# C4ai Aya Expanse 8b vs phi-3-medium 14B

> C4ai Aya Expanse 8b is the stronger model overall, scoring 34.9 to 29.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/c4ai-aya-expanse-8b-vs-phi-3-medium-14b
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in knowledge, where C4ai Aya Expanse 8b leads 33.6 to 9.1.

## Snapshot

| | C4ai Aya Expanse 8b | phi-3-medium 14B |
|---|---|---|
| Provider | Cohere | Microsoft |
| Noometry Index | 34.9 | 29.7 |
| Rank | 229 | 306 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- C4ai Aya Expanse 8b: 33.8 (#252)
- phi-3-medium 14B: 36.8 (#201)

| Benchmark | C4ai Aya Expanse 8b | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1160 | — |
| BigCodeBench Complete | — | 48.7% |

## Reasoning

- C4ai Aya Expanse 8b: 22.4 (#197)
- phi-3-medium 14B: —

| Benchmark | C4ai Aya Expanse 8b | phi-3-medium 14B |
|---|---|---|
| LMArena Hard Prompts | 1156 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.23 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |

## Math

- C4ai Aya Expanse 8b: 33.3 (#203)
- phi-3-medium 14B: 27.3 (#250)

| Benchmark | C4ai Aya Expanse 8b | phi-3-medium 14B |
|---|---|---|
| LMArena Math | 1168 | — |
| MATH Level 5 | — | 17.6% |

## Knowledge

- C4ai Aya Expanse 8b: 33.6 (#201)
- phi-3-medium 14B: 9.1 (#306)

| Benchmark | C4ai Aya Expanse 8b | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| Vectara Hallucination Rate | 9.5% | — |
| LMArena Expert | 1153 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |

## Multilingual

- C4ai Aya Expanse 8b: 36.1 (#242)
- phi-3-medium 14B: —

| Benchmark | C4ai Aya Expanse 8b | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1180 | — |
| LMArena Chinese | 1181 | — |
| LMArena German | 1188 | — |
| LMArena Japanese | 1120 | — |
| LMArena Russian | 1197 | — |

## Instruction Following

- C4ai Aya Expanse 8b: 60.1 (#253)
- phi-3-medium 14B: —

| Benchmark | C4ai Aya Expanse 8b | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1155 | — |

## Long Context

- C4ai Aya Expanse 8b: 36.1 (#236)
- phi-3-medium 14B: —

| Benchmark | C4ai Aya Expanse 8b | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1191 | — |

## Writing & Preference

- C4ai Aya Expanse 8b: 39.0 (#250)
- phi-3-medium 14B: —

| Benchmark | C4ai Aya Expanse 8b | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1185 | — |
| LMArena Creative Writing | 1168 | — |
| LMArena Multi-Turn | 1160 | — |

## FAQ

### Is C4ai Aya Expanse 8b better than phi-3-medium 14B?

C4ai Aya Expanse 8b is the stronger model overall, scoring 34.9 to 29.7 on the Noometry Index.

### Is C4ai Aya Expanse 8b or phi-3-medium 14B better for coding?

phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 33.8 in the Noometry coding category.

### How many benchmarks do C4ai Aya Expanse 8b and phi-3-medium 14B share?

0 benchmarks have published results for both models. C4ai Aya Expanse 8b has 15 scored results on Noometry and phi-3-medium 14B has 13.