling: 34.5 (#234)

Coding benchmarks
BenchmarkGranite 3.0 8b InstructInkling
LMArena Coding11121464
FrontierCode—14%
LMArena WebDev—1413
FrontierSWE—4.1%
SciCode—47%
WeirdML—32.3%
BigCodeBench Instruct29.3%—
BigCodeBench Complete35.4%—
ALE-Bench—946

Agentic & Tool Use Not comparable

Granite 3.0 8b Instruct: —, Inkling: 29.6 (#85)

Agentic & Tool Use benchmarks
BenchmarkGranite 3.0 8b InstructInkling
APEX-Agents—33.8%
τ²-bench Banking—25%

Reasoning Inkling leads

Granite 3.0 8b Instruct: 20.9 (#230), Inkling: 40.4 (#56)

Reasoning benchmarks
BenchmarkGranite 3.0 8b InstructInkling
LMArena Hard Prompts10921451
ARC-AGI-2—36.5%
SimpleBench—50%
ARC-AGI-1—79.5%
CritPt—5.4%
Chess Puzzles—21%
DTBench—87.5%
LMCA—37.6%
Epoch Capabilities Index—148.54

Math Granite 3.0 8b Instruct leads

Granite 3.0 8b Instruct: 32.8 (#210), Inkling: 31.3 (#225)

Math benchmarks
BenchmarkGranite 3.0 8b InstructInkling
LMArena Math11431479
FrontierMath (Tiers 1-3)—33.3%
FrontierMath Tier 4—4.9%
OTIS Mock AIME 2024-2025—88.9%
ProofBench—0%

Knowledge Inkling leads

Granite 3.0 8b Instruct: 29.6 (#236), Inkling: 55.1 (#49)

Knowledge benchmarks
BenchmarkGranite 3.0 8b InstructInkling
LMArena Expert10871465
GPQA Diamond—88.3%
SimpleQA Verified—40.3%

Multilingual Inkling leads

Granite 3.0 8b Instruct: 27.2 (#276), Inkling: 54.0 (#52)

Multilingual benchmarks
BenchmarkGranite 3.0 8b InstructInkling
LMArena Non-English10371434
LMArena Chinese10631490
LMArena Russian10601429
LMArena French—1458
LMArena German—1446
LMArena Japanese—1429
LMArena Korean—1404
LMArena Spanish—1448

Instruction Following Inkling leads

Granite 3.0 8b Instruct: 56.0 (#276), Inkling: 75.1 (#71)

Instruction Following benchmarks
BenchmarkGranite 3.0 8b InstructInkling
LMArena Instruction Following10881426

Long Context Inkling leads

Granite 3.0 8b Instruct: 34.0 (#252), Inkling: 43.8 (#86)

Long Context benchmarks
BenchmarkGranite 3.0 8b InstructInkling
LMArena Longer Query11221434

Writing & Preference Inkling leads

Granite 3.0 8b Instruct: 31.1 (#285), Inkling: 65.2 (#51)

Writing & Preference benchmarks
BenchmarkGranite 3.0 8b InstructInkling
LMArena Text10961441
LMArena Creative Writing10711387
LMArena Multi-Turn10631436
EQ-Bench Creative Writing—1611
EQ-Bench 4—1226

Frequently asked questions

Is Granite 3.0 8b Instruct better than Inkling?

Inkling is the stronger model overall, scoring 44.1 to 31.6 on the Noometry Index.

Is Granite 3.0 8b Instruct or Inkling better for coding?

Inkling scores higher on coding benchmarks: 34.5 versus 29.7 in the Noometry coding category.

How many benchmarks do Granite 3.0 8b Instruct and Inkling share?

12 benchmarks have published results for both models. Granite 3.0 8b Instruct has 14 scored results on Noometry and Inkling has 41.

Related comparisons

Go deeper