Cohere, open weights
C4ai Aya Expanse 8b
C4ai Aya Expanse 8b by Cohere ranks 227th of 349 ranked models on the Noometry Index as of October 2026, with a score of 34.3. Its strongest category is knowledge, where it ranks 197th.
Last verified
Specifications
- Noometry rank
- #227 of 349
- Index score
- 34.3
- Evidence
- Confirmed 15 results
- Provider
Cohere- Released
- October 24, 2024
- Weights
- Open weights
- Reasoning
- No
- Context window
- 8K
- Max output
- 4K
- Input price
- Not listed
- Output price
- Not listed
- Blended price
- Not listed
- Output speed
- Not measured
- Value
- Not ranked
- Knowledge cutoff
- Unknown
- Input
- text
Category scores
Each category score combines every public result we have in that category.
- Coding 33.2
- Reasoning 21.4
- Math 30.8
- Knowledge 33.0
- Multilingual 36.3
- Instruction Following 60.4
- Long Context 36.1
- Writing & Preference 39.2
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 33.2 | #252 | 1 |
| Reasoning | 21.4 | #198 | 1 |
| Math | 30.8 | #204 | 1 |
| Knowledge | 33.0 | #197 | 2 |
| Multilingual | 36.3 | #237 | 1 |
| Instruction Following | 60.4 | #248 | 1 |
| Long Context | 36.1 | #231 | 1 |
| Writing & Preference | 39.2 | #245 | 3 |
Strengths and weaknesses
Categories where C4ai Aya Expanse 8b places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Instruction Following | 60.4 | −10.9 | #248 of 300, top 83% |
| Multilingual | 36.3 | −11.1 | #237 of 292, top 82% |
| Writing & Preference | 39.2 | −14.2 | #245 of 307, top 80% |
Closest competitors
The models ranked just above and below C4ai Aya Expanse 8b. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Gemini 2.0 Flash (Feb 2025) | #223 | 34.8 | — | 92 | Compare |
| Magistral Medium | #224 | 34.8 | $2.75 | 0 | Compare |
| Claude 3.5 Sonnet | #225 | 34.4 | — | — | Compare |
| Qwen Max | #226 | 34.4 | $2.80 | — | Compare |
| Devstral Small 2505 | #228 | 33.9 | $0.15 | 88 | Compare |
| Qwen3 Coder Next | #229 | 33.8 | $0.29 | — | Compare |
| o1-mini | #230 | 33.7 | — | — | Compare |
| Qwen1.5-110B | #231 | 33.6 | — | — | Compare |
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
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Coding | 1161 | #250 of 289, top 87% | LMArena | 2026-09-25 |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Hard Prompts | 1156 | #247 of 292, top 85% | LMArena | 2026-09-25 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Math | 1168 | #237 of 278, top 86% | LMArena | 2026-09-25 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Vectara Hallucination Rate (lower is better) | 9.5% | #49 of 96, top 52% | Vectara Hallucination Leaderboard | ||
| LMArena Expert | 1153 | #229 of 268, top 86% | LMArena | 2026-09-25 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1180 | #237 of 292, top 82% | LMArena | 2026-09-25 | |
| LMArena Chinese | 1181 | #235 of 280, top 84% | LMArena | 2026-09-25 | |
| LMArena German | 1188 | #189 of 225, top 84% | LMArena | 2026-09-25 | |
| LMArena Japanese | 1120 | #176 of 204, top 87% | LMArena | 2026-09-25 | |
| LMArena Russian | 1197 | #230 of 278, top 83% | LMArena | 2026-09-25 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1155 | #247 of 293, top 85% | LMArena | 2026-09-25 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1192 | #240 of 286, top 84% | LMArena | 2026-09-25 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1185 | #245 of 292, top 84% | LMArena | 2026-09-25 | |
| LMArena Creative Writing | 1168 | #241 of 290, top 84% | LMArena | 2026-09-25 | |
| LMArena Multi-Turn | 1160 | #245 of 290, top 85% | LMArena | 2026-09-25 |
Compare C4ai Aya Expanse 8b
- C4ai Aya Expanse 8b vs Qwen Max
- C4ai Aya Expanse 8b vs Devstral Small 2505
- C4ai Aya Expanse 8b vs Claude 3.5 Sonnet
- C4ai Aya Expanse 8b vs Qwen3 Coder Next
- C4ai Aya Expanse 8b vs Magistral Medium
- C4ai Aya Expanse 8b vs o1-mini
- C4ai Aya Expanse 8b vs GPT-6 Astra
- C4ai Aya Expanse 8b vs Claude Fable 5.1
- C4ai Aya Expanse 8b vs Gemini 3.7 Flash
- C4ai Aya Expanse 8b vs Kimi K3
- C4ai Aya Expanse 8b vs Grok 4.6
- C4ai Aya Expanse 8b vs Qwen3.8 Max
- C4ai Aya Expanse 8b vs GLM-5.3
- C4ai Aya Expanse 8b vs Muse Spark 1.3
Other Cohere models
Frequently asked questions
How good is C4ai Aya Expanse 8b?
C4ai Aya Expanse 8b by Cohere ranks 227th of 349 ranked models on the Noometry Index as of October 2026, with a score of 34.3. Its strongest category is knowledge, where it ranks 197th.
What is C4ai Aya Expanse 8b's context window?
C4ai Aya Expanse 8b accepts up to 8K tokens of input and can write up to 4K tokens in one response.
Is C4ai Aya Expanse 8b open source?
Yes. C4ai Aya Expanse 8b's weights are downloadable; check the license for commercial terms.
What are C4ai Aya Expanse 8b's strengths and weaknesses?
Relative to other ranked models, C4ai Aya Expanse 8b places best in reasoning, math, knowledge and lowest in instruction following, multilingual, writing & preference.
What is C4ai Aya Expanse 8b best at?
Its best category is knowledge, where it ranks 197th on Noometry.