Model comparison
C4ai Aya Expanse 32b vs Llama 13b
C4ai Aya Expanse 32b is the stronger model overall, scoring 35.9 to 24.4 on the Noometry Index.
Last verified . 8 shared benchmarks.
Cohere
MetaSummary
- They share 8 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 6 categories and Llama 13b in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where C4ai Aya Expanse 32b leads 42.2 to 13.8.
Side by side
| C4ai Aya Expanse 32b | Llama 13b | |
|---|---|---|
| Provider | Cohere | Meta |
| Noometry Index | 35.9 | 24.4 |
| Released | 2024-10-24 | 2023-02-24 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 21 |
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: 34.8 (#231), Llama 13b: 21.4 (#337)
| Benchmark | C4ai Aya Expanse 32b | Llama 13b |
|---|---|---|
| LMArena Coding | 1197 | 683 |
Reasoning C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 23.3 (#180), Llama 13b: 14.0 (#329)
| Benchmark | C4ai Aya Expanse 32b | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1193 | 728 |
| BIG-Bench Hard | — | 37.9% |
| Epoch Capabilities Index | — | 100.58 |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |
Math C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 34.0 (#197), Llama 13b: 26.7 (#256)
| Benchmark | C4ai Aya Expanse 32b | Llama 13b |
|---|---|---|
| LMArena Math | 1200 | 838 |
| GSM8K | — | 20.6% |
Knowledge Not comparable
C4ai Aya Expanse 32b: 33.2 (#206), Llama 13b: —
| Benchmark | C4ai Aya Expanse 32b | Llama 13b |
|---|---|---|
| Vectara Hallucination Rate | 10.9% | — |
| LMArena Expert | 1182 | — |
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| MMLU | — | 47.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |
Multimodal Not comparable
C4ai Aya Expanse 32b: —, Llama 13b: —
| Benchmark | C4ai Aya Expanse 32b | Llama 13b |
|---|---|---|
| ScienceQA | — | 43.3% |
Multilingual C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 38.4 (#230), Llama 13b: 16.6 (#297)
| Benchmark | C4ai Aya Expanse 32b | Llama 13b |
|---|---|---|
| LMArena Non-English | 1213 | 819 |
| LMArena Chinese | 1211 | — |
| LMArena French | 1248 | — |
| LMArena German | 1199 | — |
| LMArena Japanese | 1163 | — |
| LMArena Korean | 1158 | — |
| LMArena Russian | 1227 | — |
| LMArena Spanish | 1193 | — |
Instruction Following C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 62.6 (#237), Llama 13b: 36.7 (#305)
| Benchmark | C4ai Aya Expanse 32b | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1196 | 781 |
Long Context Not comparable
C4ai Aya Expanse 32b: 37.2 (#220), Llama 13b: —
| Benchmark | C4ai Aya Expanse 32b | Llama 13b |
|---|---|---|
| LMArena Longer Query | 1228 | — |
Writing & Preference C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 42.2 (#235), Llama 13b: 13.8 (#312)
| Benchmark | C4ai Aya Expanse 32b | Llama 13b |
|---|---|---|
| LMArena Text | 1224 | 834 |
| LMArena Creative Writing | 1200 | 794 |
| LMArena Multi-Turn | 1190 | 753 |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Llama 13b?
C4ai Aya Expanse 32b is the stronger model overall, scoring 35.9 to 24.4 on the Noometry Index.
Is C4ai Aya Expanse 32b or Llama 13b better for coding?
C4ai Aya Expanse 32b scores higher on coding benchmarks: 34.8 versus 21.4 in the Noometry coding category.
How many benchmarks do C4ai Aya Expanse 32b and Llama 13b share?
8 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Llama 13b has 21.