Model comparison
Claude Opus 4 vs Command A
Claude Opus 4 is the stronger model overall, scoring 43.1 to 36.5 on the Noometry Index. Command A costs 6.9× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
CohereSummary
- They share 23 benchmarks with published results for both. Claude Opus 4 scores higher in 7 categories and Command A in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Opus 4 leads 47.2 to 27.2.
- The biggest single-benchmark swing is Aider Polyglot: 72% for Claude Opus 4 and 12% for Command A.
- Command A is cheaper at $2.50 / $10 per million input/output tokens, against $15 / $75 for Claude Opus 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 Opus 4 | Command A | |
|---|---|---|
| Provider | Anthropic | Cohere |
| Noometry Index | 43.1 | 36.5 |
| Released | 2025-05-22 | 2025-03-13 |
| Weights | Proprietary | Open |
| Context window | 200K | 256K |
| Max output | 32K | 8K |
| Input $ / M tokens | $15 | $2.50 |
| Output $ / M tokens | $75 | $10 |
| Results tracked | 56 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4 leads
Claude Opus 4: 47.2 (#62), Command A: 27.2 (#322)
| Benchmark | Claude Opus 4 | Command A |
|---|---|---|
| Aider Polyglot | 72% | 12% |
| LMArena Coding | 1442 | 1330 |
| SWE-bench Verified | 70.7% | — |
| SWE-bench Verified (bash only) | 67.6% | — |
| GSO | 6.9% | — |
| WeirdML | 43.7% | — |
| AlgoTune | 1.33 | — |
Agentic & Tool Use Command A leads
Claude Opus 4: 34.8 (#42), Command A: 35.9 (#40)
| Benchmark | Claude Opus 4 | Command A |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 57.1% |
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
Reasoning Claude Opus 4 leads
Claude Opus 4: 27.3 (#121), Command A: 18.3 (#283)
| Benchmark | Claude Opus 4 | Command A |
|---|---|---|
| Kagi LLM Benchmark | 74.3% | 28.8% |
| LMArena Hard Prompts | 1399 | 1326 |
| DTBench | 81.6% | 61.3% |
| LMCA | 37.4% | 10.3% |
| ARC-AGI-2 | 8.6% | — |
| SimpleBench | 58.8% | — |
| ARC-AGI-1 | 35.7% | — |
| CritPt | 0.3% | — |
| EnigmaEval | 5.6% | — |
| Epoch Capabilities Index | 142.67 | — |
| ForecastBench | 61.1 | — |
Math Claude Opus 4 leads
Claude Opus 4: 42.0 (#86), Command A: 36.2 (#171)
| Benchmark | Claude Opus 4 | Command A |
|---|---|---|
| LMArena Math | 1390 | 1300 |
| OTIS Mock AIME 2024-2025 | 64.4% | — |
| Omni-MATH | 61.6% | — |
| MATH Level 5 | 85% | — |
| FrontierMath (Feb 2025 set) | 4.5% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Opus 4 leads
Claude Opus 4: 44.0 (#88), Command A: 37.1 (#159)
| Benchmark | Claude Opus 4 | Command A |
|---|---|---|
| Vectara Hallucination Rate | 12% | 9.3% |
| LMArena Expert | 1386 | 1295 |
| GPQA Diamond | 76.3% | — |
| Humanity's Last Exam | 10.7% | — |
| MMLU-Pro | 87.5% | — |
| Confabulations | 15.9% | — |
| GPQA (HELM) | 70.8% | — |
Multimodal Not comparable
Claude Opus 4: 31.5 (#106), Command A: —
| Benchmark | Claude Opus 4 | Command A |
|---|---|---|
| LMArena Vision | 1192 | — |
| GeoBench | 49% | — |
| VPCT | 38% | — |
Multilingual Claude Opus 4 leads
Claude Opus 4: 48.8 (#138), Command A: 45.3 (#170)
| Benchmark | Claude Opus 4 | Command A |
|---|---|---|
| LMArena Non-English | 1362 | 1313 |
| LMArena Chinese | 1386 | 1327 |
| LMArena French | 1372 | 1351 |
| LMArena German | 1391 | 1341 |
| LMArena Japanese | 1331 | 1285 |
| LMArena Korean | 1321 | 1285 |
| LMArena Russian | 1392 | 1314 |
| LMArena Spanish | 1389 | 1347 |
Instruction Following Claude Opus 4 leads
Claude Opus 4: 77.1 (#28), Command A: 69.1 (#177)
| Benchmark | Claude Opus 4 | Command A |
|---|---|---|
| LMArena Instruction Following | 1406 | 1309 |
| IFEval | 91.8% | — |
Long Context Command A leads
Claude Opus 4: 39.6 (#172), Command A: 40.6 (#151)
| Benchmark | Claude Opus 4 | Command A |
|---|---|---|
| LMArena Longer Query | 1422 | 1334 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Claude Opus 4 leads
Claude Opus 4: 61.2 (#89), Command A: 47.6 (#208)
| Benchmark | Claude Opus 4 | Command A |
|---|---|---|
| LMArena Text | 1377 | 1331 |
| LMArena Creative Writing | 1387 | 1319 |
| EQ-Bench Creative Writing | 1580 | 1145 |
| LMArena Multi-Turn | 1396 | 1339 |
| Short-Story Creative Writing | 83.6% | — |
| WildBench | 85.2% | — |
Frequently asked questions
Is Claude Opus 4 better than Command A?
Claude Opus 4 is the stronger model overall, scoring 43.1 to 36.5 on the Noometry Index. Command A costs 6.9× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 4 or Command A?
Command A is cheaper. It lists at $2.50 per million input tokens and $10 per million output tokens; Claude Opus 4 lists at $15 and $75.
Is Claude Opus 4 or Command A better for coding?
Claude Opus 4 scores higher on coding benchmarks: 47.2 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 Opus 4 and Command A share?
23 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and Command A has 24.