Model comparison
Command R vs Gemma 2 9B
Command R is the stronger model overall, scoring 31.4 to 25.9 on the Noometry Index.
Last verified . 27 shared benchmarks.
Cohere
GoogleSummary
- They share 27 benchmarks with published results for both. Command R scores higher in 5 categories and Gemma 2 9B in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Command R leads 31.0 to 9.7.
- The biggest single-benchmark swing is LiveBench Language: 16.7% for Command R and 25.5% for Gemma 2 9B.
Side by side
| Command R | Gemma 2 9B | |
|---|---|---|
| Provider | Cohere | |
| Noometry Index | 31.4 | 25.9 |
| Released | 2024-08-30 | 2024-06-24 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 29 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Command R: 29.3 (#306), Gemma 2 9B: 29.4 (#304)
| Benchmark | Command R | Gemma 2 9B |
|---|---|---|
| BigCodeBench Instruct | 37.1% | 34.7% |
| LiveBench Coding | 17.9% | 22.5% |
| LMArena Coding | 1169 | 1173 |
| BigCodeBench Complete | 45.2% | 40.6% |
Reasoning Gemma 2 9B leads
Command R: 13.8 (#331), Gemma 2 9B: 15.9 (#309)
| Benchmark | Command R | Gemma 2 9B |
|---|---|---|
| LiveBench Reasoning | 21.9% | 15.2% |
| LMArena Hard Prompts | 1164 | 1171 |
| LiveBench Data Analysis | 33.3% | 36.4% |
| LiveBench | 27.5% | 28.7% |
| DTBench | 46.4% | — |
| LMCA | 9.2% | — |
| Epoch Capabilities Index | — | 119.83 |
| PIQA | — | 83.7% |
Math Command R leads
Command R: 28.0 (#246), Gemma 2 9B: 9.9 (#318)
| Benchmark | Command R | Gemma 2 9B |
|---|---|---|
| LiveBench Math | 19.4% | 19.8% |
| LMArena Math | 1155 | 1183 |
| OTIS Mock AIME 2024-2025 | — | 0.6% |
| MATH Level 5 | — | 21% |
| GSM8K | — | 84.9% |
Knowledge Command R leads
Command R: 31.0 (#221), Gemma 2 9B: 9.7 (#305)
| Benchmark | Command R | Gemma 2 9B |
|---|---|---|
| LMArena Expert | 1138 | 1147 |
| MMLU | 65.2% | 72.1% |
| GPQA Diamond | — | 27.5% |
| BoolQ | — | 85.7% |
Multilingual Too close to call
Command R: 35.7 (#245), Gemma 2 9B: 36.6 (#238)
| Benchmark | Command R | Gemma 2 9B |
|---|---|---|
| LMArena Non-English | 1174 | 1188 |
| LMArena Chinese | 1182 | 1185 |
| LMArena French | 1162 | 1190 |
| LMArena German | 1176 | 1186 |
| LMArena Japanese | 1143 | 1144 |
| LMArena Korean | 1163 | 1137 |
| LMArena Russian | 1174 | 1200 |
| LMArena Spanish | 1151 | 1200 |
Instruction Following Too close to call
Command R: 58.1 (#261), Gemma 2 9B: 57.6 (#269)
| Benchmark | Command R | Gemma 2 9B |
|---|---|---|
| LiveBench Instruction Following | 55.6% | 52.6% |
| LMArena Instruction Following | 1167 | 1178 |
Long Context Too close to call
Command R: 36.3 (#231), Gemma 2 9B: 36.3 (#233)
| Benchmark | Command R | Gemma 2 9B |
|---|---|---|
| LMArena Longer Query | 1198 | 1197 |
Writing & Preference Command R leads
Command R: 38.2 (#254), Gemma 2 9B: 32.1 (#281)
| Benchmark | Command R | Gemma 2 9B |
|---|---|---|
| LMArena Text | 1187 | 1207 |
| LMArena Creative Writing | 1170 | 1206 |
| LMArena Multi-Turn | 1163 | 1193 |
| LiveBench Language | 16.7% | 25.5% |
| EQ-Bench Creative Writing | — | 841 |
Frequently asked questions
Is Command R better than Gemma 2 9B?
Command R is the stronger model overall, scoring 31.4 to 25.9 on the Noometry Index.
Is Command R or Gemma 2 9B better for coding?
They score almost the same on coding (29.3 vs 29.4); test both on your own repository before choosing.
How many benchmarks do Command R and Gemma 2 9B share?
27 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Gemma 2 9B has 35.