Model comparison
Gemini Advanced 0514 vs phi-3-medium 14B
Gemini Advanced 0514 is the stronger model overall, scoring 37.7 to 29.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
Google
MicrosoftSummary
- The widest gap is in knowledge, where Gemini Advanced 0514 leads 33.3 to 9.1.
- phi-3-medium 14B has downloadable open weights; the other is API-only.
Side by side
| Gemini Advanced 0514 | phi-3-medium 14B | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 37.7 | 29.7 |
| Released | — | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini Advanced 0514: 36.6 (#205), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Gemini Advanced 0514 | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1255 | — |
| BigCodeBench Complete | — | 48.7% |
Reasoning Not comparable
Gemini Advanced 0514: 24.6 (#160), phi-3-medium 14B: —
| Benchmark | Gemini Advanced 0514 | phi-3-medium 14B |
|---|---|---|
| LMArena Hard Prompts | 1248 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.23 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math Gemini Advanced 0514 leads
Gemini Advanced 0514: 35.5 (#181), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Gemini Advanced 0514 | phi-3-medium 14B |
|---|---|---|
| LMArena Math | 1272 | — |
| MATH Level 5 | — | 17.6% |
Knowledge Gemini Advanced 0514 leads
Gemini Advanced 0514: 33.3 (#205), phi-3-medium 14B: 9.1 (#306)
| Benchmark | Gemini Advanced 0514 | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| LMArena Expert | 1215 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multilingual Not comparable
Gemini Advanced 0514: 42.6 (#192), phi-3-medium 14B: —
| Benchmark | Gemini Advanced 0514 | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1274 | — |
| LMArena Chinese | 1274 | — |
| LMArena French | 1307 | — |
| LMArena German | 1275 | — |
| LMArena Japanese | 1242 | — |
| LMArena Korean | 1232 | — |
| LMArena Russian | 1283 | — |
| LMArena Spanish | 1242 | — |
Instruction Following Not comparable
Gemini Advanced 0514: 66.0 (#212), phi-3-medium 14B: —
| Benchmark | Gemini Advanced 0514 | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1253 | — |
Long Context Not comparable
Gemini Advanced 0514: 38.0 (#207), phi-3-medium 14B: —
| Benchmark | Gemini Advanced 0514 | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1253 | — |
Writing & Preference Not comparable
Gemini Advanced 0514: 48.5 (#200), phi-3-medium 14B: —
| Benchmark | Gemini Advanced 0514 | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1279 | — |
| LMArena Creative Writing | 1284 | — |
| LMArena Multi-Turn | 1269 | — |
Frequently asked questions
Is Gemini Advanced 0514 better than phi-3-medium 14B?
Gemini Advanced 0514 is the stronger model overall, scoring 37.7 to 29.7 on the Noometry Index.
Is Gemini Advanced 0514 or phi-3-medium 14B better for coding?
They score almost the same on coding (36.6 vs 36.8); test both on your own repository before choosing.
How many benchmarks do Gemini Advanced 0514 and phi-3-medium 14B share?
0 benchmarks have published results for both models. Gemini Advanced 0514 has 17 scored results on Noometry and phi-3-medium 14B has 13.