Noometry

Model comparison

C4ai Aya Expanse 32b vs Claude 2

C4ai Aya Expanse 32b is the stronger model overall, scoring 35.9 to 25.0 on the Noometry Index.

Last verified . 0 shared benchmarks.

C4ai Aya Expanse 32b Cohere

35.9

Rank #221 Confirmed

Claude 2 Anthropic

25.0

Rank #346 Reported

Summary

  • The widest gap is in math, where C4ai Aya Expanse 32b leads 34.0 to 9.3.
  • C4ai Aya Expanse 32b has downloadable open weights; the other is API-only.

Side by side

C4ai Aya Expanse 32bClaude 2
ProviderCohereAnthropic
Noometry Index35.925.0
Released2024-10-242023-07-11
WeightsOpenProprietary
Context window128K—
Max output4K—
Input $ / M tokens——
Output $ / M tokens——
Results tracked188

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

Category by category

Coding Not comparable

C4ai Aya Expanse 32b: 34.8 (#231), Claude 2: —

BenchmarkC4ai Aya Expanse 32bClaude 2
LMArena Coding1197—
HumanEval+—61.6%

Reasoning C4ai Aya Expanse 32b leads

C4ai Aya Expanse 32b: 23.3 (#180), Claude 2: 21.7 (#216)

BenchmarkC4ai Aya Expanse 32bClaude 2
LMArena Hard Prompts1193—
DTBench—51.9%
Epoch Capabilities Index—120.13

Math C4ai Aya Expanse 32b leads

C4ai Aya Expanse 32b: 34.0 (#197), Claude 2: 9.3 (#320)

BenchmarkC4ai Aya Expanse 32bClaude 2
OTIS Mock AIME 2024-2025—2.5%
LMArena Math1200—
MATH Level 5—11.7%

Knowledge C4ai Aya Expanse 32b leads

C4ai Aya Expanse 32b: 33.2 (#206), Claude 2: 16.9 (#287)

BenchmarkC4ai Aya Expanse 32bClaude 2
GPQA Diamond—34.7%
Vectara Hallucination Rate10.9%—
LMArena Expert1182—
MMLU—78.5%
TriviaQA—87.5%

Multilingual Not comparable

C4ai Aya Expanse 32b: 38.4 (#230), Claude 2: —

BenchmarkC4ai Aya Expanse 32bClaude 2
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), Claude 2: —

BenchmarkC4ai Aya Expanse 32bClaude 2
LMArena Instruction Following1196—

Long Context Not comparable

C4ai Aya Expanse 32b: 37.2 (#220), Claude 2: —

BenchmarkC4ai Aya Expanse 32bClaude 2
LMArena Longer Query1228—

Writing & Preference Not comparable

C4ai Aya Expanse 32b: 42.2 (#235), Claude 2: —

BenchmarkC4ai Aya Expanse 32bClaude 2
LMArena Text1224—
LMArena Creative Writing1200—
LMArena Multi-Turn1190—

Frequently asked questions

Is C4ai Aya Expanse 32b better than Claude 2?

C4ai Aya Expanse 32b is the stronger model overall, scoring 35.9 to 25.0 on the Noometry Index.

How many benchmarks do C4ai Aya Expanse 32b and Claude 2 share?

0 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Claude 2 has 8.

Related comparisons

Go deeper