Model comparison
Claude Sonnet 5 vs Command R
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 31.4 on the Noometry Index. Command R costs 15× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
CohereSummary
- They share 19 benchmarks with published results for both. Claude Sonnet 5 scores higher in 8 categories and Command R in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.2 to 28.0.
- The biggest single-benchmark swing is DTBench: 92.5% for Claude Sonnet 5 and 46.4% for Command R.
- Command R is cheaper at $0.15 / $0.60 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- Claude Sonnet 5 accepts more context: 1M tokens versus 128K.
- Command R has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 5 | Command R | |
|---|---|---|
| Provider | Anthropic | Cohere |
| Noometry Index | 54.6 | 31.4 |
| Released | 2026-06-29 | 2024-08-30 |
| Weights | Proprietary | Open |
| Context window | 1M | 128K |
| Max output | 128K | 4K |
| Input $ / M tokens | $2 | $0.15 |
| Output $ / M tokens | $10 | $0.60 |
| Results tracked | 51 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5 leads
Claude Sonnet 5: 55.5 (#26), Command R: 29.3 (#306)
| Benchmark | Claude Sonnet 5 | Command R |
|---|---|---|
| LMArena Coding | 1483 | 1169 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| CursorBench | 34.1% | — |
| LMArena WebDev | 1541 | — |
| SciCode | 54.3% | — |
| GSO | 37.3% | — |
| WeirdML | 68.8% | — |
| BigCodeBench Instruct | — | 37.1% |
| LiveBench Coding | — | 17.9% |
| BigCodeBench Complete | — | 45.2% |
| ALE-Bench | 1,463 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 5: 42.8 (#18), Command R: —
| Benchmark | Claude Sonnet 5 | Command R |
|---|---|---|
| APEX-Agents | 54.5% | — |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |
Reasoning Claude Sonnet 5 leads
Claude Sonnet 5: 49.1 (#39), Command R: 13.8 (#331)
| Benchmark | Claude Sonnet 5 | Command R |
|---|---|---|
| LMArena Hard Prompts | 1461 | 1164 |
| DTBench | 92.5% | 46.4% |
| LMCA | 50% | 9.2% |
| SimpleBench | 60.6% | — |
| NYT Connections (extended) | 75.1% | — |
| CritPt | 16.9% | — |
| Chess Puzzles | 35% | — |
| LiveBench Reasoning | — | 21.9% |
| Mystery Game Puzzles | 35% | — |
| LiveBench Data Analysis | — | 33.3% |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
| Epoch Capabilities Index | 156.21 | — |
| ForecastBench | 61.1 | — |
| LiveBench | — | 27.5% |
Math Claude Sonnet 5 leads
Claude Sonnet 5: 66.2 (#27), Command R: 28.0 (#246)
| Benchmark | Claude Sonnet 5 | Command R |
|---|---|---|
| LMArena Math | 1467 | 1155 |
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| OTIS Mock AIME 2024-2025 | 94.7% | — |
| ProofBench | 77% | — |
| LiveBench Math | — | 19.4% |
Knowledge Claude Sonnet 5 leads
Claude Sonnet 5: 55.6 (#47), Command R: 31.0 (#221)
| Benchmark | Claude Sonnet 5 | Command R |
|---|---|---|
| LMArena Expert | 1490 | 1138 |
| GPQA Diamond | 90.5% | — |
| SimpleQA Verified | 33.7% | — |
| MMLU | — | 65.2% |
Multimodal Not comparable
Claude Sonnet 5: 42.4 (#31), Command R: —
| Benchmark | Claude Sonnet 5 | Command R |
|---|---|---|
| LMArena Vision | 1274 | — |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |
Multilingual Claude Sonnet 5 leads
Claude Sonnet 5: 53.8 (#55), Command R: 35.7 (#245)
| Benchmark | Claude Sonnet 5 | Command R |
|---|---|---|
| LMArena Non-English | 1431 | 1174 |
| LMArena Chinese | 1477 | 1182 |
| LMArena French | 1460 | 1162 |
| LMArena German | 1440 | 1176 |
| LMArena Japanese | 1422 | 1143 |
| LMArena Korean | 1411 | 1163 |
| LMArena Russian | 1451 | 1174 |
| LMArena Spanish | 1437 | 1151 |
Instruction Following Claude Sonnet 5 leads
Claude Sonnet 5: 76.3 (#41), Command R: 58.1 (#261)
| Benchmark | Claude Sonnet 5 | Command R |
|---|---|---|
| LMArena Instruction Following | 1452 | 1167 |
| LiveBench Instruction Following | — | 55.6% |
Long Context Claude Sonnet 5 leads
Claude Sonnet 5: 44.8 (#55), Command R: 36.3 (#231)
| Benchmark | Claude Sonnet 5 | Command R |
|---|---|---|
| LMArena Longer Query | 1463 | 1198 |
Writing & Preference Claude Sonnet 5 leads
Claude Sonnet 5: 69.2 (#25), Command R: 38.2 (#254)
| Benchmark | Claude Sonnet 5 | Command R |
|---|---|---|
| LMArena Text | 1442 | 1187 |
| LMArena Creative Writing | 1416 | 1170 |
| LMArena Multi-Turn | 1454 | 1163 |
| EQ-Bench Creative Writing | 1794 | — |
| EQ-Bench 4 | 1236 | — |
| LiveBench Language | — | 16.7% |
Frequently asked questions
Is Claude Sonnet 5 better than Command R?
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 31.4 on the Noometry Index. Command R costs 15× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 5 or Command R?
Command R is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Claude Sonnet 5 lists at $2 and $10.
Is Claude Sonnet 5 or Command R better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 29.3 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 5 does, with 1M tokens against 128K.
How many benchmarks do Claude Sonnet 5 and Command R share?
19 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Command R has 29.