Noometry

Model comparison

C4ai Aya Expanse 32b vs Phi 3 Small 8k Instruct

C4ai Aya Expanse 32b is the stronger model overall, scoring 35.9 to 29.3 on the Noometry Index.

Last verified . 17 shared benchmarks.

C4ai Aya Expanse 32b Cohere

35.9

Rank #221 Confirmed

Phi 3 Small 8k Instruct Microsoft

29.3

Rank #314 Confirmed

Summary

  • They share 17 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 8 categories and Phi 3 Small 8k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where C4ai Aya Expanse 32b leads 42.2 to 31.1.

Side by side

C4ai Aya Expanse 32bPhi 3 Small 8k Instruct
ProviderCohereMicrosoft
Noometry Index35.929.3
Released2024-10-242024-04-23
WeightsOpenOpen
Context window128K—
Max output4K—
Input $ / M tokens——
Output $ / M tokens——
Results tracked1832

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), Phi 3 Small 8k Instruct: 27.9 (#318)

BenchmarkC4ai Aya Expanse 32bPhi 3 Small 8k Instruct
LMArena Coding11971101
LiveBench Coding—20.3%

Reasoning C4ai Aya Expanse 32b leads

C4ai Aya Expanse 32b: 23.3 (#180), Phi 3 Small 8k Instruct: 14.8 (#323)

BenchmarkC4ai Aya Expanse 32bPhi 3 Small 8k Instruct
LMArena Hard Prompts11931100
LiveBench Reasoning—15.9%
LiveBench Data Analysis—30.3%
Adversarial NLI—58.1%
BIG-Bench Hard—79.1%
HellaSwag—77%
LiveBench—24%
WinoGrande—81.5%

Math C4ai Aya Expanse 32b leads

C4ai Aya Expanse 32b: 34.0 (#197), Phi 3 Small 8k Instruct: 27.6 (#248)

BenchmarkC4ai Aya Expanse 32bPhi 3 Small 8k Instruct
LMArena Math12001151
LiveBench Math—17.6%

Knowledge C4ai Aya Expanse 32b leads

C4ai Aya Expanse 32b: 33.2 (#206), Phi 3 Small 8k Instruct: 29.1 (#240)

BenchmarkC4ai Aya Expanse 32bPhi 3 Small 8k Instruct
LMArena Expert11821067
Vectara Hallucination Rate10.9%—
ARC (AI2) Challenge—90.7%
MMLU—75.7%
OpenBookQA—88%
TriviaQA—58.1%

Multilingual C4ai Aya Expanse 32b leads

C4ai Aya Expanse 32b: 38.4 (#230), Phi 3 Small 8k Instruct: 28.5 (#272)

BenchmarkC4ai Aya Expanse 32bPhi 3 Small 8k Instruct
LMArena Non-English12131058
LMArena Chinese12111061
LMArena French12481135
LMArena German11991080
LMArena Japanese1163966
LMArena Korean1158894
LMArena Russian12271111
LMArena Spanish11931111

Instruction Following C4ai Aya Expanse 32b leads

C4ai Aya Expanse 32b: 62.6 (#237), Phi 3 Small 8k Instruct: 51.9 (#292)

BenchmarkC4ai Aya Expanse 32bPhi 3 Small 8k Instruct
LMArena Instruction Following11961087
LiveBench Instruction Following—47.2%

Long Context C4ai Aya Expanse 32b leads

C4ai Aya Expanse 32b: 37.2 (#220), Phi 3 Small 8k Instruct: 33.0 (#267)

BenchmarkC4ai Aya Expanse 32bPhi 3 Small 8k Instruct
LMArena Longer Query12281088

Writing & Preference C4ai Aya Expanse 32b leads

C4ai Aya Expanse 32b: 42.2 (#235), Phi 3 Small 8k Instruct: 31.1 (#284)

BenchmarkC4ai Aya Expanse 32bPhi 3 Small 8k Instruct
LMArena Text12241110
LMArena Creative Writing12001083
LMArena Multi-Turn11901068
LiveBench Language—12.9%

Frequently asked questions

Is C4ai Aya Expanse 32b better than Phi 3 Small 8k Instruct?

C4ai Aya Expanse 32b is the stronger model overall, scoring 35.9 to 29.3 on the Noometry Index.

Is C4ai Aya Expanse 32b or Phi 3 Small 8k Instruct better for coding?

C4ai Aya Expanse 32b scores higher on coding benchmarks: 34.8 versus 27.9 in the Noometry coding category.

How many benchmarks do C4ai Aya Expanse 32b and Phi 3 Small 8k Instruct share?

17 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Phi 3 Small 8k Instruct has 32.

Related comparisons

Go deeper