# Gemini 3.6 Flash vs Phi-4

> Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 31.2 on the Noometry Index. Phi-4 costs 17× less per token, which makes it the better buy when Gemini 3.6 Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-3-6-flash-vs-phi-4
- Last updated: 2026-10-11
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 9 categories and Phi-4 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.6 Flash leads 58.8 to 17.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 94.2% for Gemini 3.6 Flash and 13.8% for Phi-4.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.6 Flash.
- Gemini 3.6 Flash accepts more context: 1.05M tokens versus 128K.
- Phi-4 has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.6 Flash | Phi-4 |
|---|---|---|
| Provider | Google | Microsoft |
| Noometry Index | 54.1 | 31.2 |
| Rank | 33 | 279 |
| Context | 1.05M | 128K |
| Input $/M | $0.75 | $0.07 |
| Output $/M | $3.75 | $0.14 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.6 Flash: 50.0 (#48)
- Phi-4: 34.4 (#239)

| Benchmark | Gemini 3.6 Flash | Phi-4 |
|---|---|---|
| LMArena Coding | 1491 | 1231 |
| DeepSWE | 46.7% | — |
| FrontierCode | 34.4% | — |
| LMArena WebDev | 1538 | — |
| SciCode | 52.7% | — |
| WeirdML | 56.1% | — |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| BigCodeBench Complete | — | 55.4% |
| ALE-Bench | 715.52 | — |

## Agentic & Tool Use

- Gemini 3.6 Flash: 32.3 (#65)
- Phi-4: 22.8 (#128)

| Benchmark | Gemini 3.6 Flash | Phi-4 |
|---|---|---|
| APEX-Agents | 46.9% | — |
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |
| GDP.pdf | 14% | — |

## Reasoning

- Gemini 3.6 Flash: 58.8 (#22)
- Phi-4: 17.7 (#291)

| Benchmark | Gemini 3.6 Flash | Phi-4 |
|---|---|---|
| Chess Puzzles | 43% | 1% |
| LMArena Hard Prompts | 1485 | 1220 |
| Epoch Capabilities Index | 154.25 | 130.42 |
| ARC-AGI-2 | 60.4% | — |
| NYT Connections (extended) | 89% | — |
| ARC-AGI-1 | 91.2% | — |
| CritPt | 10.6% | — |
| LiveBench Reasoning | — | 47.8% |
| Mystery Game Puzzles | 30% | — |
| DTBench | 95.5% | — |
| LiveBench Data Analysis | — | 45.2% |
| LMCA | 44.9% | — |
| LiveBench | — | 41.6% |

## Math

- Gemini 3.6 Flash: 57.3 (#40)
- Phi-4: 20.8 (#285)

| Benchmark | Gemini 3.6 Flash | Phi-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.2% | 13.8% |
| LMArena Math | 1505 | 1246 |
| FrontierMath (Tiers 1-3) | 58.9% | — |
| FrontierMath Tier 4 | 22% | — |
| MathArena Final-Answer Competitions | 70.8% | — |
| ProofBench | 36% | — |
| LiveBench Math | — | 42% |
| MATH Level 5 | — | 64.9% |

## Knowledge

- Gemini 3.6 Flash: 67.8 (#8)
- Phi-4: 32.6 (#209)

| Benchmark | Gemini 3.6 Flash | Phi-4 |
|---|---|---|
| GPQA Diamond | 94.1% | 56.1% |
| LMArena Expert | 1488 | 1203 |
| SimpleQA Verified | 66.2% | — |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
| MMLU | — | 84.8% |

## Multimodal

- Gemini 3.6 Flash: 38.5 (#64)
- Phi-4: —

| Benchmark | Gemini 3.6 Flash | Phi-4 |
|---|---|---|
| LMArena Vision | 1298 | — |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 23.3% | — |
| LMArena Document | 1456 | — |

## Multilingual

- Gemini 3.6 Flash: 56.5 (#19)
- Phi-4: 37.2 (#237)

| Benchmark | Gemini 3.6 Flash | Phi-4 |
|---|---|---|
| LMArena Non-English | 1469 | 1197 |
| LMArena Chinese | 1531 | 1212 |
| LMArena French | 1504 | 1224 |
| LMArena German | 1478 | 1222 |
| LMArena Japanese | 1476 | 1158 |
| LMArena Korean | 1431 | 1151 |
| LMArena Russian | 1487 | 1209 |
| LMArena Spanish | 1475 | 1234 |

## Instruction Following

- Gemini 3.6 Flash: 77.0 (#33)
- Phi-4: 60.4 (#251)

| Benchmark | Gemini 3.6 Flash | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 1466 | 1201 |
| LiveBench Instruction Following | — | 58.4% |

## Long Context

- Gemini 3.6 Flash: 45.1 (#50)
- Phi-4: 36.9 (#226)

| Benchmark | Gemini 3.6 Flash | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1474 | 1217 |

## Writing & Preference

- Gemini 3.6 Flash: 68.2 (#27)
- Phi-4: 40.5 (#244)

| Benchmark | Gemini 3.6 Flash | Phi-4 |
|---|---|---|
| LMArena Text | 1479 | 1217 |
| LMArena Creative Writing | 1465 | 1182 |
| LMArena Multi-Turn | 1481 | 1206 |
| Short-Story Creative Writing | — | 62.6% |
| EQ-Bench Creative Writing | 1604 | — |
| LiveBench Language | — | 25.6% |

## FAQ

### Is Gemini 3.6 Flash better than Phi-4?

Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 31.2 on the Noometry Index. Phi-4 costs 17× less per token, which makes it the better buy when Gemini 3.6 Flash's lead doesn't matter for your workload.

### Which is cheaper, Gemini 3.6 Flash or Phi-4?

Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; Gemini 3.6 Flash lists at $0.75 and $3.75.

### Is Gemini 3.6 Flash or Phi-4 better for coding?

Gemini 3.6 Flash scores higher on coding benchmarks: 50.0 versus 34.4 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.6 Flash does, with 1.05M tokens against 128K.

### How many benchmarks do Gemini 3.6 Flash and Phi-4 share?

21 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and Phi-4 has 37.