Model comparison
Gemini 1.5 Pro (May 2024) vs Phi 3 Mini 4k Instruct
Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 32.1 to 27.9 on the Noometry Index.
Last verified . 21 shared benchmarks.
Google
MicrosoftSummary
- They share 21 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 6 categories and Phi 3 Mini 4k Instruct in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 1.5 Pro (May 2024) leads 52.4 to 27.6.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 32.1 | 27.9 |
| Released | 2024-02-15 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 45 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Gemini 1.5 Pro (May 2024) | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1294 | 1093 |
| HumanEval+ | 79.3% | 59.1% |
| MBPP+ | 74.6% | 54.2% |
| WeirdML | 22.2% | — |
| BigCodeBench Instruct | 43.8% | — |
| LiveBench Coding | — | 15.5% |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
Agentic & Tool Use Not comparable
Gemini 1.5 Pro (May 2024): 17.9 (#145), Phi 3 Mini 4k Instruct: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Phi 3 Mini 4k Instruct |
|---|---|---|
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
Reasoning Phi 3 Mini 4k Instruct leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Gemini 1.5 Pro (May 2024) | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1296 | 1072 |
| BIG-Bench Hard | 89.2% | 71.7% |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 27.1% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| DTBench | 59% | — |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| Epoch Capabilities Index | 131.73 | — |
| ForecastBench | 58.4 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Too close to call
Gemini 1.5 Pro (May 2024): 25.8 (#266), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Gemini 1.5 Pro (May 2024) | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1315 | 1111 |
| OTIS Mock AIME 2024-2025 | 23.1% | — |
| Omni-MATH | 36.4% | — |
| LiveBench Math | — | 15.7% |
| MATH Level 5 | 70.4% | — |
Knowledge Too close to call
Gemini 1.5 Pro (May 2024): 29.4 (#239), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Gemini 1.5 Pro (May 2024) | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1279 | 1045 |
| MMLU | 86.9% | 68.8% |
| GPQA Diamond | 57.2% | — |
| Humanity's Last Exam | 4.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| GPQA (HELM) | 53.4% | — |
| ARC (AI2) Challenge | — | 84.9% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.8 (#77), Phi 3 Mini 4k Instruct: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
Multilingual Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Gemini 1.5 Pro (May 2024) | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1312 | 1021 |
| LMArena Chinese | 1331 | 1021 |
| LMArena French | 1302 | 1076 |
| LMArena German | 1286 | 1044 |
| LMArena Japanese | 1292 | 935 |
| LMArena Korean | 1298 | 905 |
| LMArena Russian | 1320 | 1022 |
| LMArena Spanish | 1311 | 1085 |
Instruction Following Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Gemini 1.5 Pro (May 2024) | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1297 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
| IFEval | 83.7% | — |
Long Context Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Gemini 1.5 Pro (May 2024) | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1308 | 1044 |
Writing & Preference Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Gemini 1.5 Pro (May 2024) | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1319 | 1073 |
| LMArena Creative Writing | 1333 | 1037 |
| LMArena Multi-Turn | 1296 | 1018 |
| WildBench | 81.3% | — |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than Phi 3 Mini 4k Instruct?
Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 32.1 to 27.9 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or Phi 3 Mini 4k Instruct better for coding?
Gemini 1.5 Pro (May 2024) scores higher on coding benchmarks: 34.2 versus 26.6 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and Phi 3 Mini 4k Instruct share?
21 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.