Model comparison
C4ai Aya Expanse 32b vs Gemma 2B
C4ai Aya Expanse 32b is the stronger model overall, scoring 35.3 to 29.1 on the Noometry Index.
Last verified . 11 shared benchmarks.
Cohere
GoogleSummary
- They share 11 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 7 categories and Gemma 2B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where C4ai Aya Expanse 32b leads 42.4 to 24.1.
Side by side
| C4ai Aya Expanse 32b | Gemma 2B | |
|---|---|---|
| Provider | Cohere | |
| Noometry Index | 35.3 | 29.1 |
| Released | 2024-10-24 | 2024-02-21 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 23 |
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: 34.3 (#227), Gemma 2B: 28.9 (#300)
| Benchmark | C4ai Aya Expanse 32b | Gemma 2B |
|---|---|---|
| LMArena Coding | 1197 | 1010 |
| HumanEval+ | — | 20.7% |
| MBPP+ | — | 34.1% |
Reasoning C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 22.3 (#183), Gemma 2B: 17.9 (#275)
| Benchmark | C4ai Aya Expanse 32b | Gemma 2B |
|---|---|---|
| LMArena Hard Prompts | 1193 | 989 |
| BIG-Bench Hard | — | 35.2% |
| Epoch Capabilities Index | — | 93.57 |
| HellaSwag | — | 71.4% |
| PIQA | — | 77.3% |
| WinoGrande | — | 65.4% |
Math C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 31.4 (#195), Gemma 2B: 27.6 (#237)
| Benchmark | C4ai Aya Expanse 32b | Gemma 2B |
|---|---|---|
| LMArena Math | 1200 | 1009 |
| GSM8K | — | 17.7% |
Knowledge Not comparable
C4ai Aya Expanse 32b: 32.6 (#202), Gemma 2B: —
| Benchmark | C4ai Aya Expanse 32b | Gemma 2B |
|---|---|---|
| Vectara Hallucination Rate | 10.9% | — |
| LMArena Expert | 1182 | — |
| ARC (AI2) Challenge | — | 42.1% |
| BoolQ | — | 69.4% |
| MMLU | — | 42.3% |
| TriviaQA | — | 53.2% |
Multilingual C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 38.5 (#225), Gemma 2B: 23.1 (#289)
| Benchmark | C4ai Aya Expanse 32b | Gemma 2B |
|---|---|---|
| LMArena Non-English | 1213 | 958 |
| LMArena Chinese | 1210 | 986 |
| LMArena Russian | 1227 | 937 |
| LMArena French | 1247 | — |
| LMArena German | 1199 | — |
| LMArena Japanese | 1163 | — |
| LMArena Korean | 1158 | — |
| LMArena Spanish | 1193 | — |
Instruction Following C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 62.9 (#232), Gemma 2B: 48.8 (#297)
| Benchmark | C4ai Aya Expanse 32b | Gemma 2B |
|---|---|---|
| LMArena Instruction Following | 1196 | 971 |
Long Context C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 37.2 (#215), Gemma 2B: 29.9 (#286)
| Benchmark | C4ai Aya Expanse 32b | Gemma 2B |
|---|---|---|
| LMArena Longer Query | 1228 | 981 |
Writing & Preference C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 42.4 (#230), Gemma 2B: 24.1 (#303)
| Benchmark | C4ai Aya Expanse 32b | Gemma 2B |
|---|---|---|
| LMArena Text | 1224 | 1002 |
| LMArena Creative Writing | 1200 | 986 |
| LMArena Multi-Turn | 1190 | 945 |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Gemma 2B?
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 Gemma 2B better for coding?
C4ai Aya Expanse 32b scores higher on coding benchmarks: 34.3 versus 28.9 in the Noometry coding category.
How many benchmarks do C4ai Aya Expanse 32b and Gemma 2B share?
11 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Gemma 2B has 23.