# Gemini 3.5 Flash vs GPT-4.1

> Gemini 3.5 Flash is the stronger model overall, scoring 54.2 to 35.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-5-flash-vs-gpt-4-1
- Last updated: 2026-10-10
- Shared benchmarks: 36

## Summary

- They share 36 benchmarks with published results for both. Gemini 3.5 Flash scores higher in 9 categories and GPT-4.1 in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.5 Flash leads 62.8 to 11.7.
- The biggest single-benchmark swing is ARC-AGI-1: 92.5% for Gemini 3.5 Flash and 5.5% for GPT-4.1.
- Both cost about the same: $1.50 input and $9 output per million tokens.
- Gemini 3.5 Flash accepts more context: 1.05M tokens versus 1.05M.

## Snapshot

| | Gemini 3.5 Flash | GPT-4.1 |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 54.2 | 35.9 |
| Rank | 32 | 219 |
| Context | 1.05M | 1.05M |
| Input $/M | $1.50 | $2 |
| Output $/M | $9 | $8 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3.5 Flash: 49.4 (#49)
- GPT-4.1: 34.4 (#238)

| Benchmark | Gemini 3.5 Flash | GPT-4.1 |
|---|---|---|
| SWE-bench Verified | 79.3% | 48.5% |
| WeirdML | 62.6% | 39% |
| LMArena Coding | 1492 | 1391 |
| ALE-Bench | 911.02 | 558.1 |
| DeepSWE | 37.4% | — |
| SWE-bench Verified (bash only) | — | 39.6% |
| Aider Polyglot | — | 52.4% |
| LMArena WebDev | 1499 | — |
| SciCode | 53.1% | — |
| CadEval | — | 42% |

## Agentic & Tool Use

- Gemini 3.5 Flash: 24.7 (#114)
- GPT-4.1: 34.7 (#43)

| Benchmark | Gemini 3.5 Flash | GPT-4.1 |
|---|---|---|
| APEX-Agents | 27.5% | — |
| Berkeley Function Calling Leaderboard | — | 54% |
| GBAEval | 6.7% | — |
| GDP.pdf | 14% | — |
| Vending-Bench 2 | 5,396 | — |

## Reasoning

- Gemini 3.5 Flash: 62.8 (#18)
- GPT-4.1: 11.7 (#339)

| Benchmark | Gemini 3.5 Flash | GPT-4.1 |
|---|---|---|
| ARC-AGI-2 | 72.1% | 0.4% |
| SimpleBench | 76.7% | 27% |
| ARC-AGI-1 | 92.5% | 5.5% |
| Chess Puzzles | 50% | 6% |
| EnigmaEval | 25.4% | 2.2% |
| LMArena Hard Prompts | 1488 | 1384 |
| DTBench | 94.7% | 68.3% |
| LMCA | 47.1% | 25.6% |
| Epoch Capabilities Index | 154.46 | 136.78 |
| ForecastBench | 59 | 61.5 |
| Kagi LLM Benchmark | — | 52.3% |
| NYT Connections (extended) | 92.6% | — |
| CritPt | 13.1% | — |
| EBR-Bench | 4.8% | — |
| Mystery Game Puzzles | 32% | — |
| Surface Evolver Bench | 58.1% | — |

## Math

- Gemini 3.5 Flash: 60.7 (#36)
- GPT-4.1: 22.3 (#280)

| Benchmark | Gemini 3.5 Flash | GPT-4.1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 62.8% | 6% |
| OTIS Mock AIME 2024-2025 | 95.6% | 38.3% |
| LMArena Math | 1504 | 1370 |
| FrontierMath (Feb 2025 set) | 39% | 5.5% |
| FrontierMath Tier 4 (v1) | 14.6% | 0% |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.3% | — |
| ProofBench | 31% | — |
| Omni-MATH | — | 47.1% |
| MATH Level 5 | — | 83% |

## Knowledge

- Gemini 3.5 Flash: 66.3 (#11)
- GPT-4.1: 37.1 (#160)

| Benchmark | Gemini 3.5 Flash | GPT-4.1 |
|---|---|---|
| GPQA Diamond | 92.8% | 66.9% |
| SimpleQA Verified | 66.2% | 31.1% |
| LMArena Expert | 1495 | 1364 |
| Humanity's Last Exam | — | 5.4% |
| MMLU-Pro | — | 81.1% |
| Vectara Hallucination Rate | — | 5.6% |
| GPQA (HELM) | — | 65.9% |

## Multimodal

- Gemini 3.5 Flash: 45.7 (#15)
- GPT-4.1: 38.2 (#67)

| Benchmark | Gemini 3.5 Flash | GPT-4.1 |
|---|---|---|
| LMArena Vision | 1310 | 1211 |
| GeoBench | — | 72% |
| Blueprint-Bench 2 | 33.6% | — |
| LMArena Document | 1463 | — |

## Multilingual

- Gemini 3.5 Flash: 57.0 (#13)
- GPT-4.1: 49.4 (#133)

| Benchmark | Gemini 3.5 Flash | GPT-4.1 |
|---|---|---|
| LMArena Non-English | 1476 | 1370 |
| LMArena Chinese | 1526 | 1382 |
| LMArena French | 1490 | 1382 |
| LMArena German | 1492 | 1381 |
| LMArena Japanese | 1486 | 1319 |
| LMArena Korean | 1451 | 1339 |
| LMArena Russian | 1493 | 1377 |
| LMArena Spanish | 1480 | 1376 |

## Instruction Following

- Gemini 3.5 Flash: 77.0 (#30)
- GPT-4.1: 71.3 (#153)

| Benchmark | Gemini 3.5 Flash | GPT-4.1 |
|---|---|---|
| LMArena Instruction Following | 1467 | 1367 |
| IFEval | — | 83.8% |

## Long Context

- Gemini 3.5 Flash: 45.4 (#38)
- GPT-4.1: 40.0 (#163)

| Benchmark | Gemini 3.5 Flash | GPT-4.1 |
|---|---|---|
| LMArena Longer Query | 1482 | 1385 |
| Fiction.LiveBench | — | 63.9% |

## Writing & Preference

- Gemini 3.5 Flash: 65.5 (#47)
- GPT-4.1: 57.6 (#125)

| Benchmark | Gemini 3.5 Flash | GPT-4.1 |
|---|---|---|
| LMArena Text | 1482 | 1383 |
| LMArena Creative Writing | 1470 | 1363 |
| LMArena Multi-Turn | 1481 | 1398 |
| EQ-Bench Creative Writing | — | 1420 |
| WildBench | — | 85.4% |
| EQ-Bench 4 | 1087 | — |

## FAQ

### Is Gemini 3.5 Flash better than GPT-4.1?

Gemini 3.5 Flash is the stronger model overall, scoring 54.2 to 35.9 on the Noometry Index.

### Which is cheaper, Gemini 3.5 Flash or GPT-4.1?

Gemini 3.5 Flash is cheaper. It lists at $1.50 per million input tokens and $9 per million output tokens; GPT-4.1 lists at $2 and $8.

### Is Gemini 3.5 Flash or GPT-4.1 better for coding?

Gemini 3.5 Flash scores higher on coding benchmarks: 49.4 versus 34.4 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.5 Flash does, with 1.05M tokens against 1.05M.

### How many benchmarks do Gemini 3.5 Flash and GPT-4.1 share?

36 benchmarks have published results for both models. Gemini 3.5 Flash has 54 scored results on Noometry and GPT-4.1 has 52.