Model comparison
Gemini 3 Flash Preview vs Phi-4 Mini
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 30.9 on the Noometry Index. Phi-4 Mini costs 8.6× less per token, which makes it the better buy when Gemini 3 Flash Preview's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
Google
MicrosoftSummary
- They share 1 benchmark with published results for both. Gemini 3 Flash Preview scores higher in 3 categories and Phi-4 Mini in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3 Flash Preview leads 58.8 to 25.3.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 13.5% for Gemini 3 Flash Preview and 23.5% for Phi-4 Mini.
- Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $0.50 / $3 for Gemini 3 Flash Preview.
- Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 128K.
- Phi-4 Mini has downloadable open weights; the other is API-only.
Side by side
| Gemini 3 Flash Preview | Phi-4 Mini | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 52.3 | 30.9 |
| Released | 2025-12-17 | 2024-12-11 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 128K |
| Max output | 66K | 4K |
| Input $ / M tokens | $0.50 | $0.075 |
| Output $ / M tokens | $3 | $0.30 |
| Results tracked | 59 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 50.9 (#42), Phi-4 Mini: 28.1 (#317)
| Benchmark | Gemini 3 Flash Preview | Phi-4 Mini |
|---|---|---|
| SWE-bench Verified | 75.4% | — |
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1439 | — |
| SWE-bench Multilingual | 72.7% | — |
| SciCode | — | 10.8% |
| GSO | 9.8% | — |
| WeirdML | 61.6% | — |
| LMArena Coding | 1460 | — |
| ALE-Bench | 1,367 | — |
Agentic & Tool Use Not comparable
Gemini 3 Flash Preview: 38.7 (#29), Phi-4 Mini: —
| Benchmark | Gemini 3 Flash Preview | Phi-4 Mini |
|---|---|---|
| Terminal-Bench | 64.3% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 27.3% | — |
| τ²-bench Retail | 76.8% | — |
| τ²-bench Telecom | 91.2% | — |
| DeepResearch Bench | 49.8% | — |
| BALROG | 48.1% | — |
| GDP.pdf | 10% | — |
| LMArena Search | 1198 | — |
| Vending-Bench 2 | 3,635 | — |
Reasoning Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 49.2 (#37), Phi-4 Mini: 22.4 (#195)
| Benchmark | Gemini 3 Flash Preview | Phi-4 Mini |
|---|---|---|
| ARC-AGI-2 | 33.6% | — |
| SimpleBench | 61.1% | — |
| NYT Connections (extended) | 83.1% | — |
| ARC-AGI-1 | 84.7% | — |
| CritPt | — | 0% |
| Chess Puzzles | 40% | — |
| LMArena Hard Prompts | 1465 | — |
| Mystery Game Puzzles | 26% | — |
| DTBench | 89.1% | — |
| LMCA | 43.1% | — |
| Epoch Capabilities Index | 151.8 | — |
| ForecastBench | 58.5 | — |
Math Not comparable
Gemini 3 Flash Preview: 51.7 (#55), Phi-4 Mini: —
| Benchmark | Gemini 3 Flash Preview | Phi-4 Mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 17.1% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| ProofBench | 15% | — |
| LMArena Math | 1473 | — |
| FrontierMath (Feb 2025 set) | 35.6% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 58.8 (#33), Phi-4 Mini: 25.3 (#262)
| Benchmark | Gemini 3 Flash Preview | Phi-4 Mini |
|---|---|---|
| Vectara Hallucination Rate | 13.5% | 23.5% |
| GPQA Diamond | 89.4% | — |
| SimpleQA Verified | 66.8% | — |
| LMArena Expert | 1462 | — |
Multimodal Not comparable
Gemini 3 Flash Preview: 45.5 (#16), Phi-4 Mini: —
| Benchmark | Gemini 3 Flash Preview | Phi-4 Mini |
|---|---|---|
| LMArena Vision | 1285 | — |
| GeoBench | 88% | — |
| VPCT | 72.6% | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1413 | — |
Multilingual Not comparable
Gemini 3 Flash Preview: 55.7 (#27), Phi-4 Mini: —
| Benchmark | Gemini 3 Flash Preview | Phi-4 Mini |
|---|---|---|
| LMArena Non-English | 1458 | — |
| LMArena Chinese | 1511 | — |
| LMArena French | 1477 | — |
| LMArena German | 1497 | — |
| LMArena Japanese | 1489 | — |
| LMArena Korean | 1443 | — |
| LMArena Russian | 1480 | — |
| LMArena Spanish | 1469 | — |
Instruction Following Not comparable
Gemini 3 Flash Preview: 75.7 (#56), Phi-4 Mini: —
| Benchmark | Gemini 3 Flash Preview | Phi-4 Mini |
|---|---|---|
| LMArena Instruction Following | 1437 | — |
Long Context Not comparable
Gemini 3 Flash Preview: 44.4 (#67), Phi-4 Mini: —
| Benchmark | Gemini 3 Flash Preview | Phi-4 Mini |
|---|---|---|
| LMArena Longer Query | 1452 | — |
Writing & Preference Not comparable
Gemini 3 Flash Preview: 65.5 (#45), Phi-4 Mini: —
| Benchmark | Gemini 3 Flash Preview | Phi-4 Mini |
|---|---|---|
| LMArena Text | 1466 | — |
| LMArena Creative Writing | 1457 | — |
| LMArena Multi-Turn | 1471 | — |
Frequently asked questions
Is Gemini 3 Flash Preview better than Phi-4 Mini?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 30.9 on the Noometry Index. Phi-4 Mini costs 8.6× less per token, which makes it the better buy when Gemini 3 Flash Preview's lead doesn't matter for your workload.
Which is cheaper, Gemini 3 Flash Preview or Phi-4 Mini?
Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; Gemini 3 Flash Preview lists at $0.50 and $3.
Is Gemini 3 Flash Preview or Phi-4 Mini better for coding?
Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 28.1 in the Noometry coding category.
Which has the bigger context window?
Gemini 3 Flash Preview does, with 1.05M tokens against 128K.
How many benchmarks do Gemini 3 Flash Preview and Phi-4 Mini share?
1 benchmark has published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and Phi-4 Mini has 3.