Noometry

Cohere, open weights

Aya Expanse 32B

Aya Expanse 32B by Cohere ranks 235th of 368 ranked models on the Noometry Index as of November 2026, with a score of 36.6. Its strongest category is reasoning, where it ranks 182nd.

Last verified

Noometry rank
#235 of 368
Index score
36.6
Evidence
Confirmed 17 results
Provider
Cohere
Released
Unknown
Weights
Open weights
Reasoning
Unknown
Context window
—
Max output
—
Input price
Not listed
Output price
Not listed
Blended price
Not listed
Output speed
Not measured
Value
Not ranked
Knowledge cutoff
Unknown

Category scores

Each category score combines every public result we have in that category.

  1. Coding 35.4
  2. Reasoning 25.7
  3. Math 36.1
  4. Knowledge 33.3
  5. Multilingual 37.1
  6. Instruction Following 62.4
  7. Long Context 37.1
  8. Writing & Preference 42.3
CategoryScoreRankResults
Coding35.4#2381
Reasoning25.7#1821
Math36.1#2071
Knowledge33.3#2211
Multilingual37.1#2281
Instruction Following62.4#2391
Long Context37.1#2181
Writing & Preference42.3#2433

Strengths and weaknesses

Categories where Aya Expanse 32B places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Reasoning25.7−0.4#182 of 349, top 53%
Math36.1−2.5#207 of 342, top 61%
Knowledge33.3−5.0#221 of 326, top 68%

Weakest categories

CategoryScorevs medianRank
Instruction Following62.4−8.6#239 of 308, top 78%
Multilingual37.1−9.7#228 of 294, top 78%
Writing & Preference42.3−11.3#243 of 317, top 77%

Closest competitors

The models ranked just above and below Aya Expanse 32B. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
Deepseek Coder v2#23136.8——Compare
Llama 3.1 Nemotron 51b Instruct#23236.8——Compare
Nemotron 4 340b Instruct#23336.8——Compare
Llama 3.1 Tulu 3 8b#23436.7——Compare
Qwen3 14B#23636.5$0.6179Compare
Olmo 2 0325 32b Instruct#23736.5——Compare
Amazon Nova Micro 1.0#23836.4$0.0613—Compare
gpt-oss-120b#23936.3$0.070355Compare

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

Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

Coding

BenchmarkScorePositionSettingSourceDate
LMArena Coding1196#240 of 291, top 83%Aya Expanse 32BLMArena2026-10-28

Reasoning

BenchmarkScorePositionSettingSourceDate
LMArena Hard Prompts1193#238 of 294, top 81%Aya Expanse 32BLMArena2026-10-28

Math

BenchmarkScorePositionSettingSourceDate
LMArena Math1200#231 of 283, top 82%Aya Expanse 32BLMArena2026-10-28

Knowledge

BenchmarkScorePositionSettingSourceDate
LMArena Expert1182#224 of 271, top 83%Aya Expanse 32BLMArena2026-10-28

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1213#228 of 294, top 78%Aya Expanse 32BLMArena2026-10-28
LMArena Chinese1211#227 of 281, top 81%Aya Expanse 32BLMArena2026-10-28
LMArena French1248#190 of 229, top 83%Aya Expanse 32BLMArena2026-10-28
LMArena German1199#198 of 236, top 84%Aya Expanse 32BLMArena2026-10-28
LMArena Japanese1163#180 of 218, top 83%Aya Expanse 32BLMArena2026-10-28
LMArena Korean1158#179 of 217, top 83%Aya Expanse 32BLMArena2026-10-28
LMArena Russian1227#223 of 280, top 80%Aya Expanse 32BLMArena2026-10-28
LMArena Spanish1193#200 of 229, top 88%Aya Expanse 32BLMArena2026-10-28

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1196#236 of 294, top 81%Aya Expanse 32BLMArena2026-10-28

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1227#229 of 287, top 80%Aya Expanse 32BLMArena2026-10-28

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1224#233 of 294, top 80%Aya Expanse 32BLMArena2026-10-28
LMArena Creative Writing1200#231 of 292, top 80%Aya Expanse 32BLMArena2026-10-28
LMArena Multi-Turn1190#238 of 292, top 82%Aya Expanse 32BLMArena2026-10-28

Compare Aya Expanse 32B

Other Cohere models

Frequently asked questions

How good is Aya Expanse 32B?

Aya Expanse 32B by Cohere ranks 235th of 368 ranked models on the Noometry Index as of November 2026, with a score of 36.6. Its strongest category is reasoning, where it ranks 182nd.

Is Aya Expanse 32B open source?

Yes. Aya Expanse 32B's weights are downloadable; check the license for commercial terms.

What are Aya Expanse 32B's strengths and weaknesses?

Relative to other ranked models, Aya Expanse 32B places best in reasoning, math, knowledge and lowest in instruction following, multilingual, writing & preference.

What is Aya Expanse 32B best at?

Its best category is reasoning, where it ranks 182nd on Noometry.