Model comparison
Palm 2 vs Phi 3 Mini 4k Instruct
Palm 2 is the stronger model overall, scoring 29.4 to 27.4 on the Noometry Index.
Last verified . 10 shared benchmarks.
Google
MicrosoftSummary
- They share 10 benchmarks with published results for both. Palm 2 scores higher in 4 categories and Phi 3 Mini 4k Instruct in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Phi 3 Mini 4k Instruct leads 26.5 to 21.1.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| Palm 2 | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 29.4 | 27.4 |
| Released | — | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Palm 2 leads
Palm 2: 28.5 (#306), Phi 3 Mini 4k Instruct: 26.1 (#319)
| Benchmark | Palm 2 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 995 | 1093 |
| LiveBench Coding | — | 15.5% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Reasoning Palm 2 leads
Palm 2: 18.2 (#270), Phi 3 Mini 4k Instruct: 13.6 (#326)
| Benchmark | Palm 2 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1005 | 1072 |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Palm 2 leads
Palm 2: 28.4 (#229), Phi 3 Mini 4k Instruct: 24.5 (#258)
| Benchmark | Palm 2 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1049 | 1111 |
| LiveBench Math | — | 15.7% |
Knowledge Not comparable
Palm 2: —, Phi 3 Mini 4k Instruct: 27.9 (#241)
| Benchmark | Palm 2 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | — | 1045 |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Phi 3 Mini 4k Instruct leads
Palm 2: 21.1 (#290), Phi 3 Mini 4k Instruct: 26.5 (#275)
| Benchmark | Palm 2 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 916 | 1021 |
| LMArena Chinese | 887 | 1021 |
| LMArena French | — | 1075 |
| LMArena German | — | 1044 |
| LMArena Japanese | — | 935 |
| LMArena Korean | — | 905 |
| LMArena Russian | — | 1022 |
| LMArena Spanish | — | 1084 |
Instruction Following Palm 2 leads
Palm 2: 51.3 (#291), Phi 3 Mini 4k Instruct: 48.0 (#298)
| Benchmark | Palm 2 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1010 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Too close to call
Palm 2: 30.7 (#280), Phi 3 Mini 4k Instruct: 31.7 (#271)
| Benchmark | Palm 2 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1010 | 1044 |
Writing & Preference Phi 3 Mini 4k Instruct leads
Palm 2: 25.7 (#299), Phi 3 Mini 4k Instruct: 27.7 (#295)
| Benchmark | Palm 2 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1027 | 1073 |
| LMArena Creative Writing | 991 | 1037 |
| LMArena Multi-Turn | 994 | 1018 |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Palm 2 better than Phi 3 Mini 4k Instruct?
Palm 2 is the stronger model overall, scoring 29.4 to 27.4 on the Noometry Index.
Is Palm 2 or Phi 3 Mini 4k Instruct better for coding?
Palm 2 scores higher on coding benchmarks: 28.5 versus 26.1 in the Noometry coding category.
How many benchmarks do Palm 2 and Phi 3 Mini 4k Instruct share?
10 benchmarks have published results for both models. Palm 2 has 10 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.