Model comparison
Command R vs Sonar
Sonar is the stronger model overall, scoring 38.5 to 31.4 on the Noometry Index. Command R costs 3.8× less per token, which makes it the better buy when Sonar's lead doesn't matter for your workload.
Last verified . 7 shared benchmarks.
Cohere
PerplexitySummary
- They share 7 benchmarks with published results for both. Command R scores higher in 0 categories and Sonar in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Sonar leads 52.6 to 38.2.
- The biggest single-benchmark swing is LiveBench Language: 16.7% for Command R and 44.1% for Sonar.
- Command R is cheaper at $0.15 / $0.60 per million input/output tokens, against $1 / $1 for Sonar.
- Command R has downloadable open weights; the other is API-only.
Side by side
| Command R | Sonar | |
|---|---|---|
| Provider | Cohere | Perplexity |
| Noometry Index | 31.4 | 38.5 |
| Released | 2024-08-30 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 128K | 128K |
| Max output | 4K | 4K |
| Input $ / M tokens | $0.15 | $1 |
| Output $ / M tokens | $0.60 | $1 |
| Results tracked | 29 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Sonar leads
Command R: 29.3 (#306), Sonar: 35.7 (#221)
| Benchmark | Command R | Sonar |
|---|---|---|
| LiveBench Coding | 17.9% | 35.1% |
| BigCodeBench Instruct | 37.1% | — |
| LMArena Coding | 1169 | — |
| BigCodeBench Complete | 45.2% | — |
Reasoning Sonar leads
Command R: 13.8 (#331), Sonar: 21.1 (#227)
| Benchmark | Command R | Sonar |
|---|---|---|
| LiveBench Reasoning | 21.9% | 46.3% |
| LiveBench Data Analysis | 33.3% | 37.9% |
| LiveBench | 27.5% | 46.9% |
| LMArena Hard Prompts | 1164 | — |
| DTBench | 46.4% | — |
| LMCA | 9.2% | — |
Math Sonar leads
Command R: 28.0 (#246), Sonar: 33.7 (#200)
| Benchmark | Command R | Sonar |
|---|---|---|
| LiveBench Math | 19.4% | 41.6% |
| LMArena Math | 1155 | — |
Knowledge Not comparable
Command R: 31.0 (#221), Sonar: —
| Benchmark | Command R | Sonar |
|---|---|---|
| LMArena Expert | 1138 | — |
| MMLU | 65.2% | — |
Multilingual Not comparable
Command R: 35.7 (#245), Sonar: —
| Benchmark | Command R | Sonar |
|---|---|---|
| LMArena Non-English | 1174 | — |
| LMArena Chinese | 1182 | — |
| LMArena French | 1162 | — |
| LMArena German | 1176 | — |
| LMArena Japanese | 1143 | — |
| LMArena Korean | 1163 | — |
| LMArena Russian | 1174 | — |
| LMArena Spanish | 1151 | — |
Instruction Following Sonar leads
Command R: 58.1 (#261), Sonar: 71.4 (#150)
| Benchmark | Command R | Sonar |
|---|---|---|
| LiveBench Instruction Following | 55.6% | 76.2% |
| LMArena Instruction Following | 1167 | — |
Long Context Not comparable
Command R: 36.3 (#231), Sonar: —
| Benchmark | Command R | Sonar |
|---|---|---|
| LMArena Longer Query | 1198 | — |
Writing & Preference Sonar leads
Command R: 38.2 (#254), Sonar: 52.6 (#167)
| Benchmark | Command R | Sonar |
|---|---|---|
| LiveBench Language | 16.7% | 44.1% |
| LMArena Text | 1187 | — |
| LMArena Creative Writing | 1170 | — |
| LMArena Multi-Turn | 1163 | — |
Frequently asked questions
Is Command R better than Sonar?
Sonar is the stronger model overall, scoring 38.5 to 31.4 on the Noometry Index. Command R costs 3.8× less per token, which makes it the better buy when Sonar's lead doesn't matter for your workload.
Which is cheaper, Command R or Sonar?
Command R is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Sonar lists at $1 and $1.
Is Command R or Sonar better for coding?
Sonar scores higher on coding benchmarks: 35.7 versus 29.3 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do Command R and Sonar share?
7 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Sonar has 7.