Model comparison
Claude Sonnet 4 vs Command A
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 36.5 on the Noometry Index.
Last verified . 23 shared benchmarks.
CohereSummary
- They share 23 benchmarks with published results for both. Claude Sonnet 4 scores higher in 8 categories and Command A in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Sonnet 4 leads 43.5 to 27.2.
- The biggest single-benchmark swing is Aider Polyglot: 61.3% for Claude Sonnet 4 and 12% for Command A.
- Command A is cheaper at $2.50 / $10 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- Command A accepts more context: 256K tokens versus 200K.
- Command A has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4 | Command A | |
|---|---|---|
| Provider | Anthropic | Cohere |
| Noometry Index | 40.8 | 36.5 |
| Released | 2025-05-22 | 2025-03-13 |
| Weights | Proprietary | Open |
| Context window | 200K | 256K |
| Max output | 64K | 8K |
| Input $ / M tokens | $3 | $2.50 |
| Output $ / M tokens | $15 | $10 |
| Results tracked | 58 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 43.5 (#88), Command A: 27.2 (#322)
| Benchmark | Claude Sonnet 4 | Command A |
|---|---|---|
| Aider Polyglot | 61.3% | 12% |
| LMArena Coding | 1414 | 1330 |
| SWE-bench Verified (bash only) | 64.9% | — |
| SciCode | 40% | — |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
| ALE-Bench | 655.35 | — |
Agentic & Tool Use Claude Sonnet 4 leads
Claude Sonnet 4: 38.5 (#31), Command A: 35.9 (#40)
| Benchmark | Claude Sonnet 4 | Command A |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 57.1% |
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Claude Sonnet 4 leads
Claude Sonnet 4: 22.9 (#187), Command A: 18.3 (#283)
| Benchmark | Claude Sonnet 4 | Command A |
|---|---|---|
| Kagi LLM Benchmark | 73% | 28.8% |
| LMArena Hard Prompts | 1372 | 1326 |
| DTBench | 77.1% | 61.3% |
| LMCA | 29% | 10.3% |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| ARC-AGI-1 | 40% | — |
| CritPt | 0.3% | — |
| EnigmaEval | 3.1% | — |
| Epoch Capabilities Index | 141.69 | — |
| ForecastBench | 60.2 | — |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 43.3 (#80), Command A: 36.2 (#171)
| Benchmark | Claude Sonnet 4 | Command A |
|---|---|---|
| LMArena Math | 1375 | 1300 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| Omni-MATH | 60.2% | — |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.8 (#108), Command A: 37.1 (#159)
| Benchmark | Claude Sonnet 4 | Command A |
|---|---|---|
| Vectara Hallucination Rate | 10.3% | 9.3% |
| LMArena Expert | 1372 | 1295 |
| GPQA Diamond | 79.2% | — |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| GPQA (HELM) | 70.6% | — |
Multimodal Not comparable
Claude Sonnet 4: 26.2 (#121), Command A: —
| Benchmark | Claude Sonnet 4 | Command A |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Claude Sonnet 4 leads
Claude Sonnet 4: 46.7 (#156), Command A: 45.3 (#170)
| Benchmark | Claude Sonnet 4 | Command A |
|---|---|---|
| LMArena Non-English | 1333 | 1313 |
| LMArena Chinese | 1350 | 1327 |
| LMArena French | 1363 | 1351 |
| LMArena German | 1331 | 1341 |
| LMArena Japanese | 1302 | 1285 |
| LMArena Korean | 1291 | 1285 |
| LMArena Russian | 1355 | 1314 |
| LMArena Spanish | 1357 | 1347 |
Instruction Following Claude Sonnet 4 leads
Claude Sonnet 4: 71.7 (#145), Command A: 69.1 (#177)
| Benchmark | Claude Sonnet 4 | Command A |
|---|---|---|
| LMArena Instruction Following | 1376 | 1309 |
| IFEval | 84% | — |
Long Context Command A leads
Claude Sonnet 4: 33.7 (#259), Command A: 40.6 (#151)
| Benchmark | Claude Sonnet 4 | Command A |
|---|---|---|
| LMArena Longer Query | 1398 | 1334 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference Claude Sonnet 4 leads
Claude Sonnet 4: 57.1 (#132), Command A: 47.6 (#208)
| Benchmark | Claude Sonnet 4 | Command A |
|---|---|---|
| LMArena Text | 1351 | 1331 |
| LMArena Creative Writing | 1345 | 1319 |
| EQ-Bench Creative Writing | 1483 | 1145 |
| LMArena Multi-Turn | 1376 | 1339 |
| Short-Story Creative Writing | 81.4% | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is Claude Sonnet 4 better than Command A?
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 36.5 on the Noometry Index.
Which is cheaper, Claude Sonnet 4 or Command A?
Command A is cheaper. It lists at $2.50 per million input tokens and $10 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or Command A better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 27.2 in the Noometry coding category.
Which has the bigger context window?
Command A does, with 256K tokens against 200K.
How many benchmarks do Claude Sonnet 4 and Command A share?
23 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Command A has 24.