Noometry

Model comparison

C4ai Aya Expanse 32b vs Inkling

Inkling is the stronger model overall, scoring 44.1 to 35.3 on the Noometry Index.

Last verified . 17 shared benchmarks.

C4ai Aya Expanse 32b Cohere

35.3

Rank #216 Confirmed

Inkling Thinking Machines Lab

44.1

Rank #75 Confirmed

Summary

  • They share 17 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 2 categories and Inkling in 6 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Inkling leads 65.5 to 42.4.
  • C4ai Aya Expanse 32b accepts more context: 128K tokens versus 66K.

Side by side

C4ai Aya Expanse 32bInkling
ProviderCohereThinking Machines Lab
Noometry Index35.344.1
Released2024-10-242026-07-15
WeightsOpenOpen
Context window128K66K
Max output4K66K
Input $ / M tokens—$1.87
Output $ / M tokens—$4.68
Results tracked1841

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

Category by category

Coding Too close to call

C4ai Aya Expanse 32b: 34.3 (#227), Inkling: 34.1 (#229)

BenchmarkC4ai Aya Expanse 32bInkling
LMArena Coding11971463
FrontierCode—14%
LMArena WebDev—1412
FrontierSWE—4.1%
SciCode—47%
WeirdML—32.3%
ALE-Bench—946

Agentic & Tool Use Not comparable

C4ai Aya Expanse 32b: —, Inkling: 29.5 (#76)

BenchmarkC4ai Aya Expanse 32bInkling
APEX-Agents—33.8%
τ²-bench Banking—25%

Reasoning Inkling leads

C4ai Aya Expanse 32b: 22.3 (#183), Inkling: 40.6 (#48)

BenchmarkC4ai Aya Expanse 32bInkling
LMArena Hard Prompts11931452
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—148.6

Math Too close to call

C4ai Aya Expanse 32b: 31.4 (#195), Inkling: 31.2 (#198)

BenchmarkC4ai Aya Expanse 32bInkling
LMArena Math12001482
FrontierMath (Tiers 1-3)—33.3%
FrontierMath Tier 4—4.9%
OTIS Mock AIME 2024-2025—88.9%
ProofBench—0%

Knowledge Inkling leads

C4ai Aya Expanse 32b: 32.6 (#202), Inkling: 55.2 (#44)

BenchmarkC4ai Aya Expanse 32bInkling
LMArena Expert11821468
GPQA Diamond—88.3%
SimpleQA Verified—40.3%
Vectara Hallucination Rate10.9%—

Multilingual Inkling leads

C4ai Aya Expanse 32b: 38.5 (#225), Inkling: 54.2 (#49)

BenchmarkC4ai Aya Expanse 32bInkling
LMArena Non-English12131434
LMArena Chinese12101495
LMArena French12471453
LMArena German11991456
LMArena Japanese11631428
LMArena Korean11581401
LMArena Russian12271430
LMArena Spanish11931442

Instruction Following Inkling leads

C4ai Aya Expanse 32b: 62.9 (#232), Inkling: 75.3 (#65)

BenchmarkC4ai Aya Expanse 32bInkling
LMArena Instruction Following11961427

Long Context Inkling leads

C4ai Aya Expanse 32b: 37.2 (#215), Inkling: 43.9 (#79)

BenchmarkC4ai Aya Expanse 32bInkling
LMArena Longer Query12281436

Writing & Preference Inkling leads

C4ai Aya Expanse 32b: 42.4 (#230), Inkling: 65.5 (#48)

BenchmarkC4ai Aya Expanse 32bInkling
LMArena Text12241443
LMArena Creative Writing12001390
LMArena Multi-Turn11901436
EQ-Bench Creative Writing—1611
EQ-Bench 4—1226

Frequently asked questions

Is C4ai Aya Expanse 32b better than Inkling?

Inkling is the stronger model overall, scoring 44.1 to 35.3 on the Noometry Index.

Is C4ai Aya Expanse 32b or Inkling better for coding?

They score almost the same on coding (34.3 vs 34.1); test both on your own repository before choosing.

Which has the bigger context window?

C4ai Aya Expanse 32b does, with 128K tokens against 66K.

How many benchmarks do C4ai Aya Expanse 32b and Inkling share?

17 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Inkling has 41.

Related comparisons

Go deeper