Model comparison
Command R+ vs Gemma 7B
Command R+ is the stronger model overall, scoring 32.4 to 30.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
Cohere
GoogleSummary
- They share 17 benchmarks with published results for both. Command R+ scores higher in 5 categories and Gemma 7B in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Command R+ leads 43.5 to 27.1.
Side by side
| Command R+ | Gemma 7B | |
|---|---|---|
| Provider | Cohere | |
| Noometry Index | 32.4 | 30.0 |
| 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 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 7B leads
Command R+: 29.1 (#309), Gemma 7B: 30.5 (#294)
| Benchmark | Command R+ | Gemma 7B |
|---|---|---|
| LMArena Coding | 1187 | 1048 |
| HumanEval+ | 56.7% | 28.7% |
| MBPP+ | 63.5% | 43.4% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
Reasoning Gemma 7B leads
Command R+: 9.2 (#344), Gemma 7B: 19.9 (#249)
| Benchmark | Command R+ | Gemma 7B |
|---|---|---|
| LMArena Hard Prompts | 1186 | 1042 |
| Epoch Capabilities Index | 119.34 | 111.99 |
| SimpleBench | 17.4% | — |
| LiveBench Reasoning | 24.8% | — |
| DTBench | 54.9% | — |
| LiveBench Data Analysis | 38.1% | — |
| LMCA | 5% | — |
| Adversarial NLI | — | 48.7% |
| BIG-Bench Hard | — | 55.1% |
| HellaSwag | — | 82.2% |
| LiveBench | 31.8% | — |
| PIQA | — | 81.2% |
| WinoGrande | — | 79% |
Math Gemma 7B leads
Command R+: 28.9 (#242), Gemma 7B: 31.2 (#228)
| Benchmark | Command R+ | Gemma 7B |
|---|---|---|
| LMArena Math | 1188 | 1066 |
| LiveBench Math | 21.3% | — |
| GSM8K | — | 46.4% |
Knowledge Command R+ leads
Command R+: 36.4 (#169), Gemma 7B: 27.3 (#252)
| Benchmark | Command R+ | Gemma 7B |
|---|---|---|
| LMArena Expert | 1174 | 1001 |
| MMLU | 69.4% | 66.1% |
| Vectara Hallucination Rate | 6.9% | — |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 83.2% |
| OpenBookQA | — | 78.6% |
| TriviaQA | — | 72.3% |
Multilingual Command R+ leads
Command R+: 38.6 (#227), Gemma 7B: 25.1 (#287)
| Benchmark | Command R+ | Gemma 7B |
|---|---|---|
| LMArena Non-English | 1216 | 999 |
| LMArena Chinese | 1226 | 1035 |
| LMArena French | 1209 | 1025 |
| LMArena Russian | 1227 | 993 |
| LMArena German | 1216 | — |
| LMArena Japanese | 1166 | — |
| LMArena Korean | 1138 | — |
| LMArena Spanish | 1189 | — |
Instruction Following Command R+ leads
Command R+: 60.0 (#254), Gemma 7B: 51.5 (#295)
| Benchmark | Command R+ | Gemma 7B |
|---|---|---|
| LMArena Instruction Following | 1197 | 1017 |
| LiveBench Instruction Following | 57.6% | — |
Long Context Command R+ leads
Command R+: 37.3 (#219), Gemma 7B: 31.1 (#282)
| Benchmark | Command R+ | Gemma 7B |
|---|---|---|
| LMArena Longer Query | 1230 | 1022 |
Writing & Preference Command R+ leads
Command R+: 43.5 (#228), Gemma 7B: 27.1 (#302)
| Benchmark | Command R+ | Gemma 7B |
|---|---|---|
| LMArena Text | 1229 | 1056 |
| LMArena Creative Writing | 1235 | 1024 |
| LMArena Multi-Turn | 1213 | 963 |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than Gemma 7B?
Command R+ is the stronger model overall, scoring 32.4 to 30.0 on the Noometry Index.
Is Command R+ or Gemma 7B better for coding?
Gemma 7B scores higher on coding benchmarks: 30.5 versus 29.1 in the Noometry coding category.
How many benchmarks do Command R+ and Gemma 7B share?
17 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Gemma 7B has 27.