Model comparison

C4ai Aya Expanse 32b vs StarCoder 2 3B

C4ai Aya Expanse 32b has enough public results to be ranked (#221); StarCoder 2 3B does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

C4ai Aya Expanse 32b Cohere

35.9

Rank #221 Confirmed

StarCoder 2 3B NVIDIA

36.3

Unranked Sparse

Side by side

C4ai Aya Expanse 32b and StarCoder 2 3B specifications
C4ai Aya Expanse 32bStarCoder 2 3B
ProviderCohereNVIDIA
Noometry Index35.936.3
Released2024-10-242024-02-22
WeightsOpenOpen
Context window128K—
Max output4K—
Input $ / M tokens——
Output $ / M tokens——
Results tracked187

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

Category by category

Coding C4ai Aya Expanse 32b leads

C4ai Aya Expanse 32b: 34.8 (#231), StarCoder 2 3B: 33.5

Coding benchmarks
BenchmarkC4ai Aya Expanse 32bStarCoder 2 3B
LMArena Coding1197—
BigCodeBench Complete—21.4%
HumanEval+—27.4%

Reasoning Not comparable

C4ai Aya Expanse 32b: 23.3 (#180), StarCoder 2 3B: —

Reasoning benchmarks
BenchmarkC4ai Aya Expanse 32bStarCoder 2 3B
LMArena Hard Prompts1193—
Epoch Capabilities Index—88.76
WinoGrande—57.1%

Math Not comparable

C4ai Aya Expanse 32b: 34.0 (#197), StarCoder 2 3B: —

Math benchmarks
BenchmarkC4ai Aya Expanse 32bStarCoder 2 3B
LMArena Math1200—
GSM8K—21.6%

Knowledge Not comparable

C4ai Aya Expanse 32b: 33.2 (#206), StarCoder 2 3B: —

Knowledge benchmarks
BenchmarkC4ai Aya Expanse 32bStarCoder 2 3B
Vectara Hallucination Rate10.9%—
LMArena Expert1182—
ARC (AI2) Challenge—34.2%
MMLU—36.6%

Multilingual Not comparable

C4ai Aya Expanse 32b: 38.4 (#230), StarCoder 2 3B: —

Multilingual benchmarks
BenchmarkC4ai Aya Expanse 32bStarCoder 2 3B
LMArena Non-English1213—
LMArena Chinese1211—
LMArena French1248—
LMArena German1199—
LMArena Japanese1163—
LMArena Korean1158—
LMArena Russian1227—
LMArena Spanish1193—

Instruction Following Not comparable

C4ai Aya Expanse 32b: 62.6 (#237), StarCoder 2 3B: —

Instruction Following benchmarks
BenchmarkC4ai Aya Expanse 32bStarCoder 2 3B
LMArena Instruction Following1196—

Long Context Not comparable

C4ai Aya Expanse 32b: 37.2 (#220), StarCoder 2 3B: —

Long Context benchmarks
BenchmarkC4ai Aya Expanse 32bStarCoder 2 3B
LMArena Longer Query1228—

Writing & Preference Not comparable

C4ai Aya Expanse 32b: 42.2 (#235), StarCoder 2 3B: —

Writing & Preference benchmarks
BenchmarkC4ai Aya Expanse 32bStarCoder 2 3B
LMArena Text1224—
LMArena Creative Writing1200—
LMArena Multi-Turn1190—

Frequently asked questions

Is C4ai Aya Expanse 32b better than StarCoder 2 3B?

C4ai Aya Expanse 32b has enough public results to be ranked (#221); StarCoder 2 3B does not yet, so treat this comparison as directional.

Is C4ai Aya Expanse 32b or StarCoder 2 3B better for coding?

C4ai Aya Expanse 32b scores higher on coding benchmarks: 34.8 versus 33.5 in the Noometry coding category.

How many benchmarks do C4ai Aya Expanse 32b and StarCoder 2 3B share?

0 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and StarCoder 2 3B has 7.

Related comparisons

Go deeper