Model comparison
Gemini 1.5 Pro (May 2024) vs Phi-4
Gemini 1.5 Pro (May 2024) and Phi-4 score almost the same on the Noometry Index (32.1 vs 31.2), so choose on price, context window or the category you care about most.
Last verified . 26 shared benchmarks.
Google
MicrosoftSummary
- They share 26 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 5 categories and Phi-4 in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 1.5 Pro (May 2024) leads 52.4 to 40.5.
- The biggest single-benchmark swing is Confabulations: 13.5% for Gemini 1.5 Pro (May 2024) and 29.4% for Phi-4.
- Phi-4 has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | Phi-4 | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 32.1 | 31.2 |
| Released | 2024-02-15 | 2024-12-11 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.07 |
| Output $ / M tokens | — | $0.14 |
| Results tracked | 45 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 1.5 Pro (May 2024): 34.2 (#241), Phi-4: 34.4 (#239)
| Benchmark | Gemini 1.5 Pro (May 2024) | Phi-4 |
|---|---|---|
| BigCodeBench Instruct | 43.8% | 45.5% |
| LMArena Coding | 1294 | 1231 |
| BigCodeBench Complete | 57.5% | 55.4% |
| WeirdML | 22.2% | — |
| LiveBench Coding | — | 30.7% |
| CadEval | 34% | — |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use Phi-4 leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), Phi-4: 22.8 (#128)
| Benchmark | Gemini 1.5 Pro (May 2024) | Phi-4 |
|---|---|---|
| BALROG | 21% | 11.6% |
| Berkeley Function Calling Leaderboard | — | 28.8% |
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
Reasoning Phi-4 leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), Phi-4: 17.7 (#291)
| Benchmark | Gemini 1.5 Pro (May 2024) | Phi-4 |
|---|---|---|
| LMArena Hard Prompts | 1296 | 1220 |
| Epoch Capabilities Index | 131.73 | 130.42 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 27.1% | — |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | — | 47.8% |
| DTBench | 59% | — |
| LiveBench Data Analysis | — | 45.2% |
| BIG-Bench Hard | 89.2% | — |
| ForecastBench | 58.4 | — |
| LiveBench | — | 41.6% |
Math Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), Phi-4: 20.8 (#285)
| Benchmark | Gemini 1.5 Pro (May 2024) | Phi-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 13.8% |
| LMArena Math | 1315 | 1246 |
| MATH Level 5 | 70.4% | 64.9% |
| Omni-MATH | 36.4% | — |
| LiveBench Math | — | 42% |
Knowledge Phi-4 leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), Phi-4: 32.6 (#209)
| Benchmark | Gemini 1.5 Pro (May 2024) | Phi-4 |
|---|---|---|
| GPQA Diamond | 57.2% | 56.1% |
| Confabulations | 13.5% | 29.4% |
| LMArena Expert | 1279 | 1203 |
| MMLU | 86.9% | 84.8% |
| Humanity's Last Exam | 4.6% | — |
| MMLU-Pro | 73.7% | — |
| Vectara Hallucination Rate | — | 3.7% |
| GPQA (HELM) | 53.4% | — |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.8 (#77), Phi-4: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Phi-4 |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
Multilingual Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), Phi-4: 37.2 (#237)
| Benchmark | Gemini 1.5 Pro (May 2024) | Phi-4 |
|---|---|---|
| LMArena Non-English | 1312 | 1197 |
| LMArena Chinese | 1331 | 1212 |
| LMArena French | 1302 | 1224 |
| LMArena German | 1286 | 1222 |
| LMArena Japanese | 1292 | 1158 |
| LMArena Korean | 1298 | 1151 |
| LMArena Russian | 1320 | 1209 |
| LMArena Spanish | 1311 | 1234 |
Instruction Following Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), Phi-4: 60.4 (#251)
| Benchmark | Gemini 1.5 Pro (May 2024) | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 1297 | 1201 |
| LiveBench Instruction Following | — | 58.4% |
| IFEval | 83.7% | — |
Long Context Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), Phi-4: 36.9 (#226)
| Benchmark | Gemini 1.5 Pro (May 2024) | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1308 | 1217 |
Writing & Preference Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), Phi-4: 40.5 (#244)
| Benchmark | Gemini 1.5 Pro (May 2024) | Phi-4 |
|---|---|---|
| LMArena Text | 1319 | 1217 |
| LMArena Creative Writing | 1333 | 1182 |
| LMArena Multi-Turn | 1296 | 1206 |
| Short-Story Creative Writing | — | 62.6% |
| WildBench | 81.3% | — |
| LiveBench Language | — | 25.6% |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than Phi-4?
Gemini 1.5 Pro (May 2024) and Phi-4 score almost the same on the Noometry Index (32.1 vs 31.2), so choose on price, context window or the category you care about most.
Is Gemini 1.5 Pro (May 2024) or Phi-4 better for coding?
They score almost the same on coding (34.2 vs 34.4); test both on your own repository before choosing.
How many benchmarks do Gemini 1.5 Pro (May 2024) and Phi-4 share?
26 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Phi-4 has 37.