Model comparison
C4ai Aya Expanse 32b vs Gemma 2 27B
C4ai Aya Expanse 32b is the stronger model overall, scoring 35.9 to 29.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Cohere
GoogleSummary
- They share 17 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 5 categories and Gemma 2 27B in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where C4ai Aya Expanse 32b leads 34.0 to 10.7.
- C4ai Aya Expanse 32b accepts more context: 128K tokens versus 8K.
Side by side
| C4ai Aya Expanse 32b | Gemma 2 27B | |
|---|---|---|
| Provider | Cohere | |
| Noometry Index | 35.9 | 29.4 |
| Released | 2024-10-24 | 2024-06-24 |
| Weights | Open | Open |
| Context window | 128K | 8K |
| Max output | 4K | 2K |
| Input $ / M tokens | — | $0.65 |
| Output $ / M tokens | — | $0.65 |
| Results tracked | 18 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
C4ai Aya Expanse 32b: 34.8 (#231), Gemma 2 27B: 34.1 (#246)
| Benchmark | C4ai Aya Expanse 32b | Gemma 2 27B |
|---|---|---|
| LMArena Coding | 1197 | 1211 |
| BigCodeBench Instruct | — | 42.8% |
| LiveBench Coding | — | 36% |
| BigCodeBench Complete | — | 52.5% |
Reasoning C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 23.3 (#180), Gemma 2 27B: 15.3 (#315)
| Benchmark | C4ai Aya Expanse 32b | Gemma 2 27B |
|---|---|---|
| LMArena Hard Prompts | 1193 | 1198 |
| LiveBench Reasoning | — | 28.1% |
| DTBench | — | 48% |
| LiveBench Data Analysis | — | 47.9% |
| LMCA | — | 7.1% |
| Epoch Capabilities Index | — | 122.08 |
| LiveBench | — | 38.2% |
Math C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 34.0 (#197), Gemma 2 27B: 10.7 (#311)
| Benchmark | C4ai Aya Expanse 32b | Gemma 2 27B |
|---|---|---|
| LMArena Math | 1200 | 1212 |
| OTIS Mock AIME 2024-2025 | — | 1.4% |
| LiveBench Math | — | 26.5% |
| MATH Level 5 | — | 27.9% |
Knowledge C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 33.2 (#206), Gemma 2 27B: 19.0 (#280)
| Benchmark | C4ai Aya Expanse 32b | Gemma 2 27B |
|---|---|---|
| LMArena Expert | 1182 | 1172 |
| GPQA Diamond | — | 36.5% |
| Confabulations | — | 27.1% |
| Vectara Hallucination Rate | 10.9% | — |
| MMLU | — | 75.7% |
Multilingual Too close to call
C4ai Aya Expanse 32b: 38.4 (#230), Gemma 2 27B: 38.6 (#226)
| Benchmark | C4ai Aya Expanse 32b | Gemma 2 27B |
|---|---|---|
| LMArena Non-English | 1213 | 1217 |
| LMArena Chinese | 1211 | 1221 |
| LMArena French | 1248 | 1247 |
| LMArena German | 1199 | 1209 |
| LMArena Japanese | 1163 | 1175 |
| LMArena Korean | 1158 | 1174 |
| LMArena Russian | 1227 | 1234 |
| LMArena Spanish | 1193 | 1228 |
Instruction Following C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 62.6 (#237), Gemma 2 27B: 60.5 (#249)
| Benchmark | C4ai Aya Expanse 32b | Gemma 2 27B |
|---|---|---|
| LMArena Instruction Following | 1196 | 1206 |
| LiveBench Instruction Following | — | 58.1% |
Long Context Too close to call
C4ai Aya Expanse 32b: 37.2 (#220), Gemma 2 27B: 37.3 (#218)
| Benchmark | C4ai Aya Expanse 32b | Gemma 2 27B |
|---|---|---|
| LMArena Longer Query | 1228 | 1231 |
Writing & Preference Gemma 2 27B leads
C4ai Aya Expanse 32b: 42.2 (#235), Gemma 2 27B: 44.2 (#225)
| Benchmark | C4ai Aya Expanse 32b | Gemma 2 27B |
|---|---|---|
| LMArena Text | 1224 | 1231 |
| LMArena Creative Writing | 1200 | 1241 |
| LMArena Multi-Turn | 1190 | 1224 |
| LiveBench Language | — | 32.6% |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Gemma 2 27B?
C4ai Aya Expanse 32b is the stronger model overall, scoring 35.9 to 29.4 on the Noometry Index.
Is C4ai Aya Expanse 32b or Gemma 2 27B better for coding?
They score almost the same on coding (34.8 vs 34.1); test both on your own repository before choosing.
Which has the bigger context window?
C4ai Aya Expanse 32b does, with 128K tokens against 8K.
How many benchmarks do C4ai Aya Expanse 32b and Gemma 2 27B share?
17 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Gemma 2 27B has 34.