Model comparison
Command R vs Gemma 3 4B
Command R is the stronger model overall, scoring 31.0 to 27.9 on the Noometry Index. Gemma 3 4B costs 5.2× less per token, which makes it the better buy when Command R's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
Cohere
GoogleSummary
- They share 14 benchmarks with published results for both. Command R scores higher in 3 categories and Gemma 3 4B in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Command R leads 30.5 to 11.8.
- The biggest single-benchmark swing is LMCA: 9.2% for Command R and 2.8% for Gemma 3 4B.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.15 / $0.60 for Command R.
- Gemma 3 4B accepts more context: 131K tokens versus 128K.
Side by side
| Command R | Gemma 3 4B | |
|---|---|---|
| Provider | Cohere | |
| Noometry Index | 31.0 | 27.9 |
| Released | 2024-08-30 | 2025-03-12 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 4K | 4K |
| Input $ / M tokens | $0.15 | $0.04 |
| Output $ / M tokens | $0.60 | $0.08 |
| Results tracked | 29 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3 4B leads
Command R: 28.8 (#301), Gemma 3 4B: 35.3 (#214)
| Benchmark | Command R | Gemma 3 4B |
|---|---|---|
| LMArena Coding | 1170 | 1230 |
| BigCodeBench Instruct | 37.1% | — |
| LiveBench Coding | 17.9% | — |
| BigCodeBench Complete | 45.2% | — |
Agentic & Tool Use Not comparable
Command R: —, Gemma 3 4B: 20.7 (#134)
| Benchmark | Command R | Gemma 3 4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 19.6% |
Reasoning Too close to call
Command R: 13.3 (#329), Gemma 3 4B: 12.7 (#330)
| Benchmark | Command R | Gemma 3 4B |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1253 |
| DTBench | 46.4% | 50.9% |
| LMCA | 9.2% | 2.8% |
| Kagi LLM Benchmark | — | 25.2% |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 21.9% | — |
| LiveBench Data Analysis | 33.3% | — |
| Epoch Capabilities Index | — | 116.02 |
| LiveBench | 27.5% | — |
Math Command R leads
Command R: 25.8 (#244), Gemma 3 4B: 15.8 (#286)
| Benchmark | Command R | Gemma 3 4B |
|---|---|---|
| LMArena Math | 1155 | 1239 |
| OTIS Mock AIME 2024-2025 | — | 7.5% |
| LiveBench Math | 19.4% | — |
Knowledge Command R leads
Command R: 30.5 (#219), Gemma 3 4B: 11.8 (#294)
| Benchmark | Command R | Gemma 3 4B |
|---|---|---|
| LMArena Expert | 1138 | 1223 |
| GPQA Diamond | — | 23.2% |
| Vectara Hallucination Rate | — | 6.4% |
| MMLU | 65.2% | — |
Multilingual Gemma 3 4B leads
Command R: 35.9 (#240), Gemma 3 4B: 42.7 (#189)
| Benchmark | Command R | Gemma 3 4B |
|---|---|---|
| LMArena Non-English | 1174 | 1273 |
| LMArena German | 1176 | 1281 |
| LMArena Russian | 1174 | 1294 |
| LMArena Chinese | 1182 | — |
| LMArena French | 1161 | — |
| LMArena Japanese | 1143 | — |
| LMArena Korean | 1162 | — |
| LMArena Spanish | 1150 | — |
Instruction Following Gemma 3 4B leads
Command R: 58.3 (#256), Gemma 3 4B: 65.4 (#219)
| Benchmark | Command R | Gemma 3 4B |
|---|---|---|
| LMArena Instruction Following | 1167 | 1239 |
| LiveBench Instruction Following | 55.6% | — |
Long Context Gemma 3 4B leads
Command R: 36.3 (#226), Gemma 3 4B: 38.6 (#189)
| Benchmark | Command R | Gemma 3 4B |
|---|---|---|
| LMArena Longer Query | 1198 | 1274 |
Writing & Preference Gemma 3 4B leads
Command R: 38.4 (#248), Gemma 3 4B: 42.2 (#234)
| Benchmark | Command R | Gemma 3 4B |
|---|---|---|
| LMArena Text | 1187 | 1291 |
| LMArena Creative Writing | 1170 | 1270 |
| LMArena Multi-Turn | 1163 | 1255 |
| EQ-Bench Creative Writing | — | 1068 |
| LiveBench Language | 16.7% | — |
Frequently asked questions
Is Command R better than Gemma 3 4B?
Command R is the stronger model overall, scoring 31.0 to 27.9 on the Noometry Index. Gemma 3 4B costs 5.2× less per token, which makes it the better buy when Command R's lead doesn't matter for your workload.
Which is cheaper, Command R or Gemma 3 4B?
Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Command R lists at $0.15 and $0.60.
Is Command R or Gemma 3 4B better for coding?
Gemma 3 4B scores higher on coding benchmarks: 35.3 versus 28.8 in the Noometry coding category.
Which has the bigger context window?
Gemma 3 4B does, with 131K tokens against 128K.
How many benchmarks do Command R and Gemma 3 4B share?
14 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Gemma 3 4B has 22.