Model comparison
Gemini 1.5 Flash (May 2024) vs Phi-3.5-mini
Gemini 1.5 Flash (May 2024) has enough public results to be ranked (#246); Phi-3.5-mini does not yet, so treat this comparison as directional.
Last verified . 5 shared benchmarks.
Google
MicrosoftSummary
- They share 5 benchmarks with published results for both. Gemini 1.5 Flash (May 2024) scores higher in 0 categories and Phi-3.5-mini in 1 category, but none of those gaps is larger than the uncertainty.
- The biggest single-benchmark swing is BigCodeBench Complete: 55.1% for Gemini 1.5 Flash (May 2024) and 38.5% for Phi-3.5-mini.
- Phi-3.5-mini has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Flash (May 2024) | Phi-3.5-mini | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 33.2 | 36.9 |
| Released | 2024-05-14 | 2024-08-16 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 42 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 1.5 Flash (May 2024): 34.4 (#236), Phi-3.5-mini: 34.6 (#232)
| Benchmark | Gemini 1.5 Flash (May 2024) | Phi-3.5-mini |
|---|---|---|
| BigCodeBench Instruct | 43.5% | 32.8% |
| BigCodeBench Complete | 55.1% | 38.5% |
| WeirdML | 24.9% | — |
| LMArena Coding | 1261 | — |
| HumanEval+ | 75.6% | — |
| MBPP+ | 67.5% | — |
Agentic & Tool Use Not comparable
Gemini 1.5 Flash (May 2024): 26.6 (#102), Phi-3.5-mini: —
| Benchmark | Gemini 1.5 Flash (May 2024) | Phi-3.5-mini |
|---|---|---|
| BALROG | 14.6% | — |
Reasoning Not comparable
Gemini 1.5 Flash (May 2024): 21.7 (#215), Phi-3.5-mini: —
| Benchmark | Gemini 1.5 Flash (May 2024) | Phi-3.5-mini |
|---|---|---|
| PIQA | 87.5% | 81% |
| LMArena Hard Prompts | 1257 | — |
| DTBench | 53.8% | — |
| Epoch Capabilities Index | 129.36 | — |
| ForecastBench | 53.9 | — |
Math Not comparable
Gemini 1.5 Flash (May 2024): 22.1 (#281), Phi-3.5-mini: —
| Benchmark | Gemini 1.5 Flash (May 2024) | Phi-3.5-mini |
|---|---|---|
| GSM8K | 82.4% | 86.2% |
| OTIS Mock AIME 2024-2025 | 16.3% | — |
| Omni-MATH | 30.4% | — |
| LMArena Math | 1269 | — |
| MATH Level 5 | 61.9% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
Knowledge Not comparable
Gemini 1.5 Flash (May 2024): 26.2 (#260), Phi-3.5-mini: —
| Benchmark | Gemini 1.5 Flash (May 2024) | Phi-3.5-mini |
|---|---|---|
| BoolQ | 85.8% | 78% |
| GPQA Diamond | 47.3% | — |
| MMLU-Pro | 67.8% | — |
| GPQA (HELM) | 43.7% | — |
| LMArena Expert | 1233 | — |
| MMLU | 77.9% | — |
Multimodal Not comparable
Gemini 1.5 Flash (May 2024): 36.0 (#81), Phi-3.5-mini: —
| Benchmark | Gemini 1.5 Flash (May 2024) | Phi-3.5-mini |
|---|---|---|
| LMArena Vision | 1141 | — |
| Video-MME | 70.3% | — |
| GeoBench | 76% | — |
Multilingual Not comparable
Gemini 1.5 Flash (May 2024): 42.9 (#189), Phi-3.5-mini: —
| Benchmark | Gemini 1.5 Flash (May 2024) | Phi-3.5-mini |
|---|---|---|
| LMArena Non-English | 1278 | — |
| LMArena Chinese | 1295 | — |
| LMArena French | 1258 | — |
| LMArena German | 1262 | — |
| LMArena Japanese | 1252 | — |
| LMArena Korean | 1221 | — |
| LMArena Russian | 1288 | — |
| LMArena Spanish | 1243 | — |
Instruction Following Not comparable
Gemini 1.5 Flash (May 2024): 66.8 (#205), Phi-3.5-mini: —
| Benchmark | Gemini 1.5 Flash (May 2024) | Phi-3.5-mini |
|---|---|---|
| IFEval | 83.1% | — |
| LMArena Instruction Following | 1258 | — |
Long Context Not comparable
Gemini 1.5 Flash (May 2024): 39.0 (#187), Phi-3.5-mini: —
| Benchmark | Gemini 1.5 Flash (May 2024) | Phi-3.5-mini |
|---|---|---|
| LMArena Longer Query | 1284 | — |
Writing & Preference Not comparable
Gemini 1.5 Flash (May 2024): 48.7 (#196), Phi-3.5-mini: —
| Benchmark | Gemini 1.5 Flash (May 2024) | Phi-3.5-mini |
|---|---|---|
| LMArena Text | 1287 | — |
| LMArena Creative Writing | 1285 | — |
| WildBench | 79.2% | — |
| LMArena Multi-Turn | 1253 | — |
Frequently asked questions
Is Gemini 1.5 Flash (May 2024) better than Phi-3.5-mini?
Gemini 1.5 Flash (May 2024) has enough public results to be ranked (#246); Phi-3.5-mini does not yet, so treat this comparison as directional.
Is Gemini 1.5 Flash (May 2024) or Phi-3.5-mini better for coding?
They score almost the same on coding (34.4 vs 34.6); test both on your own repository before choosing.
How many benchmarks do Gemini 1.5 Flash (May 2024) and Phi-3.5-mini share?
5 benchmarks have published results for both models. Gemini 1.5 Flash (May 2024) has 42 scored results on Noometry and Phi-3.5-mini has 5.