# Gemini 3.6 Flash vs GPT-5.1

> Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 48.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-6-flash-vs-gpt-5-1
- Last updated: 2026-10-10
- Shared benchmarks: 34

## Summary

- They share 34 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 6 categories and GPT-5.1 in 4 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.6 Flash leads 58.9 to 39.9.
- The biggest single-benchmark swing is ARC-AGI-2: 60.4% for Gemini 3.6 Flash and 17.6% for GPT-5.1.
- Gemini 3.6 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
- Gemini 3.6 Flash accepts more context: 1.05M tokens versus 400K.

## Snapshot

| | Gemini 3.6 Flash | GPT-5.1 |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 54.1 | 48.8 |
| Rank | 30 | 47 |
| Context | 1.05M | 400K |
| Input $/M | $0.75 | $1.25 |
| Output $/M | $3.75 | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3.6 Flash: 49.6 (#45)
- GPT-5.1: 46.9 (#59)

| Benchmark | Gemini 3.6 Flash | GPT-5.1 |
|---|---|---|
| LMArena WebDev | 1536 | 1395 |
| SciCode | 52.7% | 43.3% |
| WeirdML | 56.1% | 60.8% |
| LMArena Coding | 1492 | 1454 |
| ALE-Bench | 715.52 | 1,192 |
| SWE-bench Verified | — | 68% |
| DeepSWE | 46.7% | — |
| FrontierCode | 34.4% | — |
| SWE-bench Verified (bash only) | — | 66% |
| GSO | — | 13.7% |
| LiveBench Coding | — | 72.5% |

## Agentic & Tool Use

- Gemini 3.6 Flash: 32.4 (#56)
- GPT-5.1: 32.5 (#55)

| Benchmark | Gemini 3.6 Flash | GPT-5.1 |
|---|---|---|
| Terminal-Bench | — | 47.6% |
| APEX-Agents | 46.9% | — |
| DeepResearch Bench | — | 42.8% |
| GDP.pdf | 14% | — |
| LMArena Search | — | 1199 |
| Vending-Bench 2 | — | 1,473 |

## Reasoning

- Gemini 3.6 Flash: 58.9 (#20)
- GPT-5.1: 39.9 (#50)

| Benchmark | Gemini 3.6 Flash | GPT-5.1 |
|---|---|---|
| ARC-AGI-2 | 60.4% | 17.6% |
| ARC-AGI-1 | 91.2% | 72.8% |
| CritPt | 10.6% | 4.9% |
| Chess Puzzles | 43% | 32% |
| LMArena Hard Prompts | 1486 | 1457 |
| Mystery Game Puzzles | 30% | 19% |
| DTBench | 95.5% | 90.1% |
| LMCA | 44.9% | 43.9% |
| Epoch Capabilities Index | 154.36 | 149.66 |
| SimpleBench | — | 53.2% |
| NYT Connections (extended) | 89% | — |
| EnigmaEval | — | 11.2% |
| LiveBench Reasoning | — | 95.8% |
| LiveBench Data Analysis | — | 72.1% |
| ForecastBench | — | 58.1 |
| LiveBench | — | 78.8% |

## Math

- Gemini 3.6 Flash: 57.0 (#33)
- GPT-5.1: 50.3 (#45)

| Benchmark | Gemini 3.6 Flash | GPT-5.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.2% | 88.6% |
| LMArena Math | 1504 | 1446 |
| FrontierMath (Tiers 1-3) | 58.9% | — |
| FrontierMath Tier 4 | 22% | — |
| MathArena Final-Answer Competitions | 70.8% | — |
| ProofBench | 36% | — |
| Omni-MATH | — | 46.4% |
| LiveBench Math | — | 94.5% |
| FrontierMath (Feb 2025 set) | — | 31% |
| FrontierMath Tier 4 (v1) | — | 12.5% |

## Knowledge

- Gemini 3.6 Flash: 67.8 (#7)
- GPT-5.1: 50.5 (#65)

| Benchmark | Gemini 3.6 Flash | GPT-5.1 |
|---|---|---|
| GPQA Diamond | 94.1% | 87.6% |
| SimpleQA Verified | 66.2% | 48% |
| LMArena Expert | 1489 | 1470 |
| Humanity's Last Exam | — | 23.7% |
| MMLU-Pro | — | 57.9% |
| Vectara Hallucination Rate | — | 10.9% |
| GPQA (HELM) | — | 44.2% |

## Multimodal

- Gemini 3.6 Flash: 38.7 (#55)
- GPT-5.1: 44.0 (#17)

| Benchmark | Gemini 3.6 Flash | GPT-5.1 |
|---|---|---|
| LMArena Vision | 1297 | 1250 |
| LMArena Document | 1456 | 1403 |
| VPCT | — | 58.7% |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 23.3% | — |

## Multilingual

- Gemini 3.6 Flash: 56.8 (#17)
- GPT-5.1: 54.0 (#51)

| Benchmark | Gemini 3.6 Flash | GPT-5.1 |
|---|---|---|
| LMArena Non-English | 1470 | 1431 |
| LMArena Chinese | 1530 | 1495 |
| LMArena French | 1501 | 1451 |
| LMArena German | 1478 | 1439 |
| LMArena Japanese | 1477 | 1453 |
| LMArena Korean | 1435 | 1401 |
| LMArena Russian | 1490 | 1435 |
| LMArena Spanish | 1477 | 1430 |

## Instruction Following

- Gemini 3.6 Flash: 77.2 (#27)
- GPT-5.1: 84.0 (#1)

| Benchmark | Gemini 3.6 Flash | GPT-5.1 |
|---|---|---|
| LMArena Instruction Following | 1467 | 1442 |
| LiveBench Instruction Following | — | 93.3% |
| IFEval | — | 93.5% |

## Long Context

- Gemini 3.6 Flash: 45.1 (#47)
- GPT-5.1: 47.6 (#14)

| Benchmark | Gemini 3.6 Flash | GPT-5.1 |
|---|---|---|
| LMArena Longer Query | 1475 | 1448 |
| CL-bench | — | 23.7% |
| CL-bench Life | — | 17.3% |

## Writing & Preference

- Gemini 3.6 Flash: 68.3 (#26)
- GPT-5.1: 64.7 (#53)

| Benchmark | Gemini 3.6 Flash | GPT-5.1 |
|---|---|---|
| LMArena Text | 1478 | 1443 |
| LMArena Creative Writing | 1464 | 1427 |
| LMArena Multi-Turn | 1481 | 1449 |
| EQ-Bench Creative Writing | 1604 | — |
| WildBench | — | 86.3% |
| LiveBench Language | — | 80.2% |

## FAQ

### Is Gemini 3.6 Flash better than GPT-5.1?

Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 48.8 on the Noometry Index.

### Which is cheaper, Gemini 3.6 Flash or GPT-5.1?

Gemini 3.6 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; GPT-5.1 lists at $1.25 and $10.

### Is Gemini 3.6 Flash or GPT-5.1 better for coding?

Gemini 3.6 Flash scores higher on coding benchmarks: 49.6 versus 46.9 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.6 Flash does, with 1.05M tokens against 400K.

### How many benchmarks do Gemini 3.6 Flash and GPT-5.1 share?

34 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and GPT-5.1 has 63.