# Gemini 3.6 Flash vs GPT-5.4 mini

> Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 44.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-6-flash-vs-gpt-5-4-mini
- Last updated: 2026-10-10
- Shared benchmarks: 39

## Summary

- They share 39 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 9 categories and GPT-5.4 mini in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.6 Flash leads 58.9 to 30.3.
- The biggest single-benchmark swing is ARC-AGI-2: 60.4% for Gemini 3.6 Flash and 18.9% for GPT-5.4 mini.
- Gemini 3.6 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- Gemini 3.6 Flash accepts more context: 1.05M tokens versus 400K.

## Snapshot

| | Gemini 3.6 Flash | GPT-5.4 mini |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 54.1 | 44.8 |
| Rank | 30 | 69 |
| Context | 1.05M | 400K |
| Input $/M | $0.75 | $0.75 |
| Output $/M | $3.75 | $4.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3.6 Flash: 49.6 (#45)
- GPT-5.4 mini: 45.0 (#67)

| Benchmark | Gemini 3.6 Flash | GPT-5.4 mini |
|---|---|---|
| FrontierCode | 34.4% | 27% |
| LMArena WebDev | 1536 | 1397 |
| SciCode | 52.7% | 49.9% |
| WeirdML | 56.1% | 60.3% |
| LMArena Coding | 1492 | 1438 |
| ALE-Bench | 715.52 | 1,189 |
| DeepSWE | 46.7% | — |

## Agentic & Tool Use

- Gemini 3.6 Flash: 32.4 (#56)
- GPT-5.4 mini: 29.6 (#74)

| Benchmark | Gemini 3.6 Flash | GPT-5.4 mini |
|---|---|---|
| APEX-Agents | 46.9% | — |
| DeepResearch Bench | — | 36.3% |
| GDP.pdf | 14% | — |

## Reasoning

- Gemini 3.6 Flash: 58.9 (#20)
- GPT-5.4 mini: 30.3 (#77)

| Benchmark | Gemini 3.6 Flash | GPT-5.4 mini |
|---|---|---|
| ARC-AGI-2 | 60.4% | 18.9% |
| NYT Connections (extended) | 89% | 61.8% |
| ARC-AGI-1 | 91.2% | 63.7% |
| CritPt | 10.6% | 10% |
| Chess Puzzles | 43% | 24% |
| LMArena Hard Prompts | 1486 | 1424 |
| Mystery Game Puzzles | 30% | 11% |
| DTBench | 95.5% | 80% |
| LMCA | 44.9% | 40.8% |
| Epoch Capabilities Index | 154.36 | 148.83 |
| Kagi LLM Benchmark | — | 37.9% |
| Thematic Generalization | — | 61.7% |
| ForecastBench | — | 57 |

## Math

- Gemini 3.6 Flash: 57.0 (#33)
- GPT-5.4 mini: 45.4 (#63)

| Benchmark | Gemini 3.6 Flash | GPT-5.4 mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 58.9% | 51.2% |
| FrontierMath Tier 4 | 22% | 9.8% |
| OTIS Mock AIME 2024-2025 | 94.2% | 88.9% |
| ProofBench | 36% | 21% |
| LMArena Math | 1504 | 1418 |
| MathArena Final-Answer Competitions | 70.8% | — |
| FrontierMath (Feb 2025 set) | — | 28.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- Gemini 3.6 Flash: 67.8 (#7)
- GPT-5.4 mini: 51.4 (#62)

| Benchmark | Gemini 3.6 Flash | GPT-5.4 mini |
|---|---|---|
| GPQA Diamond | 94.1% | 86.9% |
| SimpleQA Verified | 66.2% | 29.4% |
| LMArena Expert | 1489 | 1434 |
| Vectara Hallucination Rate | — | 5.5% |

## Multimodal

- Gemini 3.6 Flash: 38.7 (#55)
- GPT-5.4 mini: 39.0 (#51)

| Benchmark | Gemini 3.6 Flash | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | 1297 | 1245 |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 23.3% | — |
| LMArena Document | 1456 | — |

## Multilingual

- Gemini 3.6 Flash: 56.8 (#17)
- GPT-5.4 mini: 52.1 (#94)

| Benchmark | Gemini 3.6 Flash | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 1470 | 1405 |
| LMArena Chinese | 1530 | 1446 |
| LMArena French | 1501 | 1440 |
| LMArena German | 1478 | 1407 |
| LMArena Japanese | 1477 | 1375 |
| LMArena Korean | 1435 | 1369 |
| LMArena Russian | 1490 | 1417 |
| LMArena Spanish | 1477 | 1403 |

## Instruction Following

- Gemini 3.6 Flash: 77.2 (#27)
- GPT-5.4 mini: 74.3 (#99)

| Benchmark | Gemini 3.6 Flash | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1467 | 1405 |

## Long Context

- Gemini 3.6 Flash: 45.1 (#47)
- GPT-5.4 mini: 42.9 (#107)

| Benchmark | Gemini 3.6 Flash | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | 1475 | 1407 |

## Writing & Preference

- Gemini 3.6 Flash: 68.3 (#26)
- GPT-5.4 mini: 64.2 (#56)

| Benchmark | Gemini 3.6 Flash | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1478 | 1411 |
| LMArena Creative Writing | 1464 | 1370 |
| EQ-Bench Creative Writing | 1604 | 1665 |
| LMArena Multi-Turn | 1481 | 1429 |

## FAQ

### Is Gemini 3.6 Flash better than GPT-5.4 mini?

Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 44.8 on the Noometry Index.

### Which is cheaper, Gemini 3.6 Flash or GPT-5.4 mini?

Gemini 3.6 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.

### Is Gemini 3.6 Flash or GPT-5.4 mini better for coding?

Gemini 3.6 Flash scores higher on coding benchmarks: 49.6 versus 45.0 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.6 Flash does, with 1.05M tokens against 400K.

### How many benchmarks do Gemini 3.6 Flash and GPT-5.4 mini share?

39 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and GPT-5.4 mini has 46.