# Gemini 3.8 Flash vs GPT-4o mini

> Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 25.5 on the Noometry Index. GPT-4o mini costs 5.7× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-3-8-flash-vs-gpt-4o-mini
- Last updated: 2026-10-10
- Shared benchmarks: 30

## Summary

- They share 30 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 10 categories and GPT-4o 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 8.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.9% for Gemini 3.8 Flash and 6.9% for GPT-4o mini.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.8 Flash.
- Gemini 3.8 Flash accepts more context: 1.05M tokens versus 128K.

## Snapshot

| | Gemini 3.8 Flash | GPT-4o mini |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 61.8 | 25.5 |
| Rank | 11 | 343 |
| Context | 1.05M | 128K |
| Input $/M | $0.75 | $0.15 |
| Output $/M | $3.75 | $0.60 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3.8 Flash: 59.2 (#15)
- GPT-4o mini: 22.0 (#335)

| Benchmark | Gemini 3.8 Flash | GPT-4o mini |
|---|---|---|
| WeirdML | 84.8% | 11.8% |
| LMArena Coding | 1510 | 1290 |
| DeepSWE | 73.8% | — |
| FrontierCode | 41.2% | — |
| Aider Polyglot | — | 3.6% |
| CursorBench | 39.6% | — |
| LMArena WebDev | 1584 | — |
| FrontierSWE | 19.6% | — |
| SciCode | 56.6% | — |
| BigCodeBench Instruct | — | 46.1% |
| LiveBench Coding | — | 43.1% |
| BigCodeBench Complete | — | 57.4% |
| ALE-Bench | 1,270 | — |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 72.2% |

## Agentic & Tool Use

- Gemini 3.8 Flash: 41.8 (#21)
- GPT-4o mini: 27.5 (#101)

| Benchmark | Gemini 3.8 Flash | GPT-4o mini |
|---|---|---|
| APEX-Agents | 64.3% | — |
| Remote Labor Index | 5.8% | — |
| BALROG | — | 17.4% |
| GDP.pdf | 23.4% | — |
| Vending-Bench 2 | 5,094 | — |

## Reasoning

- Gemini 3.8 Flash: 76.9 (#5)
- GPT-4o mini: 8.7 (#347)

| Benchmark | Gemini 3.8 Flash | GPT-4o mini |
|---|---|---|
| ARC-AGI-2 | 89.2% | 0% |
| Chess Puzzles | 61% | 0% |
| LMArena Hard Prompts | 1508 | 1267 |
| Mystery Game Puzzles | 47% | 12% |
| DTBench | 95.7% | 54.4% |
| LMCA | 52.9% | 10.4% |
| Epoch Capabilities Index | 156.71 | 126.56 |
| SimpleBench | — | 10.7% |
| Kagi LLM Benchmark | — | 28.8% |
| NYT Connections (extended) | 97.4% | — |
| ARC-AGI-1 | 98.5% | — |
| CritPt | 18.3% | — |
| LiveBench Reasoning | — | 32.8% |
| LiveBench Data Analysis | — | 50% |
| Surface Evolver Bench | 76.9% | — |
| LiveBench | — | 41.3% |
| PIQA | — | 88.7% |

## Math

- Gemini 3.8 Flash: 65.3 (#28)
- GPT-4o mini: 10.4 (#314)

| Benchmark | Gemini 3.8 Flash | GPT-4o mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 68.4% | 0.7% |
| OTIS Mock AIME 2024-2025 | 98.9% | 6.9% |
| LMArena Math | 1528 | 1267 |
| FrontierMath Tier 4 | 22% | — |
| ProofBench | 48% | — |
| Omni-MATH | — | 28% |
| LiveBench Math | — | 36.3% |
| MATH Level 5 | — | 52.6% |
| GSM8K | — | 91.3% |

## Knowledge

- Gemini 3.8 Flash: 74.8 (#2)
- GPT-4o mini: 17.7 (#284)

| Benchmark | Gemini 3.8 Flash | GPT-4o mini |
|---|---|---|
| GPQA Diamond | 95.4% | 37.7% |
| SimpleQA Verified | 69.7% | 8.3% |
| LMArena Expert | 1524 | 1235 |
| Humanity's Last Exam | 44.5% | — |
| MMLU-Pro | — | 60.3% |
| Confabulations | — | 37.2% |
| GPQA (HELM) | — | 36.8% |
| BoolQ | — | 88.7% |
| MMLU | — | 81.8% |

## Multimodal

- Gemini 3.8 Flash: 40.7 (#45)
- GPT-4o mini: 25.9 (#122)

| Benchmark | Gemini 3.8 Flash | GPT-4o mini |
|---|---|---|
| LMArena Vision | 1314 | 1066 |
| Video-MME | — | 64.8% |
| GeoBench | — | 64% |
| VPCT | — | 34% |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 31.7% | — |

## Multilingual

- Gemini 3.8 Flash: 58.0 (#5)
- GPT-4o mini: 42.0 (#199)

| Benchmark | Gemini 3.8 Flash | GPT-4o mini |
|---|---|---|
| LMArena Non-English | 1491 | 1266 |
| LMArena Chinese | 1554 | 1265 |
| LMArena French | 1498 | 1297 |
| LMArena German | 1493 | 1272 |
| LMArena Japanese | 1502 | 1216 |
| LMArena Korean | 1459 | 1195 |
| LMArena Russian | 1515 | 1275 |
| LMArena Spanish | 1485 | 1276 |

## Instruction Following

- Gemini 3.8 Flash: 78.0 (#13)
- GPT-4o mini: 61.9 (#239)

| Benchmark | Gemini 3.8 Flash | GPT-4o mini |
|---|---|---|
| LMArena Instruction Following | 1490 | 1258 |
| LiveBench Instruction Following | — | 56.8% |
| IFEval | — | 78.2% |

## Long Context

- Gemini 3.8 Flash: 46.3 (#24)
- GPT-4o mini: 39.1 (#186)

| Benchmark | Gemini 3.8 Flash | GPT-4o mini |
|---|---|---|
| LMArena Longer Query | 1508 | 1289 |

## Writing & Preference

- Gemini 3.8 Flash: 72.2 (#15)
- GPT-4o mini: 39.5 (#248)

| Benchmark | Gemini 3.8 Flash | GPT-4o mini |
|---|---|---|
| LMArena Text | 1499 | 1286 |
| LMArena Creative Writing | 1492 | 1268 |
| EQ-Bench Creative Writing | 1748 | 873 |
| LMArena Multi-Turn | 1501 | 1285 |
| Short-Story Creative Writing | — | 67.2% |
| WildBench | — | 79.1% |
| LiveBench Language | — | 28.6% |

## FAQ

### Is Gemini 3.8 Flash better than GPT-4o mini?

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 25.5 on the Noometry Index. GPT-4o mini costs 5.7× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.

### Which is cheaper, Gemini 3.8 Flash or GPT-4o mini?

GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Gemini 3.8 Flash lists at $0.75 and $3.75.

### Is Gemini 3.8 Flash or GPT-4o mini better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 22.0 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.8 Flash does, with 1.05M tokens against 128K.

### How many benchmarks do Gemini 3.8 Flash and GPT-4o mini share?

30 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and GPT-4o mini has 60.