Model comparison
C4ai Aya Expanse 8b vs Mistral Large
C4ai Aya Expanse 8b is the stronger model overall, scoring 34.9 to 31.9 on the Noometry Index.
Last verified . 15 shared benchmarks.
Cohere
Mistral AISummary
- They share 15 benchmarks with published results for both. C4ai Aya Expanse 8b scores higher in 3 categories and Mistral Large 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 18.2.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 9.5% for C4ai Aya Expanse 8b and 4.5% for Mistral Large.
Side by side
| C4ai Aya Expanse 8b | Mistral Large | |
|---|---|---|
| Provider | Cohere | Mistral AI |
| Noometry Index | 34.9 | 31.9 |
| Released | — | 2024-02-26 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 15 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
C4ai Aya Expanse 8b: 33.8 (#252), Mistral Large: 34.3 (#240)
| Benchmark | C4ai Aya Expanse 8b | Mistral Large |
|---|---|---|
| LMArena Coding | 1160 | 1277 |
| SciCode | — | 36.2% |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| ALE-Bench | — | 264.7 |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Not comparable
C4ai Aya Expanse 8b: —, Mistral Large: 28.6 (#89)
| Benchmark | C4ai Aya Expanse 8b | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
Reasoning C4ai Aya Expanse 8b leads
C4ai Aya Expanse 8b: 22.4 (#197), Mistral Large: 15.8 (#310)
| Benchmark | C4ai Aya Expanse 8b | Mistral Large |
|---|---|---|
| LMArena Hard Prompts | 1156 | 1257 |
| SimpleBench | — | 22.5% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 43.5% |
| DTBench | — | 65.1% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| Epoch Capabilities Index | — | 128.52 |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |
Math C4ai Aya Expanse 8b leads
C4ai Aya Expanse 8b: 33.3 (#203), Mistral Large: 18.2 (#291)
| Benchmark | C4ai Aya Expanse 8b | Mistral Large |
|---|---|---|
| LMArena Math | 1168 | 1262 |
| OTIS Mock AIME 2024-2025 | — | 8.5% |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge C4ai Aya Expanse 8b leads
C4ai Aya Expanse 8b: 33.6 (#201), Mistral Large: 30.1 (#230)
| Benchmark | C4ai Aya Expanse 8b | Mistral Large |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | 4.5% |
| LMArena Expert | 1153 | 1232 |
| GPQA Diamond | — | 51.3% |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |
Multilingual Mistral Large leads
C4ai Aya Expanse 8b: 36.1 (#242), Mistral Large: 40.0 (#219)
| Benchmark | C4ai Aya Expanse 8b | Mistral Large |
|---|---|---|
| LMArena Non-English | 1180 | 1237 |
| LMArena Chinese | 1181 | 1240 |
| LMArena German | 1188 | 1254 |
| LMArena Japanese | 1120 | 1188 |
| LMArena Russian | 1197 | 1257 |
| LMArena French | — | 1325 |
| LMArena Korean | — | 1202 |
| LMArena Spanish | — | 1268 |
Instruction Following Mistral Large leads
C4ai Aya Expanse 8b: 60.1 (#253), Mistral Large: 67.9 (#191)
| Benchmark | C4ai Aya Expanse 8b | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1155 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context Mistral Large leads
C4ai Aya Expanse 8b: 36.1 (#236), Mistral Large: 38.3 (#199)
| Benchmark | C4ai Aya Expanse 8b | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1191 | 1261 |
Writing & Preference Mistral Large leads
C4ai Aya Expanse 8b: 39.0 (#250), Mistral Large: 40.7 (#242)
| Benchmark | C4ai Aya Expanse 8b | Mistral Large |
|---|---|---|
| LMArena Text | 1185 | 1266 |
| LMArena Creative Writing | 1168 | 1243 |
| LMArena Multi-Turn | 1160 | 1260 |
| Short-Story Creative Writing | — | 69% |
| EQ-Bench Creative Writing | — | 985 |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is C4ai Aya Expanse 8b better than Mistral Large?
C4ai Aya Expanse 8b is the stronger model overall, scoring 34.9 to 31.9 on the Noometry Index.
Is C4ai Aya Expanse 8b or Mistral Large better for coding?
They score almost the same on coding (33.8 vs 34.3); test both on your own repository before choosing.
How many benchmarks do C4ai Aya Expanse 8b and Mistral Large share?
15 benchmarks have published results for both models. C4ai Aya Expanse 8b has 15 scored results on Noometry and Mistral Large has 51.