Model comparison
Command R+ vs Phi-2
Command R+ has enough public results to be ranked (#257); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 4 shared benchmarks.
Cohere
MicrosoftSummary
- They share 4 benchmarks with published results for both.
Side by side
| Command R+ | Phi-2 | |
|---|---|---|
| Provider | Cohere | Microsoft |
| Noometry Index | 32.4 | — |
| Released | 2024-08-30 | 2023-12-12 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 34 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Command R+: 29.1 (#309), Phi-2: —
| Benchmark | Command R+ | Phi-2 |
|---|---|---|
| HumanEval+ | 56.7% | 45.1% |
| MBPP+ | 63.5% | 54.2% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| LMArena Coding | 1187 | — |
| BigCodeBench Complete | 41.9% | — |
Reasoning Not comparable
Command R+: 9.2 (#344), Phi-2: —
| Benchmark | Command R+ | Phi-2 |
|---|---|---|
| Epoch Capabilities Index | 119.34 | 107.94 |
| SimpleBench | 17.4% | — |
| LiveBench Reasoning | 24.8% | — |
| LMArena Hard Prompts | 1186 | — |
| DTBench | 54.9% | — |
| LiveBench Data Analysis | 38.1% | — |
| LMCA | 5% | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| HellaSwag | — | 53.6% |
| LiveBench | 31.8% | — |
| WinoGrande | — | 54.7% |
Math Not comparable
Command R+: 28.9 (#242), Phi-2: —
| Benchmark | Command R+ | Phi-2 |
|---|---|---|
| LiveBench Math | 21.3% | — |
| LMArena Math | 1188 | — |
Knowledge Not comparable
Command R+: 36.4 (#169), Phi-2: —
| Benchmark | Command R+ | Phi-2 |
|---|---|---|
| MMLU | 69.4% | 58.4% |
| Vectara Hallucination Rate | 6.9% | — |
| LMArena Expert | 1174 | — |
| ARC (AI2) Challenge | — | 75.9% |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |
Multilingual Not comparable
Command R+: 38.6 (#227), Phi-2: —
| Benchmark | Command R+ | Phi-2 |
|---|---|---|
| LMArena Non-English | 1216 | — |
| LMArena Chinese | 1226 | — |
| LMArena French | 1209 | — |
| LMArena German | 1216 | — |
| LMArena Japanese | 1166 | — |
| LMArena Korean | 1138 | — |
| LMArena Russian | 1227 | — |
| LMArena Spanish | 1189 | — |
Instruction Following Not comparable
Command R+: 60.0 (#254), Phi-2: —
| Benchmark | Command R+ | Phi-2 |
|---|---|---|
| LiveBench Instruction Following | 57.6% | — |
| LMArena Instruction Following | 1197 | — |
Long Context Not comparable
Command R+: 37.3 (#219), Phi-2: —
| Benchmark | Command R+ | Phi-2 |
|---|---|---|
| LMArena Longer Query | 1230 | — |
Writing & Preference Not comparable
Command R+: 43.5 (#228), Phi-2: —
| Benchmark | Command R+ | Phi-2 |
|---|---|---|
| LMArena Text | 1229 | — |
| LMArena Creative Writing | 1235 | — |
| LMArena Multi-Turn | 1213 | — |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than Phi-2?
Command R+ has enough public results to be ranked (#257); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do Command R+ and Phi-2 share?
4 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Phi-2 has 11.