Model comparison
Command R vs Phi-4
Command R and Phi-4 score almost the same on the Noometry Index (31.4 vs 31.2), so choose on price, context window or the category you care about most.
Last verified . 27 shared benchmarks.
Cohere
MicrosoftSummary
- They share 27 benchmarks with published results for both. Command R scores higher in 1 category and Phi-4 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Command R leads 28.0 to 20.8.
- The biggest single-benchmark swing is LiveBench Reasoning: 21.9% for Command R and 47.8% for Phi-4.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.15 / $0.60 for Command R.
Side by side
| Command R | Phi-4 | |
|---|---|---|
| Provider | Cohere | Microsoft |
| Noometry Index | 31.4 | 31.2 |
| Released | 2024-08-30 | 2024-12-11 |
| Weights | Open | Open |
| Context window | 128K | 128K |
| Max output | 4K | 4K |
| Input $ / M tokens | $0.15 | $0.07 |
| Output $ / M tokens | $0.60 | $0.14 |
| Results tracked | 29 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi-4 leads
Command R: 29.3 (#306), Phi-4: 34.4 (#239)
| Benchmark | Command R | Phi-4 |
|---|---|---|
| BigCodeBench Instruct | 37.1% | 45.5% |
| LiveBench Coding | 17.9% | 30.7% |
| LMArena Coding | 1169 | 1231 |
| BigCodeBench Complete | 45.2% | 55.4% |
Agentic & Tool Use Not comparable
Command R: —, Phi-4: 22.8 (#128)
| Benchmark | Command R | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |
Reasoning Phi-4 leads
Command R: 13.8 (#331), Phi-4: 17.7 (#291)
| Benchmark | Command R | Phi-4 |
|---|---|---|
| LiveBench Reasoning | 21.9% | 47.8% |
| LMArena Hard Prompts | 1164 | 1220 |
| LiveBench Data Analysis | 33.3% | 45.2% |
| LiveBench | 27.5% | 41.6% |
| Chess Puzzles | — | 1% |
| DTBench | 46.4% | — |
| LMCA | 9.2% | — |
| Epoch Capabilities Index | — | 130.42 |
Math Command R leads
Command R: 28.0 (#246), Phi-4: 20.8 (#285)
| Benchmark | Command R | Phi-4 |
|---|---|---|
| LiveBench Math | 19.4% | 42% |
| LMArena Math | 1155 | 1246 |
| OTIS Mock AIME 2024-2025 | — | 13.8% |
| MATH Level 5 | — | 64.9% |
Knowledge Phi-4 leads
Command R: 31.0 (#221), Phi-4: 32.6 (#209)
| Benchmark | Command R | Phi-4 |
|---|---|---|
| LMArena Expert | 1138 | 1203 |
| MMLU | 65.2% | 84.8% |
| GPQA Diamond | — | 56.1% |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
Multilingual Phi-4 leads
Command R: 35.7 (#245), Phi-4: 37.2 (#237)
| Benchmark | Command R | Phi-4 |
|---|---|---|
| LMArena Non-English | 1174 | 1197 |
| LMArena Chinese | 1182 | 1212 |
| LMArena French | 1162 | 1224 |
| LMArena German | 1176 | 1222 |
| LMArena Japanese | 1143 | 1158 |
| LMArena Korean | 1163 | 1151 |
| LMArena Russian | 1174 | 1209 |
| LMArena Spanish | 1151 | 1234 |
Instruction Following Phi-4 leads
Command R: 58.1 (#261), Phi-4: 60.4 (#251)
| Benchmark | Command R | Phi-4 |
|---|---|---|
| LiveBench Instruction Following | 55.6% | 58.4% |
| LMArena Instruction Following | 1167 | 1201 |
Long Context Too close to call
Command R: 36.3 (#231), Phi-4: 36.9 (#226)
| Benchmark | Command R | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1198 | 1217 |
Writing & Preference Phi-4 leads
Command R: 38.2 (#254), Phi-4: 40.5 (#244)
| Benchmark | Command R | Phi-4 |
|---|---|---|
| LMArena Text | 1187 | 1217 |
| LMArena Creative Writing | 1170 | 1182 |
| LMArena Multi-Turn | 1163 | 1206 |
| LiveBench Language | 16.7% | 25.6% |
| Short-Story Creative Writing | — | 62.6% |
Frequently asked questions
Is Command R better than Phi-4?
Command R and Phi-4 score almost the same on the Noometry Index (31.4 vs 31.2), so choose on price, context window or the category you care about most.
Which is cheaper, Command R or Phi-4?
Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; Command R lists at $0.15 and $0.60.
Is Command R or Phi-4 better for coding?
Phi-4 scores higher on coding benchmarks: 34.4 versus 29.3 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do Command R and Phi-4 share?
27 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Phi-4 has 37.