# Gemini 3.5 Flash vs GPT-5.1

> Gemini 3.5 Flash is the stronger model overall, scoring 54.1 to 48.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-5-flash-vs-gpt-5-1
- Last updated: 2026-10-10
- Shared benchmarks: 41

## Summary

- They share 41 benchmarks with published results for both. Gemini 3.5 Flash scores higher in 7 categories and GPT-5.1 in 3 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.5 Flash leads 62.7 to 39.9.
- The biggest single-benchmark swing is ARC-AGI-2: 72.1% for Gemini 3.5 Flash and 17.6% for GPT-5.1.
- 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 400K.

## Snapshot

| | Gemini 3.5 Flash | GPT-5.1 |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 54.1 | 48.8 |
| Rank | 29 | 47 |
| Context | 1.05M | 400K |
| Input $/M | $1.50 | $1.25 |
| Output $/M | $9 | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3.5 Flash: 49.1 (#46)
- GPT-5.1: 46.9 (#59)

| Benchmark | Gemini 3.5 Flash | GPT-5.1 |
|---|---|---|
| SWE-bench Verified | 79.3% | 68% |
| LMArena WebDev | 1499 | 1395 |
| SciCode | 53.1% | 43.3% |
| WeirdML | 62.6% | 60.8% |
| LMArena Coding | 1492 | 1454 |
| ALE-Bench | 911.02 | 1,192 |
| DeepSWE | 37.4% | — |
| SWE-bench Verified (bash only) | — | 66% |
| GSO | — | 13.7% |
| LiveBench Coding | — | 72.5% |

## Agentic & Tool Use

- Gemini 3.5 Flash: 24.8 (#107)
- GPT-5.1: 32.5 (#55)

| Benchmark | Gemini 3.5 Flash | GPT-5.1 |
|---|---|---|
| Vending-Bench 2 | 5,396 | 1,473 |
| Terminal-Bench | — | 47.6% |
| APEX-Agents | 27.5% | — |
| DeepResearch Bench | — | 42.8% |
| GBAEval | 6.7% | — |
| GDP.pdf | 14% | — |
| LMArena Search | — | 1199 |

## Reasoning

- Gemini 3.5 Flash: 62.7 (#16)
- GPT-5.1: 39.9 (#50)

| Benchmark | Gemini 3.5 Flash | GPT-5.1 |
|---|---|---|
| ARC-AGI-2 | 72.1% | 17.6% |
| SimpleBench | 76.7% | 53.2% |
| ARC-AGI-1 | 92.5% | 72.8% |
| CritPt | 13.1% | 4.9% |
| Chess Puzzles | 50% | 32% |
| EnigmaEval | 25.4% | 11.2% |
| LMArena Hard Prompts | 1488 | 1457 |
| Mystery Game Puzzles | 32% | 19% |
| DTBench | 94.7% | 90.1% |
| LMCA | 47.1% | 43.9% |
| Epoch Capabilities Index | 154.55 | 149.66 |
| ForecastBench | 59 | 58.1 |
| NYT Connections (extended) | 92.6% | — |
| EBR-Bench | 4.8% | — |
| LiveBench Reasoning | — | 95.8% |
| LiveBench Data Analysis | — | 72.1% |
| Surface Evolver Bench | 58.1% | — |
| LiveBench | — | 78.8% |

## Math

- Gemini 3.5 Flash: 60.5 (#30)
- GPT-5.1: 50.3 (#45)

| Benchmark | Gemini 3.5 Flash | GPT-5.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 88.6% |
| LMArena Math | 1502 | 1446 |
| FrontierMath (Feb 2025 set) | 39% | 31% |
| FrontierMath Tier 4 (v1) | 14.6% | 12.5% |
| FrontierMath (Tiers 1-3) | 62.8% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.3% | — |
| ProofBench | 31% | — |
| Omni-MATH | — | 46.4% |
| LiveBench Math | — | 94.5% |

## Knowledge

- Gemini 3.5 Flash: 66.3 (#10)
- GPT-5.1: 50.5 (#65)

| Benchmark | Gemini 3.5 Flash | GPT-5.1 |
|---|---|---|
| GPQA Diamond | 92.8% | 87.6% |
| SimpleQA Verified | 66.2% | 48% |
| LMArena Expert | 1493 | 1470 |
| Humanity's Last Exam | — | 23.7% |
| MMLU-Pro | — | 57.9% |
| Vectara Hallucination Rate | — | 10.9% |
| GPQA (HELM) | — | 44.2% |

## Multimodal

- Gemini 3.5 Flash: 45.7 (#13)
- GPT-5.1: 44.0 (#17)

| Benchmark | Gemini 3.5 Flash | GPT-5.1 |
|---|---|---|
| LMArena Vision | 1311 | 1250 |
| LMArena Document | 1463 | 1403 |
| VPCT | — | 58.7% |
| Blueprint-Bench 2 | 33.6% | — |

## Multilingual

- Gemini 3.5 Flash: 57.1 (#12)
- GPT-5.1: 54.0 (#51)

| Benchmark | Gemini 3.5 Flash | GPT-5.1 |
|---|---|---|
| LMArena Non-English | 1475 | 1431 |
| LMArena Chinese | 1525 | 1495 |
| LMArena French | 1490 | 1451 |
| LMArena German | 1500 | 1439 |
| LMArena Japanese | 1481 | 1453 |
| LMArena Korean | 1453 | 1401 |
| LMArena Russian | 1491 | 1435 |
| LMArena Spanish | 1478 | 1430 |

## Instruction Following

- Gemini 3.5 Flash: 77.2 (#29)
- GPT-5.1: 84.0 (#1)

| Benchmark | Gemini 3.5 Flash | GPT-5.1 |
|---|---|---|
| LMArena Instruction Following | 1466 | 1442 |
| LiveBench Instruction Following | — | 93.3% |
| IFEval | — | 93.5% |

## Long Context

- Gemini 3.5 Flash: 45.3 (#39)
- GPT-5.1: 47.6 (#14)

| Benchmark | Gemini 3.5 Flash | GPT-5.1 |
|---|---|---|
| LMArena Longer Query | 1481 | 1448 |
| CL-bench | — | 23.7% |
| CL-bench Life | — | 17.3% |

## Writing & Preference

- Gemini 3.5 Flash: 65.5 (#46)
- GPT-5.1: 64.7 (#53)

| Benchmark | Gemini 3.5 Flash | GPT-5.1 |
|---|---|---|
| LMArena Text | 1481 | 1443 |
| LMArena Creative Writing | 1467 | 1427 |
| LMArena Multi-Turn | 1482 | 1449 |
| WildBench | — | 86.3% |
| EQ-Bench 4 | 1087 | — |
| LiveBench Language | — | 80.2% |

## FAQ

### Is Gemini 3.5 Flash better than GPT-5.1?

Gemini 3.5 Flash is the stronger model overall, scoring 54.1 to 48.8 on the Noometry Index.

### Which is cheaper, Gemini 3.5 Flash or GPT-5.1?

Gemini 3.5 Flash is cheaper. It lists at $1.50 per million input tokens and $9 per million output tokens; GPT-5.1 lists at $1.25 and $10.

### Is Gemini 3.5 Flash or GPT-5.1 better for coding?

Gemini 3.5 Flash scores higher on coding benchmarks: 49.1 versus 46.9 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.5 Flash does, with 1.05M tokens against 400K.

### How many benchmarks do Gemini 3.5 Flash and GPT-5.1 share?

41 benchmarks have published results for both models. Gemini 3.5 Flash has 54 scored results on Noometry and GPT-5.1 has 63.