Model comparison
Gemini 1.0 Pro vs Phi-4
Phi-4 is the stronger model overall, scoring 31.2 to 27.3 on the Noometry Index.
Last verified . 21 shared benchmarks.
Google
MicrosoftSummary
- They share 21 benchmarks with published results for both. Gemini 1.0 Pro scores higher in 0 categories and Phi-4 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi-4 leads 32.6 to 15.6.
- The biggest single-benchmark swing is MATH Level 5: 11.2% for Gemini 1.0 Pro and 64.9% for Phi-4.
- Phi-4 has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.0 Pro | Phi-4 | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 27.3 | 31.2 |
| Released | 2023-12-13 | 2024-12-11 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.07 |
| Output $ / M tokens | — | $0.14 |
| Results tracked | 24 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi-4 leads
Gemini 1.0 Pro: 32.2 (#275), Phi-4: 34.4 (#239)
| Benchmark | Gemini 1.0 Pro | Phi-4 |
|---|---|---|
| LMArena Coding | 1108 | 1231 |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| BigCodeBench Complete | — | 55.4% |
| HumanEval+ | 55.5% | — |
| MBPP+ | 61.4% | — |
Agentic & Tool Use Not comparable
Gemini 1.0 Pro: —, Phi-4: 22.8 (#128)
| Benchmark | Gemini 1.0 Pro | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |
Reasoning Too close to call
Gemini 1.0 Pro: 17.1 (#296), Phi-4: 17.7 (#291)
| Benchmark | Gemini 1.0 Pro | Phi-4 |
|---|---|---|
| LMArena Hard Prompts | 1109 | 1220 |
| Epoch Capabilities Index | 117.04 | 130.42 |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | — | 47.8% |
| DTBench | 45.9% | — |
| LiveBench Data Analysis | — | 45.2% |
| LiveBench | — | 41.6% |
Math Phi-4 leads
Gemini 1.0 Pro: 9.3 (#321), Phi-4: 20.8 (#285)
| Benchmark | Gemini 1.0 Pro | Phi-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | 13.8% |
| LMArena Math | 1132 | 1246 |
| MATH Level 5 | 11.2% | 64.9% |
| LiveBench Math | — | 42% |
Knowledge Phi-4 leads
Gemini 1.0 Pro: 15.6 (#291), Phi-4: 32.6 (#209)
| Benchmark | Gemini 1.0 Pro | Phi-4 |
|---|---|---|
| GPQA Diamond | 34% | 56.1% |
| LMArena Expert | 1059 | 1203 |
| MMLU | 70% | 84.8% |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
Multilingual Phi-4 leads
Gemini 1.0 Pro: 33.4 (#252), Phi-4: 37.2 (#237)
| Benchmark | Gemini 1.0 Pro | Phi-4 |
|---|---|---|
| LMArena Non-English | 1138 | 1197 |
| LMArena Chinese | 1124 | 1212 |
| LMArena French | 1145 | 1224 |
| LMArena German | 1125 | 1222 |
| LMArena Japanese | 1023 | 1158 |
| LMArena Russian | 1186 | 1209 |
| LMArena Spanish | 1119 | 1234 |
| LMArena Korean | — | 1151 |
Instruction Following Phi-4 leads
Gemini 1.0 Pro: 57.6 (#267), Phi-4: 60.4 (#251)
| Benchmark | Gemini 1.0 Pro | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 1114 | 1201 |
| LiveBench Instruction Following | — | 58.4% |
Long Context Phi-4 leads
Gemini 1.0 Pro: 34.3 (#249), Phi-4: 36.9 (#226)
| Benchmark | Gemini 1.0 Pro | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1132 | 1217 |
Writing & Preference Phi-4 leads
Gemini 1.0 Pro: 36.0 (#264), Phi-4: 40.5 (#244)
| Benchmark | Gemini 1.0 Pro | Phi-4 |
|---|---|---|
| LMArena Text | 1149 | 1217 |
| LMArena Creative Writing | 1131 | 1182 |
| LMArena Multi-Turn | 1139 | 1206 |
| Short-Story Creative Writing | — | 62.6% |
| LiveBench Language | — | 25.6% |
Frequently asked questions
Is Gemini 1.0 Pro better than Phi-4?
Phi-4 is the stronger model overall, scoring 31.2 to 27.3 on the Noometry Index.
Is Gemini 1.0 Pro or Phi-4 better for coding?
Phi-4 scores higher on coding benchmarks: 34.4 versus 32.2 in the Noometry coding category.
How many benchmarks do Gemini 1.0 Pro and Phi-4 share?
21 benchmarks have published results for both models. Gemini 1.0 Pro has 24 scored results on Noometry and Phi-4 has 37.