Model comparison
C4ai Aya Expanse 32b vs Step 3
Step 3 is the stronger model overall, scoring 39.9 to 35.3 on the Noometry Index.
Last verified . 15 shared benchmarks.
Cohere
StepFunSummary
- They share 15 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3 leads 54.5 to 42.4.
Side by side
| C4ai Aya Expanse 32b | Step 3 | |
|---|---|---|
| Provider | Cohere | StepFun |
| Noometry Index | 35.3 | 39.9 |
| Released | 2024-10-24 | — |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
C4ai Aya Expanse 32b: 34.3 (#227), Step 3: 39.5 (#144)
| Benchmark | C4ai Aya Expanse 32b | Step 3 |
|---|---|---|
| LMArena Coding | 1197 | 1367 |
Reasoning Step 3 leads
C4ai Aya Expanse 32b: 22.3 (#183), Step 3: 27.6 (#102)
| Benchmark | C4ai Aya Expanse 32b | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1193 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
Math Step 3 leads
C4ai Aya Expanse 32b: 31.4 (#195), Step 3: 34.9 (#148)
| Benchmark | C4ai Aya Expanse 32b | Step 3 |
|---|---|---|
| LMArena Math | 1200 | 1366 |
Knowledge Step 3 leads
C4ai Aya Expanse 32b: 32.6 (#202), Step 3: 36.2 (#161)
| Benchmark | C4ai Aya Expanse 32b | Step 3 |
|---|---|---|
| LMArena Expert | 1182 | 1333 |
| Vectara Hallucination Rate | 10.9% | — |
Multimodal Not comparable
C4ai Aya Expanse 32b: —, Step 3: 34.9 (#81)
| Benchmark | C4ai Aya Expanse 32b | Step 3 |
|---|---|---|
| LMArena Vision | — | 1176 |
Multilingual Step 3 leads
C4ai Aya Expanse 32b: 38.5 (#225), Step 3: 46.5 (#154)
| Benchmark | C4ai Aya Expanse 32b | Step 3 |
|---|---|---|
| LMArena Non-English | 1213 | 1327 |
| LMArena Chinese | 1210 | 1396 |
| LMArena German | 1199 | 1371 |
| LMArena Korean | 1158 | 1271 |
| LMArena Russian | 1227 | 1331 |
| LMArena Spanish | 1193 | 1372 |
| LMArena French | 1247 | — |
| LMArena Japanese | 1163 | — |
Instruction Following Step 3 leads
C4ai Aya Expanse 32b: 62.9 (#232), Step 3: 70.6 (#159)
| Benchmark | C4ai Aya Expanse 32b | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1196 | 1332 |
Long Context Step 3 leads
C4ai Aya Expanse 32b: 37.2 (#215), Step 3: 40.3 (#152)
| Benchmark | C4ai Aya Expanse 32b | Step 3 |
|---|---|---|
| LMArena Longer Query | 1228 | 1326 |
Writing & Preference Step 3 leads
C4ai Aya Expanse 32b: 42.4 (#230), Step 3: 54.5 (#146)
| Benchmark | C4ai Aya Expanse 32b | Step 3 |
|---|---|---|
| LMArena Text | 1224 | 1351 |
| LMArena Creative Writing | 1200 | 1322 |
| LMArena Multi-Turn | 1190 | 1340 |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Step 3?
Step 3 is the stronger model overall, scoring 39.9 to 35.3 on the Noometry Index.
Is C4ai Aya Expanse 32b or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 39.5 versus 34.3 in the Noometry coding category.
How many benchmarks do C4ai Aya Expanse 32b and Step 3 share?
15 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Step 3 has 17.