Model comparison
Command A vs Phi 3 Mini 4k Instruct
Command A is the stronger model overall, scoring 35.9 to 27.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Cohere
MicrosoftSummary
- They share 17 benchmarks with published results for both. Command A scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Command A leads 69.3 to 48.0.
Side by side
| Command A | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Cohere | Microsoft |
| Noometry Index | 35.9 | 27.4 |
| Released | 2025-03-13 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 24 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Command A: 26.8 (#317), Phi 3 Mini 4k Instruct: 26.1 (#319)
| Benchmark | Command A | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1331 | 1093 |
| Aider Polyglot | 12% | — |
| LiveBench Coding | — | 15.5% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
Command A: 35.7 (#36), Phi 3 Mini 4k Instruct: —
| Benchmark | Command A | Phi 3 Mini 4k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
Reasoning Command A leads
Command A: 17.7 (#276), Phi 3 Mini 4k Instruct: 13.6 (#326)
| Benchmark | Command A | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1072 |
| Kagi LLM Benchmark | 28.8% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| DTBench | 61.3% | — |
| LiveBench Data Analysis | — | 34.7% |
| LMCA | 10.3% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Command A leads
Command A: 33.5 (#172), Phi 3 Mini 4k Instruct: 24.5 (#258)
| Benchmark | Command A | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1300 | 1111 |
| LiveBench Math | — | 15.7% |
Knowledge Command A leads
Command A: 36.5 (#157), Phi 3 Mini 4k Instruct: 27.9 (#241)
| Benchmark | Command A | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1295 | 1045 |
| Vectara Hallucination Rate | 9.3% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Command A leads
Command A: 45.5 (#166), Phi 3 Mini 4k Instruct: 26.5 (#275)
| Benchmark | Command A | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1313 | 1021 |
| LMArena Chinese | 1327 | 1021 |
| LMArena French | 1352 | 1075 |
| LMArena German | 1341 | 1044 |
| LMArena Japanese | 1283 | 935 |
| LMArena Korean | 1285 | 905 |
| LMArena Russian | 1314 | 1022 |
| LMArena Spanish | 1346 | 1084 |
Instruction Following Command A leads
Command A: 69.3 (#172), Phi 3 Mini 4k Instruct: 48.0 (#298)
| Benchmark | Command A | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1309 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Command A leads
Command A: 40.6 (#147), Phi 3 Mini 4k Instruct: 31.7 (#271)
| Benchmark | Command A | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1334 | 1044 |
Writing & Preference Command A leads
Command A: 47.8 (#204), Phi 3 Mini 4k Instruct: 27.7 (#295)
| Benchmark | Command A | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1331 | 1073 |
| LMArena Creative Writing | 1319 | 1037 |
| LMArena Multi-Turn | 1338 | 1018 |
| EQ-Bench Creative Writing | 1145 | — |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Command A better than Phi 3 Mini 4k Instruct?
Command A is the stronger model overall, scoring 35.9 to 27.4 on the Noometry Index.
Is Command A or Phi 3 Mini 4k Instruct better for coding?
They score almost the same on coding (26.8 vs 26.1); test both on your own repository before choosing.
How many benchmarks do Command A and Phi 3 Mini 4k Instruct share?
17 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.