Model comparison
Gemini 1.0 Pro vs Phi 3 Mini 4k Instruct June 2024
Phi 3 Mini 4k Instruct June 2024 is the stronger model overall, scoring 30.7 to 27.1 on the Noometry Index.
Last verified . 14 shared benchmarks.
Google
MicrosoftSummary
- They share 14 benchmarks with published results for both. Gemini 1.0 Pro scores higher in 5 categories and Phi 3 Mini 4k Instruct June 2024 in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Phi 3 Mini 4k Instruct June 2024 leads 30.4 to 8.7.
- Phi 3 Mini 4k Instruct June 2024 has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.0 Pro | Phi 3 Mini 4k Instruct June 2024 | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 27.1 | 30.7 |
| Released | 2023-12-13 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 1.0 Pro: 31.6 (#270), Phi 3 Mini 4k Instruct June 2024: 31.2 (#275)
| Benchmark | Gemini 1.0 Pro | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Coding | 1108 | 1093 |
| HumanEval+ | 55.5% | — |
| MBPP+ | 61.4% | — |
Reasoning Phi 3 Mini 4k Instruct June 2024 leads
Gemini 1.0 Pro: 16.4 (#292), Phi 3 Mini 4k Instruct June 2024: 19.9 (#229)
| Benchmark | Gemini 1.0 Pro | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Hard Prompts | 1109 | 1088 |
| DTBench | 45.9% | — |
| Epoch Capabilities Index | 116.97 | — |
Math Phi 3 Mini 4k Instruct June 2024 leads
Gemini 1.0 Pro: 8.7 (#315), Phi 3 Mini 4k Instruct June 2024: 30.4 (#209)
| Benchmark | Gemini 1.0 Pro | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Math | 1132 | 1152 |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| MATH Level 5 | 11.2% | — |
Knowledge Phi 3 Mini 4k Instruct June 2024 leads
Gemini 1.0 Pro: 15.5 (#286), Phi 3 Mini 4k Instruct June 2024: 28.1 (#240)
| Benchmark | Gemini 1.0 Pro | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Expert | 1059 | 1051 |
| GPQA Diamond | 34% | — |
| MMLU | 70% | — |
Multilingual Gemini 1.0 Pro leads
Gemini 1.0 Pro: 33.5 (#247), Phi 3 Mini 4k Instruct June 2024: 26.0 (#277)
| Benchmark | Gemini 1.0 Pro | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Non-English | 1138 | 1013 |
| LMArena Chinese | 1124 | 1033 |
| LMArena German | 1125 | 1031 |
| LMArena Japanese | 1023 | 954 |
| LMArena Russian | 1186 | 1019 |
| LMArena French | 1144 | — |
| LMArena Korean | — | 880 |
| LMArena Spanish | 1118 | — |
Instruction Following Gemini 1.0 Pro leads
Gemini 1.0 Pro: 57.9 (#262), Phi 3 Mini 4k Instruct June 2024: 54.3 (#277)
| Benchmark | Gemini 1.0 Pro | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Instruction Following | 1114 | 1058 |
Long Context Gemini 1.0 Pro leads
Gemini 1.0 Pro: 34.3 (#244), Phi 3 Mini 4k Instruct June 2024: 31.6 (#272)
| Benchmark | Gemini 1.0 Pro | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Longer Query | 1132 | 1042 |
Writing & Preference Gemini 1.0 Pro leads
Gemini 1.0 Pro: 36.2 (#259), Phi 3 Mini 4k Instruct June 2024: 29.7 (#289)
| Benchmark | Gemini 1.0 Pro | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Text | 1149 | 1080 |
| LMArena Creative Writing | 1130 | 1045 |
| LMArena Multi-Turn | 1139 | 1049 |
Frequently asked questions
Is Gemini 1.0 Pro better than Phi 3 Mini 4k Instruct June 2024?
Phi 3 Mini 4k Instruct June 2024 is the stronger model overall, scoring 30.7 to 27.1 on the Noometry Index.
Is Gemini 1.0 Pro or Phi 3 Mini 4k Instruct June 2024 better for coding?
They score almost the same on coding (31.6 vs 31.2); test both on your own repository before choosing.
How many benchmarks do Gemini 1.0 Pro and Phi 3 Mini 4k Instruct June 2024 share?
14 benchmarks have published results for both models. Gemini 1.0 Pro has 24 scored results on Noometry and Phi 3 Mini 4k Instruct June 2024 has 15.