Model comparison
C4ai Aya Expanse 32b vs Step 3.7 Flash
Step 3.7 Flash is the stronger model overall, scoring 36.5 to 35.3 on the Noometry Index.
Last verified . 0 shared benchmarks.
Cohere
StepFunSummary
- The widest gap is in math, where Step 3.7 Flash leads 40.9 to 31.4.
- Step 3.7 Flash accepts more context: 256K tokens versus 128K.
Side by side
| C4ai Aya Expanse 32b | Step 3.7 Flash | |
|---|---|---|
| Provider | Cohere | StepFun |
| Noometry Index | 35.3 | 36.5 |
| Released | 2024-10-24 | 2026-05-29 |
| Weights | Open | Open |
| Context window | 128K | 256K |
| Max output | 4K | 256K |
| Input $ / M tokens | — | $0.18 |
| Output $ / M tokens | — | $1.11 |
| Results tracked | 18 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.7 Flash leads
C4ai Aya Expanse 32b: 34.3 (#227), Step 3.7 Flash: 39.4 (#147)
| Benchmark | C4ai Aya Expanse 32b | Step 3.7 Flash |
|---|---|---|
| SciCode | — | 40% |
| LMArena Coding | 1197 | — |
| ALE-Bench | — | 694.12 |
Reasoning C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 22.3 (#183), Step 3.7 Flash: 20.9 (#211)
| Benchmark | C4ai Aya Expanse 32b | Step 3.7 Flash |
|---|---|---|
| NYT Connections (extended) | — | 39.7% |
| CritPt | — | 2.3% |
| LMArena Hard Prompts | 1193 | — |
Math Step 3.7 Flash leads
C4ai Aya Expanse 32b: 31.4 (#195), Step 3.7 Flash: 40.9 (#74)
| Benchmark | C4ai Aya Expanse 32b | Step 3.7 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 68.5% |
| LMArena Math | 1200 | — |
Knowledge Not comparable
C4ai Aya Expanse 32b: 32.6 (#202), Step 3.7 Flash: —
| Benchmark | C4ai Aya Expanse 32b | Step 3.7 Flash |
|---|---|---|
| Vectara Hallucination Rate | 10.9% | — |
| LMArena Expert | 1182 | — |
Multilingual Not comparable
C4ai Aya Expanse 32b: 38.5 (#225), Step 3.7 Flash: —
| Benchmark | C4ai Aya Expanse 32b | Step 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1213 | — |
| LMArena Chinese | 1210 | — |
| LMArena French | 1247 | — |
| LMArena German | 1199 | — |
| LMArena Japanese | 1163 | — |
| LMArena Korean | 1158 | — |
| LMArena Russian | 1227 | — |
| LMArena Spanish | 1193 | — |
Instruction Following Not comparable
C4ai Aya Expanse 32b: 62.9 (#232), Step 3.7 Flash: —
| Benchmark | C4ai Aya Expanse 32b | Step 3.7 Flash |
|---|---|---|
| LMArena Instruction Following | 1196 | — |
Long Context Not comparable
C4ai Aya Expanse 32b: 37.2 (#215), Step 3.7 Flash: —
| Benchmark | C4ai Aya Expanse 32b | Step 3.7 Flash |
|---|---|---|
| LMArena Longer Query | 1228 | — |
Writing & Preference Not comparable
C4ai Aya Expanse 32b: 42.4 (#230), Step 3.7 Flash: —
| Benchmark | C4ai Aya Expanse 32b | Step 3.7 Flash |
|---|---|---|
| LMArena Text | 1224 | — |
| LMArena Creative Writing | 1200 | — |
| LMArena Multi-Turn | 1190 | — |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Step 3.7 Flash?
Step 3.7 Flash is the stronger model overall, scoring 36.5 to 35.3 on the Noometry Index.
Is C4ai Aya Expanse 32b or Step 3.7 Flash better for coding?
Step 3.7 Flash scores higher on coding benchmarks: 39.4 versus 34.3 in the Noometry coding category.
Which has the bigger context window?
Step 3.7 Flash does, with 256K tokens against 128K.
How many benchmarks do C4ai Aya Expanse 32b and Step 3.7 Flash share?
0 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Step 3.7 Flash has 5.