Model comparison
Command A vs Phi-4
Command A is the stronger model overall, scoring 36.5 to 31.2 on the Noometry Index. Phi-4 costs 50× less per token, which makes it the better buy when Command A's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Cohere
MicrosoftSummary
- They share 19 benchmarks with published results for both. Command A scores higher in 8 categories and Phi-4 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Command A leads 36.2 to 20.8.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 57.1% for Command A and 28.8% for Phi-4.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $2.50 / $10 for Command A.
- Command A accepts more context: 256K tokens versus 128K.
Side by side
| Command A | Phi-4 | |
|---|---|---|
| Provider | Cohere | Microsoft |
| Noometry Index | 36.5 | 31.2 |
| Released | 2025-03-13 | 2024-12-11 |
| Weights | Open | Open |
| Context window | 256K | 128K |
| Max output | 8K | 4K |
| Input $ / M tokens | $2.50 | $0.07 |
| Output $ / M tokens | $10 | $0.14 |
| Results tracked | 24 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi-4 leads
Command A: 27.2 (#322), Phi-4: 34.4 (#239)
| Benchmark | Command A | Phi-4 |
|---|---|---|
| LMArena Coding | 1330 | 1231 |
| Aider Polyglot | 12% | — |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| BigCodeBench Complete | — | 55.4% |
Agentic & Tool Use Command A leads
Command A: 35.9 (#40), Phi-4: 22.8 (#128)
| Benchmark | Command A | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | 28.8% |
| BALROG | — | 11.6% |
Reasoning Too close to call
Command A: 18.3 (#283), Phi-4: 17.7 (#291)
| Benchmark | Command A | Phi-4 |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1220 |
| Kagi LLM Benchmark | 28.8% | — |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | — | 47.8% |
| DTBench | 61.3% | — |
| LiveBench Data Analysis | — | 45.2% |
| LMCA | 10.3% | — |
| Epoch Capabilities Index | — | 130.42 |
| LiveBench | — | 41.6% |
Math Command A leads
Command A: 36.2 (#171), Phi-4: 20.8 (#285)
| Benchmark | Command A | Phi-4 |
|---|---|---|
| LMArena Math | 1300 | 1246 |
| OTIS Mock AIME 2024-2025 | — | 13.8% |
| LiveBench Math | — | 42% |
| MATH Level 5 | — | 64.9% |
Knowledge Command A leads
Command A: 37.1 (#159), Phi-4: 32.6 (#209)
| Benchmark | Command A | Phi-4 |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | 3.7% |
| LMArena Expert | 1295 | 1203 |
| GPQA Diamond | — | 56.1% |
| Confabulations | — | 29.4% |
| MMLU | — | 84.8% |
Multilingual Command A leads
Command A: 45.3 (#170), Phi-4: 37.2 (#237)
| Benchmark | Command A | Phi-4 |
|---|---|---|
| LMArena Non-English | 1313 | 1197 |
| LMArena Chinese | 1327 | 1212 |
| LMArena French | 1351 | 1224 |
| LMArena German | 1341 | 1222 |
| LMArena Japanese | 1285 | 1158 |
| LMArena Korean | 1285 | 1151 |
| LMArena Russian | 1314 | 1209 |
| LMArena Spanish | 1347 | 1234 |
Instruction Following Command A leads
Command A: 69.1 (#177), Phi-4: 60.4 (#251)
| Benchmark | Command A | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 1309 | 1201 |
| LiveBench Instruction Following | — | 58.4% |
Long Context Command A leads
Command A: 40.6 (#151), Phi-4: 36.9 (#226)
| Benchmark | Command A | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1334 | 1217 |
Writing & Preference Command A leads
Command A: 47.6 (#208), Phi-4: 40.5 (#244)
| Benchmark | Command A | Phi-4 |
|---|---|---|
| LMArena Text | 1331 | 1217 |
| LMArena Creative Writing | 1319 | 1182 |
| LMArena Multi-Turn | 1339 | 1206 |
| Short-Story Creative Writing | — | 62.6% |
| EQ-Bench Creative Writing | 1145 | — |
| LiveBench Language | — | 25.6% |
Frequently asked questions
Is Command A better than Phi-4?
Command A is the stronger model overall, scoring 36.5 to 31.2 on the Noometry Index. Phi-4 costs 50× less per token, which makes it the better buy when Command A's lead doesn't matter for your workload.
Which is cheaper, Command A or Phi-4?
Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; Command A lists at $2.50 and $10.
Is Command A or Phi-4 better for coding?
Phi-4 scores higher on coding benchmarks: 34.4 versus 27.2 in the Noometry coding category.
Which has the bigger context window?
Command A does, with 256K tokens against 128K.
How many benchmarks do Command A and Phi-4 share?
19 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Phi-4 has 37.