# C4ai Aya Expanse 8b vs Mistral Small

> C4ai Aya Expanse 8b is the stronger model overall, scoring 34.9 to 33.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/c4ai-aya-expanse-8b-vs-mistral-small
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. C4ai Aya Expanse 8b scores higher in 3 categories and Mistral Small in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where C4ai Aya Expanse 8b leads 33.3 to 16.4.

## Snapshot

| | C4ai Aya Expanse 8b | Mistral Small |
|---|---|---|
| Provider | Cohere | Mistral AI |
| Noometry Index | 34.9 | 33.4 |
| Rank | 229 | 243 |
| Context | — | 262K |
| Input $/M | — | $0.15 |
| Output $/M | — | $0.60 |
| Weights | Open | Open |

## Coding

- C4ai Aya Expanse 8b: 33.8 (#252)
- Mistral Small: 34.0 (#247)

| Benchmark | C4ai Aya Expanse 8b | Mistral Small |
|---|---|---|
| LMArena Coding | 1160 | 1362 |
| SciCode | — | 26.5% |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |

## Agentic & Tool Use

- C4ai Aya Expanse 8b: —
- Mistral Small: 28.1 (#93)

| Benchmark | C4ai Aya Expanse 8b | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |

## Reasoning

- C4ai Aya Expanse 8b: 22.4 (#197)
- Mistral Small: 19.8 (#250)

| Benchmark | C4ai Aya Expanse 8b | Mistral Small |
|---|---|---|
| LMArena Hard Prompts | 1156 | 1335 |
| Kagi LLM Benchmark | — | 37.8% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 44.8% |
| DTBench | — | 70.9% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| LiveBench | — | 44% |

## Math

- C4ai Aya Expanse 8b: 33.3 (#203)
- Mistral Small: 16.4 (#293)

| Benchmark | C4ai Aya Expanse 8b | Mistral Small |
|---|---|---|
| LMArena Math | 1168 | 1341 |
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |

## Knowledge

- C4ai Aya Expanse 8b: 33.6 (#201)
- Mistral Small: 31.0 (#222)

| Benchmark | C4ai Aya Expanse 8b | Mistral Small |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | 5.1% |
| LMArena Expert | 1153 | 1291 |
| GPQA Diamond | — | 47.5% |
| MMLU | — | 68.7% |

## Multimodal

- C4ai Aya Expanse 8b: —
- Mistral Small: 33.5 (#96)

| Benchmark | C4ai Aya Expanse 8b | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |

## Multilingual

- C4ai Aya Expanse 8b: 36.1 (#242)
- Mistral Small: 45.5 (#169)

| Benchmark | C4ai Aya Expanse 8b | Mistral Small |
|---|---|---|
| LMArena Non-English | 1180 | 1315 |
| LMArena Chinese | 1181 | 1340 |
| LMArena German | 1188 | 1340 |
| LMArena Japanese | 1120 | 1275 |
| LMArena Russian | 1197 | 1324 |
| LMArena French | — | 1337 |
| LMArena Korean | — | 1259 |
| LMArena Spanish | — | 1346 |

## Instruction Following

- C4ai Aya Expanse 8b: 60.1 (#253)
- Mistral Small: 66.4 (#209)

| Benchmark | C4ai Aya Expanse 8b | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1155 | 1310 |
| LiveBench Instruction Following | — | 63.7% |

## Long Context

- C4ai Aya Expanse 8b: 36.1 (#236)
- Mistral Small: 40.4 (#156)

| Benchmark | C4ai Aya Expanse 8b | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1191 | 1327 |

## Writing & Preference

- C4ai Aya Expanse 8b: 39.0 (#250)
- Mistral Small: 52.5 (#171)

| Benchmark | C4ai Aya Expanse 8b | Mistral Small |
|---|---|---|
| LMArena Text | 1185 | 1338 |
| LMArena Creative Writing | 1168 | 1305 |
| LMArena Multi-Turn | 1160 | 1344 |
| LiveBench Language | — | 30.5% |

## FAQ

### Is C4ai Aya Expanse 8b better than Mistral Small?

C4ai Aya Expanse 8b is the stronger model overall, scoring 34.9 to 33.4 on the Noometry Index.

### Is C4ai Aya Expanse 8b or Mistral Small better for coding?

They score almost the same on coding (33.8 vs 34.0); test both on your own repository before choosing.

### How many benchmarks do C4ai Aya Expanse 8b and Mistral Small share?

15 benchmarks have published results for both models. C4ai Aya Expanse 8b has 15 scored results on Noometry and Mistral Small has 39.