Model comparison
Command R vs Muse Spark 1.2
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 31.4 on the Noometry Index. Command R costs 7.6× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Cohere
MetaSummary
- They share 16 benchmarks with published results for both. Command R scores higher in 0 categories and Muse Spark 1.2 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 51.3 to 13.8.
- The biggest single-benchmark swing is DTBench: 46.4% for Command R and 94.7% for Muse Spark 1.2.
- Command R is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.2.
- Muse Spark 1.2 accepts more context: 1.05M tokens versus 128K.
- Command R has downloadable open weights; the other is API-only.
Side by side
| Command R | Muse Spark 1.2 | |
|---|---|---|
| Provider | Cohere | Meta |
| Noometry Index | 31.4 | 50.3 |
| Released | 2024-08-30 | 2026-08-05 |
| Weights | Open | Proprietary |
| Context window | 128K | 1.05M |
| Max output | 4K | 131K |
| Input $ / M tokens | $0.15 | $1.25 |
| Output $ / M tokens | $0.60 | $4.25 |
| Results tracked | 29 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
Command R: 29.3 (#306), Muse Spark 1.2: 49.2 (#51)
| Benchmark | Command R | Muse Spark 1.2 |
|---|---|---|
| LMArena Coding | 1169 | 1495 |
| DeepSWE | — | 54.9% |
| LMArena WebDev | — | 1533 |
| FrontierSWE | — | 12% |
| SciCode | — | 56.4% |
| WeirdML | — | 60.3% |
| BigCodeBench Instruct | 37.1% | — |
| LiveBench Coding | 17.9% | — |
| BigCodeBench Complete | 45.2% | — |
Agentic & Tool Use Not comparable
Command R: —, Muse Spark 1.2: 29.4 (#87)
| Benchmark | Command R | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | — | 36.4% |
| GDP.pdf | — | 16% |
Reasoning Muse Spark 1.2 leads
Command R: 13.8 (#331), Muse Spark 1.2: 51.3 (#34)
| Benchmark | Command R | Muse Spark 1.2 |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1486 |
| DTBench | 46.4% | 94.7% |
| LMCA | 9.2% | 48.4% |
| SimpleBench | — | 74.5% |
| NYT Connections (extended) | — | 79.2% |
| CritPt | — | 17.7% |
| LiveBench Reasoning | 21.9% | — |
| LiveBench Data Analysis | 33.3% | — |
| Epoch Capabilities Index | — | 154.87 |
| LiveBench | 27.5% | — |
Math Muse Spark 1.2 leads
Command R: 28.0 (#246), Muse Spark 1.2: 46.4 (#70)
| Benchmark | Command R | Muse Spark 1.2 |
|---|---|---|
| LMArena Math | 1155 | 1471 |
| ProofBench | — | 43% |
| LiveBench Math | 19.4% | — |
Knowledge Muse Spark 1.2 leads
Command R: 31.0 (#221), Muse Spark 1.2: 54.1 (#53)
| Benchmark | Command R | Muse Spark 1.2 |
|---|---|---|
| LMArena Expert | 1138 | 1480 |
| SimpleQA Verified | — | 60.3% |
| MMLU | 65.2% | — |
Multimodal Not comparable
Command R: —, Muse Spark 1.2: 43.4 (#25)
| Benchmark | Command R | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | — | 1305 |
Multilingual Muse Spark 1.2 leads
Command R: 35.7 (#245), Muse Spark 1.2: 57.1 (#11)
| Benchmark | Command R | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1174 | 1478 |
| LMArena Chinese | 1182 | 1511 |
| LMArena French | 1162 | 1513 |
| LMArena Russian | 1174 | 1487 |
| LMArena Spanish | 1151 | 1498 |
| LMArena German | 1176 | — |
| LMArena Japanese | 1143 | — |
| LMArena Korean | 1163 | — |
Instruction Following Muse Spark 1.2 leads
Command R: 58.1 (#261), Muse Spark 1.2: 76.7 (#36)
| Benchmark | Command R | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1167 | 1461 |
| LiveBench Instruction Following | 55.6% | — |
Long Context Muse Spark 1.2 leads
Command R: 36.3 (#231), Muse Spark 1.2: 45.2 (#48)
| Benchmark | Command R | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1198 | 1475 |
Writing & Preference Muse Spark 1.2 leads
Command R: 38.2 (#254), Muse Spark 1.2: 72.3 (#14)
| Benchmark | Command R | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1187 | 1482 |
| LMArena Creative Writing | 1170 | 1449 |
| LMArena Multi-Turn | 1163 | 1494 |
| EQ-Bench Creative Writing | — | 1840 |
| LiveBench Language | 16.7% | — |
Frequently asked questions
Is Command R better than Muse Spark 1.2?
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 31.4 on the Noometry Index. Command R costs 7.6× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.
Which is cheaper, Command R or Muse Spark 1.2?
Command R is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.
Is Command R or Muse Spark 1.2 better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 29.3 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.2 does, with 1.05M tokens against 128K.
How many benchmarks do Command R and Muse Spark 1.2 share?
16 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Muse Spark 1.2 has 31.