Model comparison
Gemini 1.0 Pro vs Phi 3 Mini 4k Instruct
Gemini 1.0 Pro and Phi 3 Mini 4k Instruct score almost the same on the Noometry Index (27.3 vs 27.9), so choose on price, context window or the category you care about most.
Last verified . 19 shared benchmarks.
Google
MicrosoftSummary
- They share 19 benchmarks with published results for both. Gemini 1.0 Pro scores higher in 6 categories and Phi 3 Mini 4k Instruct in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Phi 3 Mini 4k Instruct leads 26.6 to 9.3.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.0 Pro | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 27.3 | 27.9 |
| Released | 2023-12-13 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 1.0 Pro leads
Gemini 1.0 Pro: 32.2 (#275), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Gemini 1.0 Pro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1108 | 1093 |
| HumanEval+ | 55.5% | 59.1% |
| MBPP+ | 61.4% | 54.2% |
| LiveBench Coding | — | 15.5% |
Reasoning Gemini 1.0 Pro leads
Gemini 1.0 Pro: 17.1 (#296), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Gemini 1.0 Pro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1109 | 1072 |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| DTBench | 45.9% | — |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 117.04 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Phi 3 Mini 4k Instruct leads
Gemini 1.0 Pro: 9.3 (#321), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Gemini 1.0 Pro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1132 | 1111 |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| LiveBench Math | — | 15.7% |
| MATH Level 5 | 11.2% | — |
Knowledge Phi 3 Mini 4k Instruct leads
Gemini 1.0 Pro: 15.6 (#291), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Gemini 1.0 Pro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1059 | 1045 |
| MMLU | 70% | 68.8% |
| GPQA Diamond | 34% | — |
| ARC (AI2) Challenge | — | 84.9% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Gemini 1.0 Pro leads
Gemini 1.0 Pro: 33.4 (#252), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Gemini 1.0 Pro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1138 | 1021 |
| LMArena Chinese | 1124 | 1021 |
| LMArena French | 1145 | 1076 |
| LMArena German | 1125 | 1044 |
| LMArena Japanese | 1023 | 935 |
| LMArena Russian | 1186 | 1022 |
| LMArena Spanish | 1119 | 1085 |
| LMArena Korean | — | 905 |
Instruction Following Gemini 1.0 Pro leads
Gemini 1.0 Pro: 57.6 (#267), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Gemini 1.0 Pro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1114 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Gemini 1.0 Pro leads
Gemini 1.0 Pro: 34.3 (#249), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Gemini 1.0 Pro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1132 | 1044 |
Writing & Preference Gemini 1.0 Pro leads
Gemini 1.0 Pro: 36.0 (#264), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Gemini 1.0 Pro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1149 | 1073 |
| LMArena Creative Writing | 1131 | 1037 |
| LMArena Multi-Turn | 1139 | 1018 |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Gemini 1.0 Pro better than Phi 3 Mini 4k Instruct?
Gemini 1.0 Pro and Phi 3 Mini 4k Instruct score almost the same on the Noometry Index (27.3 vs 27.9), so choose on price, context window or the category you care about most.
Is Gemini 1.0 Pro or Phi 3 Mini 4k Instruct better for coding?
Gemini 1.0 Pro scores higher on coding benchmarks: 32.2 versus 26.6 in the Noometry coding category.
How many benchmarks do Gemini 1.0 Pro and Phi 3 Mini 4k Instruct share?
19 benchmarks have published results for both models. Gemini 1.0 Pro has 24 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.