Model comparison
Command R+ vs Llama-3.3-70B-Instruct
Command R+ is the stronger model overall, scoring 32.4 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct costs 28× less per token, which makes it the better buy when Command R+'s lead doesn't matter for your workload.
Last verified . 32 shared benchmarks.
Cohere
MetaSummary
- They share 32 benchmarks with published results for both. Command R+ scores higher in 3 categories and Llama-3.3-70B-Instruct in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Command R+ leads 28.9 to 15.3.
- The biggest single-benchmark swing is LiveBench Reasoning: 24.8% for Command R+ and 50.8% for Llama-3.3-70B-Instruct.
- Llama-3.3-70B-Instruct is cheaper at $0.10 / $0.32 per million input/output tokens, against $2.50 / $10 for Command R+.
Side by side
| Command R+ | Llama-3.3-70B-Instruct | |
|---|---|---|
| Provider | Cohere | Meta |
| Noometry Index | 32.4 | 30.6 |
| Released | 2024-08-30 | 2024-12-06 |
| Weights | Open | Open |
| Context window | 128K | 128K |
| Max output | 4K | 4K |
| Input $ / M tokens | $2.50 | $0.10 |
| Output $ / M tokens | $10 | $0.32 |
| Results tracked | 34 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama-3.3-70B-Instruct leads
Command R+: 29.1 (#309), Llama-3.3-70B-Instruct: 31.0 (#290)
| Benchmark | Command R+ | Llama-3.3-70B-Instruct |
|---|---|---|
| BigCodeBench Instruct | 33.8% | 46.9% |
| LiveBench Coding | 19.1% | 36.6% |
| LMArena Coding | 1187 | 1268 |
| BigCodeBench Complete | 41.9% | 57.5% |
| SciCode | — | 26% |
| WeirdML | — | 14.4% |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Agentic & Tool Use Not comparable
Command R+: —, Llama-3.3-70B-Instruct: 25.8 (#105)
| Benchmark | Command R+ | Llama-3.3-70B-Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 31.9% |
| BALROG | — | 23% |
Reasoning Llama-3.3-70B-Instruct leads
Command R+: 9.2 (#344), Llama-3.3-70B-Instruct: 14.1 (#327)
| Benchmark | Command R+ | Llama-3.3-70B-Instruct |
|---|---|---|
| SimpleBench | 17.4% | 19.9% |
| LiveBench Reasoning | 24.8% | 50.8% |
| LMArena Hard Prompts | 1186 | 1257 |
| DTBench | 54.9% | 59.5% |
| LiveBench Data Analysis | 38.1% | 49.5% |
| LMCA | 5% | 17.5% |
| Epoch Capabilities Index | 119.34 | 127.33 |
| LiveBench | 31.8% | 50.2% |
| CritPt | — | 0% |
| ForecastBench | — | 58.6 |
Math Command R+ leads
Command R+: 28.9 (#242), Llama-3.3-70B-Instruct: 15.3 (#298)
| Benchmark | Command R+ | Llama-3.3-70B-Instruct |
|---|---|---|
| LiveBench Math | 21.3% | 42.2% |
| LMArena Math | 1188 | 1267 |
| OTIS Mock AIME 2024-2025 | — | 5.1% |
| MATH Level 5 | — | 41.6% |
Knowledge Command R+ leads
Command R+: 36.4 (#169), Llama-3.3-70B-Instruct: 30.6 (#226)
| Benchmark | Command R+ | Llama-3.3-70B-Instruct |
|---|---|---|
| Vectara Hallucination Rate | 6.9% | 4.1% |
| LMArena Expert | 1174 | 1225 |
| MMLU | 69.4% | 86.3% |
| GPQA Diamond | — | 47.4% |
| Confabulations | — | 22.8% |
Multilingual Llama-3.3-70B-Instruct leads
Command R+: 38.6 (#227), Llama-3.3-70B-Instruct: 39.9 (#220)
| Benchmark | Command R+ | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Non-English | 1216 | 1236 |
| LMArena Chinese | 1226 | 1217 |
| LMArena French | 1209 | 1281 |
| LMArena German | 1216 | 1251 |
| LMArena Japanese | 1166 | 1150 |
| LMArena Korean | 1138 | 1143 |
| LMArena Russian | 1227 | 1252 |
| LMArena Spanish | 1189 | 1270 |
Instruction Following Llama-3.3-70B-Instruct leads
Command R+: 60.0 (#254), Llama-3.3-70B-Instruct: 71.1 (#157)
| Benchmark | Command R+ | Llama-3.3-70B-Instruct |
|---|---|---|
| LiveBench Instruction Following | 57.6% | 82.7% |
| LMArena Instruction Following | 1197 | 1242 |
Long Context Command R+ leads
Command R+: 37.3 (#219), Llama-3.3-70B-Instruct: 26.4 (#295)
| Benchmark | Command R+ | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Longer Query | 1230 | 1256 |
| Fiction.LiveBench | — | 33.3% |
Writing & Preference Llama-3.3-70B-Instruct leads
Command R+: 43.5 (#228), Llama-3.3-70B-Instruct: 47.6 (#207)
| Benchmark | Command R+ | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Text | 1229 | 1274 |
| LMArena Creative Writing | 1235 | 1250 |
| LMArena Multi-Turn | 1213 | 1280 |
| LiveBench Language | 29.7% | 39.2% |
Frequently asked questions
Is Command R+ better than Llama-3.3-70B-Instruct?
Command R+ is the stronger model overall, scoring 32.4 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct costs 28× 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-3.3-70B-Instruct?
Llama-3.3-70B-Instruct is cheaper. It lists at $0.10 per million input tokens and $0.32 per million output tokens; Command R+ lists at $2.50 and $10.
Is Command R+ or Llama-3.3-70B-Instruct better for coding?
Llama-3.3-70B-Instruct scores higher on coding benchmarks: 31.0 versus 29.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do Command R+ and Llama-3.3-70B-Instruct share?
32 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Llama-3.3-70B-Instruct has 43.