Model comparison

C4ai Aya Expanse 8b vs StarCoder 2 3B

C4ai Aya Expanse 8b has enough public results to be ranked (#229); StarCoder 2 3B does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

C4ai Aya Expanse 8b Cohere

34.9

Rank #229 Confirmed

StarCoder 2 3B NVIDIA

36.3

Unranked Sparse

Side by side

C4ai Aya Expanse 8b and StarCoder 2 3B specifications
C4ai Aya Expanse 8bStarCoder 2 3B
ProviderCohereNVIDIA
Noometry Index34.936.3
Released—2024-02-22
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked157

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

Category by category

Coding Too close to call

C4ai Aya Expanse 8b: 33.8 (#252), StarCoder 2 3B: 33.5

Coding benchmarks
BenchmarkC4ai Aya Expanse 8bStarCoder 2 3B
LMArena Coding1160—
BigCodeBench Complete—21.4%
HumanEval+—27.4%

Reasoning Not comparable

C4ai Aya Expanse 8b: 22.4 (#197), StarCoder 2 3B: —

Reasoning benchmarks
BenchmarkC4ai Aya Expanse 8bStarCoder 2 3B
LMArena Hard Prompts1156—
Epoch Capabilities Index—88.76
WinoGrande—57.1%

Math Not comparable

C4ai Aya Expanse 8b: 33.3 (#203), StarCoder 2 3B: —

Math benchmarks
BenchmarkC4ai Aya Expanse 8bStarCoder 2 3B
LMArena Math1168—
GSM8K—21.6%

Knowledge Not comparable

C4ai Aya Expanse 8b: 33.6 (#201), StarCoder 2 3B: —

Knowledge benchmarks
BenchmarkC4ai Aya Expanse 8bStarCoder 2 3B
Vectara Hallucination Rate9.5%—
LMArena Expert1153—
ARC (AI2) Challenge—34.2%
MMLU—36.6%

Multilingual Not comparable

C4ai Aya Expanse 8b: 36.1 (#242), StarCoder 2 3B: —

Multilingual benchmarks
BenchmarkC4ai Aya Expanse 8bStarCoder 2 3B
LMArena Non-English1180—
LMArena Chinese1181—
LMArena German1188—
LMArena Japanese1120—
LMArena Russian1197—

Instruction Following Not comparable

C4ai Aya Expanse 8b: 60.1 (#253), StarCoder 2 3B: —

Instruction Following benchmarks
BenchmarkC4ai Aya Expanse 8bStarCoder 2 3B
LMArena Instruction Following1155—

Long Context Not comparable

C4ai Aya Expanse 8b: 36.1 (#236), StarCoder 2 3B: —

Long Context benchmarks
BenchmarkC4ai Aya Expanse 8bStarCoder 2 3B
LMArena Longer Query1191—

Writing & Preference Not comparable

C4ai Aya Expanse 8b: 39.0 (#250), StarCoder 2 3B: —

Writing & Preference benchmarks
BenchmarkC4ai Aya Expanse 8bStarCoder 2 3B
LMArena Text1185—
LMArena Creative Writing1168—
LMArena Multi-Turn1160—

Frequently asked questions

Is C4ai Aya Expanse 8b better than StarCoder 2 3B?

C4ai Aya Expanse 8b has enough public results to be ranked (#229); StarCoder 2 3B does not yet, so treat this comparison as directional.

Is C4ai Aya Expanse 8b or StarCoder 2 3B better for coding?

They score almost the same on coding (33.8 vs 33.5); test both on your own repository before choosing.

How many benchmarks do C4ai Aya Expanse 8b and StarCoder 2 3B share?

0 benchmarks have published results for both models. C4ai Aya Expanse 8b has 15 scored results on Noometry and StarCoder 2 3B has 7.

Related comparisons

Go deeper