Model comparison
C4ai Aya Expanse 32b vs phi-3-medium 14B
C4ai Aya Expanse 32b is the stronger model overall, scoring 35.3 to 29.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Cohere
MicrosoftSummary
- The widest gap is in knowledge, where C4ai Aya Expanse 32b leads 32.6 to 9.1.
Side by side
| C4ai Aya Expanse 32b | phi-3-medium 14B | |
|---|---|---|
| Provider | Cohere | Microsoft |
| Noometry Index | 35.3 | 29.1 |
| Released | 2024-10-24 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding phi-3-medium 14B leads
C4ai Aya Expanse 32b: 34.3 (#227), phi-3-medium 14B: 36.3 (#198)
| Benchmark | C4ai Aya Expanse 32b | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1197 | — |
| BigCodeBench Complete | — | 48.7% |
Reasoning Not comparable
C4ai Aya Expanse 32b: 22.3 (#183), phi-3-medium 14B: —
| Benchmark | C4ai Aya Expanse 32b | phi-3-medium 14B |
|---|---|---|
| LMArena Hard Prompts | 1193 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.18 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 31.4 (#195), phi-3-medium 14B: 25.2 (#249)
| Benchmark | C4ai Aya Expanse 32b | phi-3-medium 14B |
|---|---|---|
| LMArena Math | 1200 | — |
| MATH Level 5 | — | 17.6% |
Knowledge C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 32.6 (#202), phi-3-medium 14B: 9.1 (#301)
| Benchmark | C4ai Aya Expanse 32b | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| Vectara Hallucination Rate | 10.9% | — |
| LMArena Expert | 1182 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multilingual Not comparable
C4ai Aya Expanse 32b: 38.5 (#225), phi-3-medium 14B: —
| Benchmark | C4ai Aya Expanse 32b | phi-3-medium 14B |
|---|---|---|
| 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-3-medium 14B: —
| Benchmark | C4ai Aya Expanse 32b | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1196 | — |
Long Context Not comparable
C4ai Aya Expanse 32b: 37.2 (#215), phi-3-medium 14B: —
| Benchmark | C4ai Aya Expanse 32b | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1228 | — |
Writing & Preference Not comparable
C4ai Aya Expanse 32b: 42.4 (#230), phi-3-medium 14B: —
| Benchmark | C4ai Aya Expanse 32b | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1224 | — |
| LMArena Creative Writing | 1200 | — |
| LMArena Multi-Turn | 1190 | — |
Frequently asked questions
Is C4ai Aya Expanse 32b better than phi-3-medium 14B?
C4ai Aya Expanse 32b is the stronger model overall, scoring 35.3 to 29.1 on the Noometry Index.
Is C4ai Aya Expanse 32b or phi-3-medium 14B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.3 versus 34.3 in the Noometry coding category.
How many benchmarks do C4ai Aya Expanse 32b and phi-3-medium 14B share?
0 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and phi-3-medium 14B has 13.