# Gemini 3.8 Flash vs GPT-4.1 mini

> Gemini 3.8 Flash is the stronger model overall, scoring 59.5 to 33.5 on the Noometry Index. GPT-4.1 mini costs 2.1× 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-4-1-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-4.1 mini in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 64.7 to 10.9.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 68.4% for Gemini 3.8 Flash and 6.7% for GPT-4.1 mini.
- GPT-4.1 mini is cheaper at $0.40 / $1.60 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 1.05M.

## Snapshot

| | Gemini 3.8 Flash | GPT-4.1 mini |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 59.5 | 33.5 |
| Rank | 13 | 232 |
| Context | 1.05M | 1.05M |
| Input $/M | $0.75 | $0.40 |
| Output $/M | $3.75 | $1.60 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3.8 Flash: 56.4 (#17)
- GPT-4.1 mini: 30.4 (#286)

| Benchmark | Gemini 3.8 Flash | GPT-4.1 mini |
|---|---|---|
| SciCode | 56.6% | 40.4% |
| LMArena Coding | 1512 | 1367 |
| DeepSWE | 73.8% | — |
| FrontierCode | 41.2% | — |
| SWE-bench Verified (bash only) | — | 23.9% |
| Aider Polyglot | — | 32.4% |
| CursorBench | 39.6% | — |
| LMArena WebDev | 1581 | — |
| FrontierSWE | 19.6% | — |
| WeirdML | — | 37.6% |
| BigCodeBench Instruct | — | 48.9% |
| CadEval | — | 16% |
| ALE-Bench | 1,270 | — |

## Agentic & Tool Use

- Gemini 3.8 Flash: 40.3 (#22)
- GPT-4.1 mini: 33.0 (#52)

| Benchmark | Gemini 3.8 Flash | GPT-4.1 mini |
|---|---|---|
| APEX-Agents | 64.3% | — |
| Berkeley Function Calling Leaderboard | — | 50.5% |
| GDP.pdf | 23.4% | — |
| Vending-Bench 2 | 5,094 | — |

## Reasoning

- Gemini 3.8 Flash: 64.7 (#13)
- GPT-4.1 mini: 10.9 (#335)

| Benchmark | Gemini 3.8 Flash | GPT-4.1 mini |
|---|---|---|
| CritPt | 18.3% | 0% |
| Chess Puzzles | 61% | 7% |
| LMArena Hard Prompts | 1506 | 1349 |
| Mystery Game Puzzles | 47% | 7% |
| DTBench | 95.7% | 68.8% |
| LMCA | 52.9% | 21.1% |
| Epoch Capabilities Index | 157.13 | 135.01 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 48.6% |
| NYT Connections (extended) | 97.4% | — |
| ARC-AGI-1 | — | 3.5% |
| Surface Evolver Bench | 76.9% | — |

## Math

- Gemini 3.8 Flash: 65.2 (#22)
- GPT-4.1 mini: 23.1 (#264)

| Benchmark | Gemini 3.8 Flash | GPT-4.1 mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 68.4% | 6.7% |
| OTIS Mock AIME 2024-2025 | 98.9% | 44.7% |
| LMArena Math | 1528 | 1343 |
| FrontierMath Tier 4 | 22% | — |
| ProofBench | 48% | — |
| Omni-MATH | — | 49.1% |
| MATH Level 5 | — | 87.3% |
| FrontierMath (Feb 2025 set) | — | 4.5% |

## Knowledge

- Gemini 3.8 Flash: 74.9 (#2)
- GPT-4.1 mini: 34.7 (#183)

| Benchmark | Gemini 3.8 Flash | GPT-4.1 mini |
|---|---|---|
| GPQA Diamond | 95.4% | 65.8% |
| SimpleQA Verified | 69.7% | 12.7% |
| LMArena Expert | 1529 | 1338 |
| Humanity's Last Exam | 44.5% | — |
| MMLU-Pro | — | 78.3% |
| GPQA (HELM) | — | 61.4% |

## Multimodal

- Gemini 3.8 Flash: 40.9 (#33)
- GPT-4.1 mini: 35.2 (#77)

| Benchmark | Gemini 3.8 Flash | GPT-4.1 mini |
|---|---|---|
| LMArena Vision | 1312 | 1181 |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 31.7% | — |

## Multilingual

- Gemini 3.8 Flash: 57.9 (#5)
- GPT-4.1 mini: 45.9 (#161)

| Benchmark | Gemini 3.8 Flash | GPT-4.1 mini |
|---|---|---|
| LMArena Non-English | 1486 | 1318 |
| LMArena Chinese | 1547 | 1329 |
| LMArena French | 1502 | 1357 |
| LMArena German | 1470 | 1349 |
| LMArena Japanese | 1505 | 1291 |
| LMArena Korean | 1479 | 1298 |
| LMArena Russian | 1507 | 1324 |
| LMArena Spanish | 1492 | 1319 |

## Instruction Following

- Gemini 3.8 Flash: 78.2 (#11)
- GPT-4.1 mini: 73.9 (#113)

| Benchmark | Gemini 3.8 Flash | GPT-4.1 mini |
|---|---|---|
| LMArena Instruction Following | 1489 | 1332 |
| IFEval | — | 90.4% |

## Long Context

- Gemini 3.8 Flash: 46.2 (#23)
- GPT-4.1 mini: 31.8 (#270)

| Benchmark | Gemini 3.8 Flash | GPT-4.1 mini |
|---|---|---|
| LMArena Longer Query | 1506 | 1344 |
| Fiction.LiveBench | — | 44.4% |

## Writing & Preference

- Gemini 3.8 Flash: 72.1 (#16)
- GPT-4.1 mini: 48.8 (#193)

| Benchmark | Gemini 3.8 Flash | GPT-4.1 mini |
|---|---|---|
| LMArena Text | 1494 | 1341 |
| LMArena Creative Writing | 1485 | 1300 |
| EQ-Bench Creative Writing | 1748 | 1147 |
| LMArena Multi-Turn | 1503 | 1354 |
| WildBench | — | 83.8% |

## FAQ

### Is Gemini 3.8 Flash better than GPT-4.1 mini?

Gemini 3.8 Flash is the stronger model overall, scoring 59.5 to 33.5 on the Noometry Index. GPT-4.1 mini costs 2.1× 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-4.1 mini?

GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Gemini 3.8 Flash lists at $0.75 and $3.75.

### Is Gemini 3.8 Flash or GPT-4.1 mini better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 56.4 versus 30.4 in the Noometry coding category.

### Which has the bigger context window?

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

### How many benchmarks do Gemini 3.8 Flash and GPT-4.1 mini share?

30 benchmarks have published results for both models. Gemini 3.8 Flash has 46 scored results on Noometry and GPT-4.1 mini has 47.