Model comparison
C4ai Aya Expanse 32b vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 35.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
Cohere
StepFunSummary
- They share 13 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 5 Preview leads 62.8 to 42.2.
- Step 5 Preview accepts more context: 1.02M tokens versus 128K.
- C4ai Aya Expanse 32b has downloadable open weights; the other is API-only.
Side by side
| C4ai Aya Expanse 32b | Step 5 Preview | |
|---|---|---|
| Provider | Cohere | StepFun |
| Noometry Index | 35.9 | 47.9 |
| Released | 2024-10-24 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | 128K | 1.02M |
| Max output | 4K | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 18 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
C4ai Aya Expanse 32b: 34.8 (#231), Step 5 Preview: 51.8 (#36)
| Benchmark | C4ai Aya Expanse 32b | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1197 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
Reasoning Step 5 Preview leads
C4ai Aya Expanse 32b: 23.3 (#180), Step 5 Preview: 40.0 (#57)
| Benchmark | C4ai Aya Expanse 32b | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1193 | 1465 |
| CritPt | — | 20.9% |
Math Step 5 Preview leads
C4ai Aya Expanse 32b: 34.0 (#197), Step 5 Preview: 46.1 (#72)
| Benchmark | C4ai Aya Expanse 32b | Step 5 Preview |
|---|---|---|
| LMArena Math | 1200 | 1470 |
| ProofBench | — | 42% |
Knowledge Step 5 Preview leads
C4ai Aya Expanse 32b: 33.2 (#206), Step 5 Preview: 41.2 (#112)
| Benchmark | C4ai Aya Expanse 32b | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1182 | 1470 |
| Vectara Hallucination Rate | 10.9% | — |
Multimodal Not comparable
C4ai Aya Expanse 32b: —, Step 5 Preview: 41.0 (#41)
| Benchmark | C4ai Aya Expanse 32b | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Step 5 Preview leads
C4ai Aya Expanse 32b: 38.4 (#230), Step 5 Preview: 53.8 (#54)
| Benchmark | C4ai Aya Expanse 32b | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1213 | 1432 |
| LMArena Chinese | 1211 | 1519 |
| LMArena Russian | 1227 | 1436 |
| LMArena Spanish | 1193 | 1439 |
| LMArena French | 1248 | — |
| LMArena German | 1199 | — |
| LMArena Japanese | 1163 | — |
| LMArena Korean | 1158 | — |
Instruction Following Step 5 Preview leads
C4ai Aya Expanse 32b: 62.6 (#237), Step 5 Preview: 76.0 (#50)
| Benchmark | C4ai Aya Expanse 32b | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1196 | 1444 |
Long Context Step 5 Preview leads
C4ai Aya Expanse 32b: 37.2 (#220), Step 5 Preview: 44.5 (#64)
| Benchmark | C4ai Aya Expanse 32b | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1228 | 1455 |
Writing & Preference Step 5 Preview leads
C4ai Aya Expanse 32b: 42.2 (#235), Step 5 Preview: 62.8 (#71)
| Benchmark | C4ai Aya Expanse 32b | Step 5 Preview |
|---|---|---|
| LMArena Text | 1224 | 1442 |
| LMArena Creative Writing | 1200 | 1410 |
| LMArena Multi-Turn | 1190 | 1447 |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 35.9 on the Noometry Index.
Is C4ai Aya Expanse 32b or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 34.8 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 128K.
How many benchmarks do C4ai Aya Expanse 32b and Step 5 Preview share?
13 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Step 5 Preview has 18.