Model comparison
C4ai Aya Expanse 32b vs Phi-4 Mini
C4ai Aya Expanse 32b is the stronger model overall, scoring 35.3 to 30.4 on the Noometry Index.
Last verified . 1 shared benchmarks.
Cohere
MicrosoftSummary
- They share 1 benchmark with published results for both. C4ai Aya Expanse 32b scores higher in 3 categories and Phi-4 Mini in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where C4ai Aya Expanse 32b leads 32.6 to 24.8.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 10.9% for C4ai Aya Expanse 32b and 23.5% for Phi-4 Mini.
Side by side
| C4ai Aya Expanse 32b | Phi-4 Mini | |
|---|---|---|
| Provider | Cohere | Microsoft |
| Noometry Index | 35.3 | 30.4 |
| Released | 2024-10-24 | 2024-12-11 |
| Weights | Open | Open |
| Context window | 128K | 128K |
| Max output | 4K | 4K |
| Input $ / M tokens | — | $0.075 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 18 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 34.3 (#227), Phi-4 Mini: 27.6 (#312)
| Benchmark | C4ai Aya Expanse 32b | Phi-4 Mini |
|---|---|---|
| SciCode | — | 10.8% |
| LMArena Coding | 1197 | — |
Reasoning Too close to call
C4ai Aya Expanse 32b: 22.3 (#183), Phi-4 Mini: 21.7 (#190)
| Benchmark | C4ai Aya Expanse 32b | Phi-4 Mini |
|---|---|---|
| CritPt | — | 0% |
| LMArena Hard Prompts | 1193 | — |
Math Not comparable
C4ai Aya Expanse 32b: 31.4 (#195), Phi-4 Mini: —
| Benchmark | C4ai Aya Expanse 32b | Phi-4 Mini |
|---|---|---|
| LMArena Math | 1200 | — |
Knowledge C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 32.6 (#202), Phi-4 Mini: 24.8 (#261)
| Benchmark | C4ai Aya Expanse 32b | Phi-4 Mini |
|---|---|---|
| Vectara Hallucination Rate | 10.9% | 23.5% |
| LMArena Expert | 1182 | — |
Multilingual Not comparable
C4ai Aya Expanse 32b: 38.5 (#225), Phi-4 Mini: —
| Benchmark | C4ai Aya Expanse 32b | Phi-4 Mini |
|---|---|---|
| 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), Phi-4 Mini: —
| Benchmark | C4ai Aya Expanse 32b | Phi-4 Mini |
|---|---|---|
| LMArena Instruction Following | 1196 | — |
Long Context Not comparable
C4ai Aya Expanse 32b: 37.2 (#215), Phi-4 Mini: —
| Benchmark | C4ai Aya Expanse 32b | Phi-4 Mini |
|---|---|---|
| LMArena Longer Query | 1228 | — |
Writing & Preference Not comparable
C4ai Aya Expanse 32b: 42.4 (#230), Phi-4 Mini: —
| Benchmark | C4ai Aya Expanse 32b | Phi-4 Mini |
|---|---|---|
| LMArena Text | 1224 | — |
| LMArena Creative Writing | 1200 | — |
| LMArena Multi-Turn | 1190 | — |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Phi-4 Mini?
C4ai Aya Expanse 32b is the stronger model overall, scoring 35.3 to 30.4 on the Noometry Index.
Is C4ai Aya Expanse 32b or Phi-4 Mini better for coding?
C4ai Aya Expanse 32b scores higher on coding benchmarks: 34.3 versus 27.6 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do C4ai Aya Expanse 32b and Phi-4 Mini share?
1 benchmark has published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Phi-4 Mini has 3.