# Gemini 3.6 Flash vs GPT-5

> Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 50.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-6-flash-vs-gpt-5
- Last updated: 2026-10-10
- Shared benchmarks: 37

## Summary

- They share 37 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 6 categories and GPT-5 in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where GPT-5 leads 69.5 to 45.1.
- The biggest single-benchmark swing is ARC-AGI-2: 60.4% for Gemini 3.6 Flash and 9.9% for GPT-5.
- Gemini 3.6 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $1.25 / $10 for GPT-5.
- Gemini 3.6 Flash accepts more context: 1.05M tokens versus 400K.

## Snapshot

| | Gemini 3.6 Flash | GPT-5 |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 54.1 | 50.9 |
| Rank | 33 | 45 |
| Context | 1.05M | 400K |
| Input $/M | $0.75 | $1.25 |
| Output $/M | $3.75 | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3.6 Flash: 50.0 (#48)
- GPT-5: 50.3 (#47)

| Benchmark | Gemini 3.6 Flash | GPT-5 |
|---|---|---|
| LMArena WebDev | 1538 | 1418 |
| SciCode | 52.7% | 42.9% |
| WeirdML | 56.1% | 60.7% |
| LMArena Coding | 1491 | 1436 |
| ALE-Bench | 715.52 | 1,162 |
| SWE-bench Verified | — | 73.6% |
| DeepSWE | 46.7% | — |
| FrontierCode | 34.4% | — |
| SWE-bench Verified (bash only) | — | 65% |
| Aider Polyglot | — | 88% |
| GSO | — | 6.9% |
| AlgoTune | — | 1.67 |

## Agentic & Tool Use

- Gemini 3.6 Flash: 32.3 (#65)
- GPT-5: 33.1 (#56)

| Benchmark | Gemini 3.6 Flash | GPT-5 |
|---|---|---|
| Terminal-Bench | — | 49.6% |
| APEX-Agents | 46.9% | — |
| GDPval | — | 34.8% |
| Remote Labor Index | — | 1.7% |
| DeepResearch Bench | — | 49.6% |
| BALROG | — | 32.8% |
| GDP.pdf | 14% | — |
| LMArena Search | — | 1133 |
| METR Time Horizons | — | 69.6% |

## Reasoning

- Gemini 3.6 Flash: 58.8 (#22)
- GPT-5: 38.3 (#64)

| Benchmark | Gemini 3.6 Flash | GPT-5 |
|---|---|---|
| ARC-AGI-2 | 60.4% | 9.9% |
| ARC-AGI-1 | 91.2% | 65.7% |
| CritPt | 10.6% | 12.6% |
| Chess Puzzles | 43% | 37% |
| LMArena Hard Prompts | 1485 | 1416 |
| Mystery Game Puzzles | 30% | 23% |
| DTBench | 95.5% | 90.7% |
| LMCA | 44.9% | 40% |
| Epoch Capabilities Index | 154.25 | 150 |
| SimpleBench | — | 56.7% |
| Kagi LLM Benchmark | — | 72.7% |
| NYT Connections (extended) | 89% | — |
| EnigmaEval | — | 10.5% |
| EBR-Bench | — | 12.7% |
| ForecastBench | — | 61.4 |

## Math

- Gemini 3.6 Flash: 57.3 (#40)
- GPT-5: 55.0 (#44)

| Benchmark | Gemini 3.6 Flash | GPT-5 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 58.9% | 55.4% |
| FrontierMath Tier 4 | 22% | 22% |
| OTIS Mock AIME 2024-2025 | 94.2% | 91.4% |
| ProofBench | 36% | 18% |
| LMArena Math | 1505 | 1407 |
| MathArena Final-Answer Competitions | 70.8% | — |
| Omni-MATH | — | 64.7% |
| MATH Level 5 | — | 98.1% |
| FrontierMath (Feb 2025 set) | — | 32.4% |
| FrontierMath Tier 4 (v1) | — | 12.5% |

## Knowledge

- Gemini 3.6 Flash: 67.8 (#8)
- GPT-5: 56.6 (#43)

| Benchmark | Gemini 3.6 Flash | GPT-5 |
|---|---|---|
| GPQA Diamond | 94.1% | 86.2% |
| SimpleQA Verified | 66.2% | 50.1% |
| LMArena Expert | 1488 | 1419 |
| Humanity's Last Exam | — | 25.3% |
| MMLU-Pro | — | 86.3% |
| Confabulations | — | 10.3% |
| Vectara Hallucination Rate | — | 14.7% |
| GPQA (HELM) | — | 79.2% |

## Multimodal

- Gemini 3.6 Flash: 38.5 (#64)
- GPT-5: 46.8 (#13)

| Benchmark | Gemini 3.6 Flash | GPT-5 |
|---|---|---|
| LMArena Vision | 1298 | 1232 |
| GeoBench | — | 81% |
| VPCT | — | 66% |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 23.3% | — |
| LMArena Document | 1456 | — |

## Multilingual

- Gemini 3.6 Flash: 56.5 (#19)
- GPT-5: 51.4 (#110)

| Benchmark | Gemini 3.6 Flash | GPT-5 |
|---|---|---|
| LMArena Non-English | 1469 | 1397 |
| LMArena Chinese | 1531 | 1422 |
| LMArena French | 1504 | 1410 |
| LMArena German | 1478 | 1416 |
| LMArena Japanese | 1476 | 1409 |
| LMArena Korean | 1431 | 1360 |
| LMArena Russian | 1487 | 1406 |
| LMArena Spanish | 1475 | 1399 |

## Instruction Following

- Gemini 3.6 Flash: 77.0 (#33)
- GPT-5: 73.8 (#113)

| Benchmark | Gemini 3.6 Flash | GPT-5 |
|---|---|---|
| LMArena Instruction Following | 1466 | 1388 |
| IFEval | — | 87.5% |

## Long Context

- Gemini 3.6 Flash: 45.1 (#50)
- GPT-5: 69.5 (#2)

| Benchmark | Gemini 3.6 Flash | GPT-5 |
|---|---|---|
| LMArena Longer Query | 1474 | 1399 |
| Fiction.LiveBench | — | 97.2% |

## Writing & Preference

- Gemini 3.6 Flash: 68.2 (#27)
- GPT-5: 63.4 (#65)

| Benchmark | Gemini 3.6 Flash | GPT-5 |
|---|---|---|
| LMArena Text | 1479 | 1406 |
| LMArena Creative Writing | 1465 | 1365 |
| EQ-Bench Creative Writing | 1604 | 1627 |
| LMArena Multi-Turn | 1481 | 1426 |
| Short-Story Creative Writing | — | 86% |
| WildBench | — | 85.7% |

## FAQ

### Is Gemini 3.6 Flash better than GPT-5?

Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 50.9 on the Noometry Index.

### Which is cheaper, Gemini 3.6 Flash or GPT-5?

Gemini 3.6 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; GPT-5 lists at $1.25 and $10.

### Is Gemini 3.6 Flash or GPT-5 better for coding?

They score almost the same on coding (50.0 vs 50.3); test both on your own repository before choosing.

### 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 share?

37 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and GPT-5 has 69.