Noometry

Model comparison

C4ai Aya Expanse 32b vs o1

o1 is the stronger model overall, scoring 40.9 to 35.9 on the Noometry Index.

Last verified . 17 shared benchmarks.

C4ai Aya Expanse 32b Cohere

35.9

Rank #221 Confirmed

o1 OpenAI

40.9

Rank #143 Confirmed

Summary

  • They share 17 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 0 categories and o1 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where o1 leads 55.6 to 42.2.
  • o1 accepts more context: 200K tokens versus 128K.
  • C4ai Aya Expanse 32b has downloadable open weights; the other is API-only.

Side by side

C4ai Aya Expanse 32bo1
ProviderCohereOpenAI
Noometry Index35.940.9
Released2024-10-242024-09-12
WeightsOpenProprietary
Context window128K200K
Max output4K100K
Input $ / M tokens—$15
Output $ / M tokens—$60
Results tracked1852

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

Category by category

Coding o1 leads

C4ai Aya Expanse 32b: 34.8 (#231), o1: 46.1 (#70)

BenchmarkC4ai Aya Expanse 32bo1
LMArena Coding11971367
Aider Polyglot—61.7%
WeirdML—47.6%
LiveBench Coding—69.7%
CadEval—56%
HumanEval+—89%
MBPP+—80.2%

Agentic & Tool Use Not comparable

C4ai Aya Expanse 32b: —, o1: 24.6 (#117)

BenchmarkC4ai Aya Expanse 32bo1
Cybench—10%
METR Time Horizons—51.1%

Reasoning o1 leads

C4ai Aya Expanse 32b: 23.3 (#180), o1: 27.9 (#111)

BenchmarkC4ai Aya Expanse 32bo1
LMArena Hard Prompts11931371
SimpleBench—41.7%
ARC-AGI-1—30.7%
Chess Puzzles—15%
EnigmaEval—5.7%
LiveBench Reasoning—91.6%
DTBench—74.7%
LiveBench Data Analysis—65.5%
LMCA—22.3%
Epoch Capabilities Index—141.91
LiveBench—75.7%

Math o1 leads

C4ai Aya Expanse 32b: 34.0 (#197), o1: 36.1 (#175)

BenchmarkC4ai Aya Expanse 32bo1
LMArena Math12001388
FrontierMath (Tiers 1-3)—14.7%
OTIS Mock AIME 2024-2025—73.3%
LiveBench Math—80.3%
MATH Level 5—94.7%
FrontierMath (Feb 2025 set)—9.3%

Knowledge o1 leads

C4ai Aya Expanse 32b: 33.2 (#206), o1: 41.5 (#110)

BenchmarkC4ai Aya Expanse 32bo1
LMArena Expert11821361
GPQA Diamond—76.8%
Humanity's Last Exam—8%
SimpleQA Verified—41.1%
Confabulations—11.7%
Vectara Hallucination Rate10.9%—

Multimodal Not comparable

C4ai Aya Expanse 32b: —, o1: 34.2 (#93)

BenchmarkC4ai Aya Expanse 32bo1
LMArena Vision—1168
GeoBench—80%
VPCT—37%
SpatialViz-Bench—41.4%

Multilingual o1 leads

C4ai Aya Expanse 32b: 38.4 (#230), o1: 48.6 (#142)

BenchmarkC4ai Aya Expanse 32bo1
LMArena Non-English12131358
LMArena Chinese12111394
LMArena French12481344
LMArena German11991337
LMArena Japanese11631346
LMArena Korean11581396
LMArena Russian12271356
LMArena Spanish11931345

Instruction Following o1 leads

C4ai Aya Expanse 32b: 62.6 (#237), o1: 74.8 (#86)

BenchmarkC4ai Aya Expanse 32bo1
LMArena Instruction Following11961367
LiveBench Instruction Following—81.5%

Long Context o1 leads

C4ai Aya Expanse 32b: 37.2 (#220), o1: 50.3 (#9)

BenchmarkC4ai Aya Expanse 32bo1
LMArena Longer Query12281378
Fiction.LiveBench—83.3%

Writing & Preference o1 leads

C4ai Aya Expanse 32b: 42.2 (#235), o1: 55.6 (#144)

BenchmarkC4ai Aya Expanse 32bo1
LMArena Text12241366
LMArena Creative Writing12001348
LMArena Multi-Turn11901369
Short-Story Creative Writing—70.2%
LiveBench Language—65.4%

Frequently asked questions

Is C4ai Aya Expanse 32b better than o1?

o1 is the stronger model overall, scoring 40.9 to 35.9 on the Noometry Index.

Is C4ai Aya Expanse 32b or o1 better for coding?

o1 scores higher on coding benchmarks: 46.1 versus 34.8 in the Noometry coding category.

Which has the bigger context window?

o1 does, with 200K tokens against 128K.

How many benchmarks do C4ai Aya Expanse 32b and o1 share?

17 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and o1 has 52.

Related comparisons

Go deeper