Model comparison
Command R+ vs Gemma 2B
Command R+ is the stronger model overall, scoring 32.4 to 29.6 on the Noometry Index.
Last verified . 15 shared benchmarks.
Cohere
GoogleSummary
- They share 15 benchmarks with published results for both. Command R+ scores higher in 4 categories and Gemma 2B in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Command R+ leads 43.5 to 24.0.
Side by side
| Command R+ | Gemma 2B | |
|---|---|---|
| Provider | Cohere | |
| Noometry Index | 32.4 | 29.6 |
| Released | 2024-08-30 | 2024-02-21 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 34 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Command R+: 29.1 (#309), Gemma 2B: 29.4 (#305)
| Benchmark | Command R+ | Gemma 2B |
|---|---|---|
| LMArena Coding | 1187 | 1010 |
| HumanEval+ | 56.7% | 20.7% |
| MBPP+ | 63.5% | 34.1% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
Reasoning Gemma 2B leads
Command R+: 9.2 (#344), Gemma 2B: 18.8 (#275)
| Benchmark | Command R+ | Gemma 2B |
|---|---|---|
| LMArena Hard Prompts | 1186 | 989 |
| Epoch Capabilities Index | 119.34 | 94.2 |
| SimpleBench | 17.4% | — |
| LiveBench Reasoning | 24.8% | — |
| DTBench | 54.9% | — |
| LiveBench Data Analysis | 38.1% | — |
| LMCA | 5% | — |
| BIG-Bench Hard | — | 35.2% |
| HellaSwag | — | 71.4% |
| LiveBench | 31.8% | — |
| PIQA | — | 77.3% |
| WinoGrande | — | 65.4% |
Math Gemma 2B leads
Command R+: 28.9 (#242), Gemma 2B: 30.0 (#239)
| Benchmark | Command R+ | Gemma 2B |
|---|---|---|
| LMArena Math | 1188 | 1009 |
| LiveBench Math | 21.3% | — |
| GSM8K | — | 17.7% |
Knowledge Not comparable
Command R+: 36.4 (#169), Gemma 2B: —
| Benchmark | Command R+ | Gemma 2B |
|---|---|---|
| MMLU | 69.4% | 42.3% |
| Vectara Hallucination Rate | 6.9% | — |
| LMArena Expert | 1174 | — |
| ARC (AI2) Challenge | — | 42.1% |
| BoolQ | — | 69.4% |
| TriviaQA | — | 53.2% |
Multilingual Command R+ leads
Command R+: 38.6 (#227), Gemma 2B: 23.0 (#294)
| Benchmark | Command R+ | Gemma 2B |
|---|---|---|
| LMArena Non-English | 1216 | 958 |
| LMArena Chinese | 1226 | 986 |
| LMArena Russian | 1227 | 937 |
| LMArena French | 1209 | — |
| LMArena German | 1216 | — |
| LMArena Japanese | 1166 | — |
| LMArena Korean | 1138 | — |
| LMArena Spanish | 1189 | — |
Instruction Following Command R+ leads
Command R+: 60.0 (#254), Gemma 2B: 48.5 (#302)
| Benchmark | Command R+ | Gemma 2B |
|---|---|---|
| LMArena Instruction Following | 1197 | 970 |
| LiveBench Instruction Following | 57.6% | — |
Long Context Command R+ leads
Command R+: 37.3 (#219), Gemma 2B: 29.9 (#291)
| Benchmark | Command R+ | Gemma 2B |
|---|---|---|
| LMArena Longer Query | 1230 | 981 |
Writing & Preference Command R+ leads
Command R+: 43.5 (#228), Gemma 2B: 24.0 (#308)
| Benchmark | Command R+ | Gemma 2B |
|---|---|---|
| LMArena Text | 1229 | 1002 |
| LMArena Creative Writing | 1235 | 987 |
| LMArena Multi-Turn | 1213 | 945 |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than Gemma 2B?
Command R+ is the stronger model overall, scoring 32.4 to 29.6 on the Noometry Index.
Is Command R+ or Gemma 2B better for coding?
They score almost the same on coding (29.1 vs 29.4); test both on your own repository before choosing.
How many benchmarks do Command R+ and Gemma 2B share?
15 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Gemma 2B has 23.