Model comparison
Palm 2 vs Phi-2
Palm 2 has enough public results to be ranked (#296); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Google
MicrosoftSummary
- Phi-2 has downloadable open weights; the other is API-only.
Side by side
| Palm 2 | Phi-2 | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 29.4 | — |
| Released | — | 2023-12-12 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Palm 2: 28.5 (#306), Phi-2: —
| Benchmark | Palm 2 | Phi-2 |
|---|---|---|
| LMArena Coding | 995 | — |
| HumanEval+ | — | 45.1% |
| MBPP+ | — | 54.2% |
Reasoning Not comparable
Palm 2: 18.2 (#270), Phi-2: —
| Benchmark | Palm 2 | Phi-2 |
|---|---|---|
| LMArena Hard Prompts | 1005 | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| Epoch Capabilities Index | — | 107.62 |
| HellaSwag | — | 53.6% |
| WinoGrande | — | 54.7% |
Math Not comparable
Palm 2: 28.4 (#229), Phi-2: —
| Benchmark | Palm 2 | Phi-2 |
|---|---|---|
| LMArena Math | 1049 | — |
Knowledge Not comparable
Palm 2: —, Phi-2: —
| Benchmark | Palm 2 | Phi-2 |
|---|---|---|
| ARC (AI2) Challenge | — | 75.9% |
| MMLU | — | 58.4% |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |
Multilingual Not comparable
Palm 2: 21.1 (#290), Phi-2: —
| Benchmark | Palm 2 | Phi-2 |
|---|---|---|
| LMArena Non-English | 916 | — |
| LMArena Chinese | 887 | — |
Instruction Following Not comparable
Palm 2: 51.3 (#291), Phi-2: —
| Benchmark | Palm 2 | Phi-2 |
|---|---|---|
| LMArena Instruction Following | 1010 | — |
Long Context Not comparable
Palm 2: 30.7 (#280), Phi-2: —
| Benchmark | Palm 2 | Phi-2 |
|---|---|---|
| LMArena Longer Query | 1010 | — |
Writing & Preference Not comparable
Palm 2: 25.7 (#299), Phi-2: —
| Benchmark | Palm 2 | Phi-2 |
|---|---|---|
| LMArena Text | 1027 | — |
| LMArena Creative Writing | 991 | — |
| LMArena Multi-Turn | 994 | — |
Frequently asked questions
Is Palm 2 better than Phi-2?
Palm 2 has enough public results to be ranked (#296); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do Palm 2 and Phi-2 share?
0 benchmarks have published results for both models. Palm 2 has 10 scored results on Noometry and Phi-2 has 11.