Model comparison
Command R vs StarCoder 2 3B
Command R has enough public results to be ranked (#267); StarCoder 2 3B does not yet, so treat this comparison as directional.
Last verified . 2 shared benchmarks.
Cohere
NVIDIASummary
- They share 2 benchmarks with published results for both. Command R scores higher in 0 categories and StarCoder 2 3B in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where StarCoder 2 3B leads 32.9 to 28.8.
- The biggest single-benchmark swing is BigCodeBench Complete: 45.2% for Command R and 21.4% for StarCoder 2 3B.
Side by side
| Command R | StarCoder 2 3B | |
|---|---|---|
| Provider | Cohere | NVIDIA |
| Noometry Index | 31.0 | 35.8 |
| Released | 2024-08-30 | 2024-02-22 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 29 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding StarCoder 2 3B leads
Command R: 28.8 (#301), StarCoder 2 3B: 32.9
| Benchmark | Command R | StarCoder 2 3B |
|---|---|---|
| BigCodeBench Complete | 45.2% | 21.4% |
| BigCodeBench Instruct | 37.1% | — |
| LiveBench Coding | 17.9% | — |
| LMArena Coding | 1170 | — |
| HumanEval+ | — | 27.4% |
Reasoning Not comparable
Command R: 13.3 (#329), StarCoder 2 3B: —
| Benchmark | Command R | StarCoder 2 3B |
|---|---|---|
| LiveBench Reasoning | 21.9% | — |
| LMArena Hard Prompts | 1164 | — |
| DTBench | 46.4% | — |
| LiveBench Data Analysis | 33.3% | — |
| LMCA | 9.2% | — |
| Epoch Capabilities Index | — | 88.01 |
| LiveBench | 27.5% | — |
| WinoGrande | — | 57.1% |
Math Not comparable
Command R: 25.8 (#244), StarCoder 2 3B: —
| Benchmark | Command R | StarCoder 2 3B |
|---|---|---|
| LiveBench Math | 19.4% | — |
| LMArena Math | 1155 | — |
| GSM8K | — | 21.6% |
Knowledge Not comparable
Command R: 30.5 (#219), StarCoder 2 3B: —
| Benchmark | Command R | StarCoder 2 3B |
|---|---|---|
| MMLU | 65.2% | 36.6% |
| LMArena Expert | 1138 | — |
| ARC (AI2) Challenge | — | 34.2% |
Multilingual Not comparable
Command R: 35.9 (#240), StarCoder 2 3B: —
| Benchmark | Command R | StarCoder 2 3B |
|---|---|---|
| LMArena Non-English | 1174 | — |
| LMArena Chinese | 1182 | — |
| LMArena French | 1161 | — |
| LMArena German | 1176 | — |
| LMArena Japanese | 1143 | — |
| LMArena Korean | 1162 | — |
| LMArena Russian | 1174 | — |
| LMArena Spanish | 1150 | — |
Instruction Following Not comparable
Command R: 58.3 (#256), StarCoder 2 3B: —
| Benchmark | Command R | StarCoder 2 3B |
|---|---|---|
| LiveBench Instruction Following | 55.6% | — |
| LMArena Instruction Following | 1167 | — |
Long Context Not comparable
Command R: 36.3 (#226), StarCoder 2 3B: —
| Benchmark | Command R | StarCoder 2 3B |
|---|---|---|
| LMArena Longer Query | 1198 | — |
Writing & Preference Not comparable
Command R: 38.4 (#248), StarCoder 2 3B: —
| Benchmark | Command R | StarCoder 2 3B |
|---|---|---|
| LMArena Text | 1187 | — |
| LMArena Creative Writing | 1170 | — |
| LMArena Multi-Turn | 1163 | — |
| LiveBench Language | 16.7% | — |
Frequently asked questions
Is Command R better than StarCoder 2 3B?
Command R has enough public results to be ranked (#267); StarCoder 2 3B does not yet, so treat this comparison as directional.
Is Command R or StarCoder 2 3B better for coding?
StarCoder 2 3B scores higher on coding benchmarks: 32.9 versus 28.8 in the Noometry coding category.
How many benchmarks do Command R and StarCoder 2 3B share?
2 benchmarks have published results for both models. Command R has 29 scored results on Noometry and StarCoder 2 3B has 7.