Model comparison
Command R vs Phi 3 Mini 4k Instruct
Command R is the stronger model overall, scoring 31.4 to 27.9 on the Noometry Index.
Last verified . 25 shared benchmarks.
Cohere
MicrosoftSummary
- They share 25 benchmarks with published results for both. Command R scores higher in 7 categories and Phi 3 Mini 4k Instruct in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Command R leads 38.2 to 27.6.
- The biggest single-benchmark swing is LiveBench Instruction Following: 55.6% for Command R and 39.1% for Phi 3 Mini 4k Instruct.
Side by side
| Command R | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Cohere | Microsoft |
| Noometry Index | 31.4 | 27.9 |
| Released | 2024-08-30 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 29 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Command R leads
Command R: 29.3 (#306), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Command R | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Coding | 17.9% | 15.5% |
| LMArena Coding | 1169 | 1093 |
| BigCodeBench Instruct | 37.1% | — |
| BigCodeBench Complete | 45.2% | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Reasoning Too close to call
Command R: 13.8 (#331), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Command R | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Reasoning | 21.9% | 26.8% |
| LMArena Hard Prompts | 1164 | 1072 |
| LiveBench Data Analysis | 33.3% | 34.7% |
| LiveBench | 27.5% | 22.4% |
| Chess Puzzles | — | 0% |
| DTBench | 46.4% | — |
| LMCA | 9.2% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| WinoGrande | — | 70.8% |
Math Command R leads
Command R: 28.0 (#246), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Command R | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Math | 19.4% | 15.7% |
| LMArena Math | 1155 | 1111 |
Knowledge Command R leads
Command R: 31.0 (#221), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Command R | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1138 | 1045 |
| MMLU | 65.2% | 68.8% |
| ARC (AI2) Challenge | — | 84.9% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Command R leads
Command R: 35.7 (#245), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Command R | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1174 | 1021 |
| LMArena Chinese | 1182 | 1021 |
| LMArena French | 1162 | 1076 |
| LMArena German | 1176 | 1044 |
| LMArena Japanese | 1143 | 935 |
| LMArena Korean | 1163 | 905 |
| LMArena Russian | 1174 | 1022 |
| LMArena Spanish | 1151 | 1085 |
Instruction Following Command R leads
Command R: 58.1 (#261), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Command R | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Instruction Following | 55.6% | 39.1% |
| LMArena Instruction Following | 1167 | 1053 |
Long Context Command R leads
Command R: 36.3 (#231), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Command R | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1198 | 1044 |
Writing & Preference Command R leads
Command R: 38.2 (#254), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Command R | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1187 | 1073 |
| LMArena Creative Writing | 1170 | 1037 |
| LMArena Multi-Turn | 1163 | 1018 |
| LiveBench Language | 16.7% | 9.2% |
Frequently asked questions
Is Command R better than Phi 3 Mini 4k Instruct?
Command R is the stronger model overall, scoring 31.4 to 27.9 on the Noometry Index.
Is Command R or Phi 3 Mini 4k Instruct better for coding?
Command R scores higher on coding benchmarks: 29.3 versus 26.6 in the Noometry coding category.
How many benchmarks do Command R and Phi 3 Mini 4k Instruct share?
25 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.