Model comparison
Command A vs GPT-4.1
Command A and GPT-4.1 score almost the same on the Noometry Index (36.5 vs 35.9), so choose on price, context window or the category you care about most.
Last verified . 24 shared benchmarks.
CohereSummary
- They share 24 benchmarks with published results for both. Command A scores higher in 4 categories and GPT-4.1 in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Command A leads 36.2 to 22.3.
- The biggest single-benchmark swing is Aider Polyglot: 12% for Command A and 52.4% for GPT-4.1.
- GPT-4.1 is cheaper at $2 / $8 per million input/output tokens, against $2.50 / $10 for Command A.
- GPT-4.1 accepts more context: 1.05M tokens versus 256K.
- Command A has downloadable open weights; the other is API-only.
Side by side
| Command A | GPT-4.1 | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 36.5 | 35.9 |
| Released | 2025-03-13 | 2025-04-14 |
| Weights | Open | Proprietary |
| Context window | 256K | 1.05M |
| Max output | 8K | 33K |
| Input $ / M tokens | $2.50 | $2 |
| Output $ / M tokens | $10 | $8 |
| Results tracked | 24 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.1 leads
Command A: 27.2 (#322), GPT-4.1: 34.4 (#238)
| Benchmark | Command A | GPT-4.1 |
|---|---|---|
| Aider Polyglot | 12% | 52.4% |
| LMArena Coding | 1330 | 1391 |
| SWE-bench Verified | — | 48.5% |
| SWE-bench Verified (bash only) | — | 39.6% |
| WeirdML | — | 39% |
| CadEval | — | 42% |
| ALE-Bench | — | 558.1 |
Agentic & Tool Use Command A leads
Command A: 35.9 (#40), GPT-4.1: 34.7 (#43)
| Benchmark | Command A | GPT-4.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | 54% |
Reasoning Command A leads
Command A: 18.3 (#283), GPT-4.1: 11.7 (#339)
| Benchmark | Command A | GPT-4.1 |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 52.3% |
| LMArena Hard Prompts | 1326 | 1384 |
| DTBench | 61.3% | 68.3% |
| LMCA | 10.3% | 25.6% |
| ARC-AGI-2 | — | 0.4% |
| SimpleBench | — | 27% |
| ARC-AGI-1 | — | 5.5% |
| Chess Puzzles | — | 6% |
| EnigmaEval | — | 2.2% |
| Epoch Capabilities Index | — | 136.78 |
| ForecastBench | — | 61.5 |
Math Command A leads
Command A: 36.2 (#171), GPT-4.1: 22.3 (#280)
| Benchmark | Command A | GPT-4.1 |
|---|---|---|
| LMArena Math | 1300 | 1370 |
| FrontierMath (Tiers 1-3) | — | 6% |
| OTIS Mock AIME 2024-2025 | — | 38.3% |
| Omni-MATH | — | 47.1% |
| MATH Level 5 | — | 83% |
| FrontierMath (Feb 2025 set) | — | 5.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Too close to call
Command A: 37.1 (#159), GPT-4.1: 37.1 (#160)
| Benchmark | Command A | GPT-4.1 |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | 5.6% |
| LMArena Expert | 1295 | 1364 |
| GPQA Diamond | — | 66.9% |
| Humanity's Last Exam | — | 5.4% |
| SimpleQA Verified | — | 31.1% |
| MMLU-Pro | — | 81.1% |
| GPQA (HELM) | — | 65.9% |
Multimodal Not comparable
Command A: —, GPT-4.1: 38.2 (#67)
| Benchmark | Command A | GPT-4.1 |
|---|---|---|
| LMArena Vision | — | 1211 |
| GeoBench | — | 72% |
Multilingual GPT-4.1 leads
Command A: 45.3 (#170), GPT-4.1: 49.4 (#133)
| Benchmark | Command A | GPT-4.1 |
|---|---|---|
| LMArena Non-English | 1313 | 1370 |
| LMArena Chinese | 1327 | 1382 |
| LMArena French | 1351 | 1382 |
| LMArena German | 1341 | 1381 |
| LMArena Japanese | 1285 | 1319 |
| LMArena Korean | 1285 | 1339 |
| LMArena Russian | 1314 | 1377 |
| LMArena Spanish | 1347 | 1376 |
Instruction Following GPT-4.1 leads
Command A: 69.1 (#177), GPT-4.1: 71.3 (#153)
| Benchmark | Command A | GPT-4.1 |
|---|---|---|
| LMArena Instruction Following | 1309 | 1367 |
| IFEval | — | 83.8% |
Long Context Too close to call
Command A: 40.6 (#151), GPT-4.1: 40.0 (#163)
| Benchmark | Command A | GPT-4.1 |
|---|---|---|
| LMArena Longer Query | 1334 | 1385 |
| Fiction.LiveBench | — | 63.9% |
Writing & Preference GPT-4.1 leads
Command A: 47.6 (#208), GPT-4.1: 57.6 (#125)
| Benchmark | Command A | GPT-4.1 |
|---|---|---|
| LMArena Text | 1331 | 1383 |
| LMArena Creative Writing | 1319 | 1363 |
| EQ-Bench Creative Writing | 1145 | 1420 |
| LMArena Multi-Turn | 1339 | 1398 |
| WildBench | — | 85.4% |
Frequently asked questions
Is Command A better than GPT-4.1?
Command A and GPT-4.1 score almost the same on the Noometry Index (36.5 vs 35.9), so choose on price, context window or the category you care about most.
Which is cheaper, Command A or GPT-4.1?
GPT-4.1 is cheaper. It lists at $2 per million input tokens and $8 per million output tokens; Command A lists at $2.50 and $10.
Is Command A or GPT-4.1 better for coding?
GPT-4.1 scores higher on coding benchmarks: 34.4 versus 27.2 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 does, with 1.05M tokens against 256K.
How many benchmarks do Command A and GPT-4.1 share?
24 benchmarks have published results for both models. Command A has 24 scored results on Noometry and GPT-4.1 has 52.