Noometry

Model comparison

Granite 3.0 8b Instruct vs Inkling-Small

Inkling-Small is the stronger model overall, scoring 46.5 to 31.6 on the Noometry Index.

Last verified . 12 shared benchmarks.

Granite 3.0 8b Instruct IBM

31.6

Rank #270 Confirmed

Inkling-Small Thinking Machines Lab

46.5

Rank #63 Confirmed

Summary

  • They share 12 benchmarks with published results for both. Granite 3.0 8b Instruct scores higher in 0 categories and Inkling-Small in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Inkling-Small leads 59.6 to 31.1.

Side by side

Granite 3.0 8b InstructInkling-Small
ProviderIBMThinking Machines Lab
Noometry Index31.646.5
Released—2026-07-15
WeightsOpenOpen
Context window—524K
Max output—1.05M
Input $ / M tokens—$0.45
Output $ / M tokens—$1.20
Results tracked1433

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

Category by category

Coding Inkling-Small leads

Granite 3.0 8b Instruct: 29.7 (#301), Inkling-Small: 43.6 (#85)

BenchmarkGranite 3.0 8b InstructInkling-Small
LMArena Coding11121451
LMArena WebDev—1409
SciCode—48.7%
BigCodeBench Instruct29.3%—
BigCodeBench Complete35.4%—

Reasoning Inkling-Small leads

Granite 3.0 8b Instruct: 20.9 (#230), Inkling-Small: 38.6 (#63)

BenchmarkGranite 3.0 8b InstructInkling-Small
LMArena Hard Prompts10921423
ARC-AGI-2—40.1%
ARC-AGI-1—84%
CritPt—8.3%
Chess Puzzles—18%
Mystery Game Puzzles—6%
Epoch Capabilities Index—150.15

Math Inkling-Small leads

Granite 3.0 8b Instruct: 32.8 (#210), Inkling-Small: 45.1 (#77)

BenchmarkGranite 3.0 8b InstructInkling-Small
LMArena Math11431459
FrontierMath (Tiers 1-3)—46.3%
FrontierMath Tier 4—17.1%
OTIS Mock AIME 2024-2025—90%
ProofBench—6%

Knowledge Inkling-Small leads

Granite 3.0 8b Instruct: 29.6 (#236), Inkling-Small: 48.2 (#77)

BenchmarkGranite 3.0 8b InstructInkling-Small
LMArena Expert10871442
GPQA Diamond—88.5%
SimpleQA Verified—19.1%

Multimodal Not comparable

Granite 3.0 8b Instruct: —, Inkling-Small: 39.1 (#62)

BenchmarkGranite 3.0 8b InstructInkling-Small
LMArena Vision—1235

Multilingual Inkling-Small leads

Granite 3.0 8b Instruct: 27.2 (#276), Inkling-Small: 51.7 (#104)

BenchmarkGranite 3.0 8b InstructInkling-Small
LMArena Non-English10371402
LMArena Chinese10631465
LMArena Russian10601391
LMArena French—1436
LMArena German—1405
LMArena Japanese—1405
LMArena Korean—1363
LMArena Spanish—1428

Instruction Following Inkling-Small leads

Granite 3.0 8b Instruct: 56.0 (#276), Inkling-Small: 73.8 (#114)

BenchmarkGranite 3.0 8b InstructInkling-Small
LMArena Instruction Following10881399

Long Context Inkling-Small leads

Granite 3.0 8b Instruct: 34.0 (#252), Inkling-Small: 42.7 (#118)

BenchmarkGranite 3.0 8b InstructInkling-Small
LMArena Longer Query11221401

Writing & Preference Inkling-Small leads

Granite 3.0 8b Instruct: 31.1 (#285), Inkling-Small: 59.6 (#107)

BenchmarkGranite 3.0 8b InstructInkling-Small
LMArena Text10961414
LMArena Creative Writing10711331
LMArena Multi-Turn10631418
EQ-Bench Creative Writing—1491

Frequently asked questions

Is Granite 3.0 8b Instruct better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 31.6 on the Noometry Index.

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

Inkling-Small scores higher on coding benchmarks: 43.6 versus 29.7 in the Noometry coding category.

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

12 benchmarks have published results for both models. Granite 3.0 8b Instruct has 14 scored results on Noometry and Inkling-Small has 33.

Related comparisons

Go deeper