Model comparison
C4ai Aya Expanse 8b vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 34.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
Cohere
StepFunSummary
- They share 13 benchmarks with published results for both. C4ai Aya Expanse 8b 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 54.3 to 39.0.
Side by side
| C4ai Aya Expanse 8b | Step 3 | |
|---|---|---|
| Provider | Cohere | StepFun |
| Noometry Index | 34.9 | 40.5 |
| Released | — | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
C4ai Aya Expanse 8b: 33.8 (#252), Step 3: 40.1 (#147)
| Benchmark | C4ai Aya Expanse 8b | Step 3 |
|---|---|---|
| LMArena Coding | 1160 | 1367 |
Reasoning Step 3 leads
C4ai Aya Expanse 8b: 22.4 (#197), Step 3: 28.4 (#105)
| Benchmark | C4ai Aya Expanse 8b | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1156 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
Math Step 3 leads
C4ai Aya Expanse 8b: 33.3 (#203), Step 3: 37.6 (#148)
| Benchmark | C4ai Aya Expanse 8b | Step 3 |
|---|---|---|
| LMArena Math | 1168 | 1366 |
Knowledge Step 3 leads
C4ai Aya Expanse 8b: 33.6 (#201), Step 3: 36.8 (#164)
| Benchmark | C4ai Aya Expanse 8b | Step 3 |
|---|---|---|
| LMArena Expert | 1153 | 1333 |
| Vectara Hallucination Rate | 9.5% | — |
Multimodal Not comparable
C4ai Aya Expanse 8b: —, Step 3: 35.5 (#86)
| Benchmark | C4ai Aya Expanse 8b | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
C4ai Aya Expanse 8b: 36.1 (#242), Step 3: 46.3 (#159)
| Benchmark | C4ai Aya Expanse 8b | Step 3 |
|---|---|---|
| LMArena Non-English | 1180 | 1327 |
| LMArena Chinese | 1181 | 1397 |
| LMArena German | 1188 | 1371 |
| LMArena Russian | 1197 | 1331 |
| LMArena Japanese | 1120 | — |
| LMArena Korean | — | 1269 |
| LMArena Spanish | — | 1371 |
Instruction Following Step 3 leads
C4ai Aya Expanse 8b: 60.1 (#253), Step 3: 70.4 (#164)
| Benchmark | C4ai Aya Expanse 8b | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1155 | 1332 |
Long Context Step 3 leads
C4ai Aya Expanse 8b: 36.1 (#236), Step 3: 40.3 (#157)
| Benchmark | C4ai Aya Expanse 8b | Step 3 |
|---|---|---|
| LMArena Longer Query | 1191 | 1326 |
Writing & Preference Step 3 leads
C4ai Aya Expanse 8b: 39.0 (#250), Step 3: 54.3 (#151)
| Benchmark | C4ai Aya Expanse 8b | Step 3 |
|---|---|---|
| LMArena Text | 1185 | 1350 |
| LMArena Creative Writing | 1168 | 1321 |
| LMArena Multi-Turn | 1160 | 1341 |
Frequently asked questions
Is C4ai Aya Expanse 8b better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 34.9 on the Noometry Index.
Is C4ai Aya Expanse 8b or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 33.8 in the Noometry coding category.
How many benchmarks do C4ai Aya Expanse 8b and Step 3 share?
13 benchmarks have published results for both models. C4ai Aya Expanse 8b has 15 scored results on Noometry and Step 3 has 17.