Model comparison
Claude 3.5 Sonnet vs Command A
Command A is the stronger model overall, scoring 36.5 to 34.6 on the Noometry Index.
Last verified . 20 shared benchmarks.
CohereSummary
- They share 20 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 3 categories and Command A in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Command A leads 36.2 to 19.2.
- The biggest single-benchmark swing is Aider Polyglot: 51.6% for Claude 3.5 Sonnet and 12% for Command A.
- Command A has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Sonnet | Command A | |
|---|---|---|
| Provider | Anthropic | Cohere |
| Noometry Index | 34.6 | 36.5 |
| Released | 2024-06-20 | 2025-03-13 |
| Weights | Proprietary | Open |
| Context window | — | 256K |
| Max output | — | 8K |
| Input $ / M tokens | — | $2.50 |
| Output $ / M tokens | — | $10 |
| Results tracked | 60 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.0 (#165), Command A: 27.2 (#322)
| Benchmark | Claude 3.5 Sonnet | Command A |
|---|---|---|
| Aider Polyglot | 51.6% | 12% |
| LMArena Coding | 1342 | 1330 |
| GSO | 4.6% | — |
| WeirdML | 40% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Command A leads
Claude 3.5 Sonnet: 32.3 (#67), Command A: 35.9 (#40)
| Benchmark | Claude 3.5 Sonnet | Command A |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 57.1% |
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
Reasoning Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 23.1 (#183), Command A: 18.3 (#283)
| Benchmark | Claude 3.5 Sonnet | Command A |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1326 |
| DTBench | 67.8% | 61.3% |
| SimpleBench | 41.4% | — |
| Kagi LLM Benchmark | — | 28.8% |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 10.3% |
| Epoch Capabilities Index | 133.55 | — |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
Math Command A leads
Claude 3.5 Sonnet: 19.2 (#288), Command A: 36.2 (#171)
| Benchmark | Claude 3.5 Sonnet | Command A |
|---|---|---|
| LMArena Math | 1307 | 1300 |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| MATH Level 5 | 56.9% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Command A leads
Claude 3.5 Sonnet: 28.6 (#245), Command A: 37.1 (#159)
| Benchmark | Claude 3.5 Sonnet | Command A |
|---|---|---|
| LMArena Expert | 1265 | 1295 |
| GPQA Diamond | 55.3% | — |
| Humanity's Last Exam | 4.1% | — |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |
Multimodal Not comparable
Claude 3.5 Sonnet: 26.5 (#120), Command A: —
| Benchmark | Claude 3.5 Sonnet | Command A |
|---|---|---|
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual Command A leads
Claude 3.5 Sonnet: 43.2 (#185), Command A: 45.3 (#170)
| Benchmark | Claude 3.5 Sonnet | Command A |
|---|---|---|
| LMArena Non-English | 1283 | 1313 |
| LMArena Chinese | 1272 | 1327 |
| LMArena French | 1305 | 1351 |
| LMArena German | 1297 | 1341 |
| LMArena Japanese | 1234 | 1285 |
| LMArena Korean | 1200 | 1285 |
| LMArena Russian | 1306 | 1314 |
| LMArena Spanish | 1290 | 1347 |
Instruction Following Too close to call
Claude 3.5 Sonnet: 68.8 (#182), Command A: 69.1 (#177)
| Benchmark | Claude 3.5 Sonnet | Command A |
|---|---|---|
| LMArena Instruction Following | 1297 | 1309 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |
Long Context Too close to call
Claude 3.5 Sonnet: 39.9 (#167), Command A: 40.6 (#151)
| Benchmark | Claude 3.5 Sonnet | Command A |
|---|---|---|
| LMArena Longer Query | 1311 | 1334 |
Writing & Preference Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 52.9 (#164), Command A: 47.6 (#208)
| Benchmark | Claude 3.5 Sonnet | Command A |
|---|---|---|
| LMArena Text | 1298 | 1331 |
| LMArena Creative Writing | 1292 | 1319 |
| EQ-Bench Creative Writing | 1451 | 1145 |
| LMArena Multi-Turn | 1326 | 1339 |
| Short-Story Creative Writing | 80.3% | — |
| WildBench | 79.2% | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Command A?
Command A is the stronger model overall, scoring 36.5 to 34.6 on the Noometry Index.
Is Claude 3.5 Sonnet or Command A better for coding?
Claude 3.5 Sonnet scores higher on coding benchmarks: 39.0 versus 27.2 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Command A share?
20 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Command A has 24.