Model comparison
Command R+ vs Llama 3.2 3B
Command R+ is the stronger model overall, scoring 32.4 to 28.9 on the Noometry Index. Llama 3.2 3B costs 36× less per token, which makes it the better buy when Command R+'s lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
Cohere
MetaSummary
- They share 15 benchmarks with published results for both. Command R+ scores higher in 6 categories and Llama 3.2 3B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Command R+ leads 43.5 to 24.7.
- The biggest single-benchmark swing is BigCodeBench Complete: 41.9% for Command R+ and 28.3% for Llama 3.2 3B.
- Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $2.50 / $10 for Command R+.
- Llama 3.2 3B accepts more context: 131K tokens versus 128K.
Side by side
| Command R+ | Llama 3.2 3B | |
|---|---|---|
| Provider | Cohere | Meta |
| Noometry Index | 32.4 | 28.9 |
| Released | 2024-08-30 | 2024-09-24 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 4K | 118K |
| Input $ / M tokens | $2.50 | $0.05 |
| Output $ / M tokens | $10 | $0.33 |
| Results tracked | 34 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Command R+ leads
Command R+: 29.1 (#309), Llama 3.2 3B: 27.6 (#319)
| Benchmark | Command R+ | Llama 3.2 3B |
|---|---|---|
| BigCodeBench Instruct | 33.8% | 23.4% |
| LMArena Coding | 1187 | 1098 |
| BigCodeBench Complete | 41.9% | 28.3% |
| LiveBench Coding | 19.1% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Agentic & Tool Use Not comparable
Command R+: —, Llama 3.2 3B: 20.1 (#143)
| Benchmark | Command R+ | Llama 3.2 3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 21.9% |
| BALROG | — | 10.1% |
Reasoning Llama 3.2 3B leads
Command R+: 9.2 (#344), Llama 3.2 3B: 21.0 (#228)
| Benchmark | Command R+ | Llama 3.2 3B |
|---|---|---|
| LMArena Hard Prompts | 1186 | 1095 |
| SimpleBench | 17.4% | — |
| LiveBench Reasoning | 24.8% | — |
| DTBench | 54.9% | — |
| LiveBench Data Analysis | 38.1% | — |
| LMCA | 5% | — |
| Epoch Capabilities Index | 119.34 | — |
| LiveBench | 31.8% | — |
Math Llama 3.2 3B leads
Command R+: 28.9 (#242), Llama 3.2 3B: 32.4 (#214)
| Benchmark | Command R+ | Llama 3.2 3B |
|---|---|---|
| LMArena Math | 1188 | 1126 |
| LiveBench Math | 21.3% | — |
Knowledge Command R+ leads
Command R+: 36.4 (#169), Llama 3.2 3B: 29.7 (#235)
| Benchmark | Command R+ | Llama 3.2 3B |
|---|---|---|
| LMArena Expert | 1174 | 1090 |
| Vectara Hallucination Rate | 6.9% | — |
| MMLU | 69.4% | — |
Multilingual Command R+ leads
Command R+: 38.6 (#227), Llama 3.2 3B: 26.2 (#281)
| Benchmark | Command R+ | Llama 3.2 3B |
|---|---|---|
| LMArena Non-English | 1216 | 1019 |
| LMArena Chinese | 1226 | 1017 |
| LMArena German | 1216 | 1056 |
| LMArena Russian | 1227 | 949 |
| LMArena French | 1209 | — |
| LMArena Japanese | 1166 | — |
| LMArena Korean | 1138 | — |
| LMArena Spanish | 1189 | — |
Instruction Following Command R+ leads
Command R+: 60.0 (#254), Llama 3.2 3B: 56.0 (#275)
| Benchmark | Command R+ | Llama 3.2 3B |
|---|---|---|
| LMArena Instruction Following | 1197 | 1089 |
| LiveBench Instruction Following | 57.6% | — |
Long Context Command R+ leads
Command R+: 37.3 (#219), Llama 3.2 3B: 33.4 (#261)
| Benchmark | Command R+ | Llama 3.2 3B |
|---|---|---|
| LMArena Longer Query | 1230 | 1100 |
Writing & Preference Command R+ leads
Command R+: 43.5 (#228), Llama 3.2 3B: 24.7 (#307)
| Benchmark | Command R+ | Llama 3.2 3B |
|---|---|---|
| LMArena Text | 1229 | 1110 |
| LMArena Creative Writing | 1235 | 1094 |
| LMArena Multi-Turn | 1213 | 1105 |
| EQ-Bench Creative Writing | — | 595 |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than Llama 3.2 3B?
Command R+ is the stronger model overall, scoring 32.4 to 28.9 on the Noometry Index. Llama 3.2 3B costs 36× 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 Llama 3.2 3B?
Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; Command R+ lists at $2.50 and $10.
Is Command R+ or Llama 3.2 3B better for coding?
Command R+ scores higher on coding benchmarks: 29.1 versus 27.6 in the Noometry coding category.
Which has the bigger context window?
Llama 3.2 3B does, with 131K tokens against 128K.
How many benchmarks do Command R+ and Llama 3.2 3B share?
15 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Llama 3.2 3B has 18.