# Gemini 3.8 Flash vs GPT-5.4 mini

> Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 45.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-8-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 3.8 Flash scores higher in 10 categories and GPT-5.4 mini in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 30.4.
- The biggest single-benchmark swing is ARC-AGI-2: 89.2% for Gemini 3.8 Flash and 18.9% for GPT-5.4 mini.
- Gemini 3.8 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- Gemini 3.8 Flash accepts more context: 1.05M tokens versus 400K.

## Snapshot

| | Gemini 3.8 Flash | GPT-5.4 mini |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 61.8 | 45.0 |
| Rank | 11 | 76 |
| Context | 1.05M | 400K |
| Input $/M | $0.75 | $0.75 |
| Output $/M | $3.75 | $4.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3.8 Flash: 59.2 (#15)
- GPT-5.4 mini: 45.2 (#72)

| Benchmark | Gemini 3.8 Flash | GPT-5.4 mini |
|---|---|---|
| FrontierCode | 41.2% | 27% |
| LMArena WebDev | 1584 | 1397 |
| SciCode | 56.6% | 49.9% |
| WeirdML | 84.8% | 60.3% |
| LMArena Coding | 1510 | 1438 |
| ALE-Bench | 1,270 | 1,189 |
| DeepSWE | 73.8% | — |
| CursorBench | 39.6% | — |
| FrontierSWE | 19.6% | — |

## Agentic & Tool Use

- Gemini 3.8 Flash: 41.8 (#21)
- GPT-5.4 mini: 29.9 (#81)

| Benchmark | Gemini 3.8 Flash | GPT-5.4 mini |
|---|---|---|
| APEX-Agents | 64.3% | — |
| Remote Labor Index | 5.8% | — |
| DeepResearch Bench | — | 36.3% |
| GDP.pdf | 23.4% | — |
| Vending-Bench 2 | 5,094 | — |

## Reasoning

- Gemini 3.8 Flash: 76.9 (#5)
- GPT-5.4 mini: 30.4 (#85)

| Benchmark | Gemini 3.8 Flash | GPT-5.4 mini |
|---|---|---|
| ARC-AGI-2 | 89.2% | 18.9% |
| NYT Connections (extended) | 97.4% | 61.8% |
| ARC-AGI-1 | 98.5% | 63.7% |
| CritPt | 18.3% | 10% |
| Chess Puzzles | 61% | 24% |
| LMArena Hard Prompts | 1508 | 1424 |
| Mystery Game Puzzles | 47% | 11% |
| DTBench | 95.7% | 80% |
| LMCA | 52.9% | 40.8% |
| Epoch Capabilities Index | 156.71 | 148.84 |
| Kagi LLM Benchmark | — | 37.9% |
| Thematic Generalization | — | 61.7% |
| Surface Evolver Bench | 76.9% | — |
| ForecastBench | — | 57 |

## Math

- Gemini 3.8 Flash: 65.3 (#28)
- GPT-5.4 mini: 45.5 (#75)

| Benchmark | Gemini 3.8 Flash | GPT-5.4 mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 68.4% | 51.2% |
| FrontierMath Tier 4 | 22% | 9.8% |
| OTIS Mock AIME 2024-2025 | 98.9% | 88.9% |
| ProofBench | 48% | 21% |
| LMArena Math | 1528 | 1419 |
| FrontierMath (Feb 2025 set) | — | 28.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- Gemini 3.8 Flash: 74.8 (#2)
- GPT-5.4 mini: 51.5 (#67)

| Benchmark | Gemini 3.8 Flash | GPT-5.4 mini |
|---|---|---|
| GPQA Diamond | 95.4% | 86.9% |
| SimpleQA Verified | 69.7% | 29.4% |
| LMArena Expert | 1524 | 1435 |
| Humanity's Last Exam | 44.5% | — |
| Vectara Hallucination Rate | — | 5.5% |

## Multimodal

- Gemini 3.8 Flash: 40.7 (#45)
- GPT-5.4 mini: 39.7 (#56)

| Benchmark | Gemini 3.8 Flash | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | 1314 | 1245 |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 31.7% | — |

## Multilingual

- Gemini 3.8 Flash: 58.0 (#5)
- GPT-5.4 mini: 51.9 (#96)

| Benchmark | Gemini 3.8 Flash | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 1491 | 1405 |
| LMArena Chinese | 1554 | 1446 |
| LMArena French | 1498 | 1440 |
| LMArena German | 1493 | 1409 |
| LMArena Japanese | 1502 | 1374 |
| LMArena Korean | 1459 | 1368 |
| LMArena Russian | 1515 | 1417 |
| LMArena Spanish | 1485 | 1405 |

## Instruction Following

- Gemini 3.8 Flash: 78.0 (#13)
- GPT-5.4 mini: 74.1 (#102)

| Benchmark | Gemini 3.8 Flash | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1490 | 1405 |

## Long Context

- Gemini 3.8 Flash: 46.3 (#24)
- GPT-5.4 mini: 43.0 (#112)

| Benchmark | Gemini 3.8 Flash | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | 1508 | 1407 |

## Writing & Preference

- Gemini 3.8 Flash: 72.2 (#15)
- GPT-5.4 mini: 64.0 (#58)

| Benchmark | Gemini 3.8 Flash | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1499 | 1412 |
| LMArena Creative Writing | 1492 | 1370 |
| EQ-Bench Creative Writing | 1748 | 1665 |
| LMArena Multi-Turn | 1501 | 1429 |

## FAQ

### Is Gemini 3.8 Flash better than GPT-5.4 mini?

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 45.0 on the Noometry Index.

### Which is cheaper, Gemini 3.8 Flash or GPT-5.4 mini?

Gemini 3.8 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 3.8 Flash or GPT-5.4 mini better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 45.2 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.8 Flash does, with 1.05M tokens against 400K.

### How many benchmarks do Gemini 3.8 Flash and GPT-5.4 mini share?

39 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and GPT-5.4 mini has 46.