# Gemini 3.6 Flash vs GPT-5.2

> Gemini 3.6 Flash and GPT-5.2 score almost the same on the Noometry Index (54.1 vs 54.1), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/gemini-3-6-flash-vs-gpt-5-2
- Last updated: 2026-10-10
- Shared benchmarks: 39

## Summary

- They share 39 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 6 categories and GPT-5.2 in 4 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where GPT-5.2 leads 51.3 to 38.5.
- The biggest single-benchmark swing is SimpleQA Verified: 66.2% for Gemini 3.6 Flash and 37.1% for GPT-5.2.
- Gemini 3.6 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $1.75 / $14 for GPT-5.2.
- Gemini 3.6 Flash accepts more context: 1.05M tokens versus 400K.

## Snapshot

| | Gemini 3.6 Flash | GPT-5.2 |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 54.1 | 54.1 |
| Rank | 33 | 34 |
| Context | 1.05M | 400K |
| Input $/M | $0.75 | $1.75 |
| Output $/M | $3.75 | $14 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3.6 Flash: 50.0 (#48)
- GPT-5.2: 51.6 (#37)

| Benchmark | Gemini 3.6 Flash | GPT-5.2 |
|---|---|---|
| LMArena WebDev | 1538 | 1416 |
| WeirdML | 56.1% | 72.2% |
| LMArena Coding | 1491 | 1447 |
| ALE-Bench | 715.52 | 1,294 |
| SWE-bench Verified | — | 73.8% |
| DeepSWE | 46.7% | — |
| FrontierCode | 34.4% | — |
| SWE-bench Verified (bash only) | — | 72.8% |
| SWE-bench Multilingual | — | 66.7% |
| SciCode | 52.7% | — |
| GSO | — | 27.4% |
| AlgoTune | — | 2.05 |

## Agentic & Tool Use

- Gemini 3.6 Flash: 32.3 (#65)
- GPT-5.2: 40.2 (#24)

| Benchmark | Gemini 3.6 Flash | GPT-5.2 |
|---|---|---|
| Terminal-Bench | — | 64.9% |
| APEX-Agents | 46.9% | — |
| Berkeley Function Calling Leaderboard | — | 55.9% |
| GDPval | — | 49.7% |
| Remote Labor Index | — | 2.5% |
| τ²-bench Airline | — | 83% |
| τ²-bench Banking | — | 32.2% |
| τ²-bench Retail | — | 81.6% |
| τ²-bench Telecom | — | 89.7% |
| DeepResearch Bench | — | 41.1% |
| GDP.pdf | 14% | — |
| LMArena Search | — | 1207 |
| METR Time Horizons | — | 75.3% |
| Vending-Bench 2 | — | 3,591 |

## Reasoning

- Gemini 3.6 Flash: 58.8 (#22)
- GPT-5.2: 50.2 (#35)

| Benchmark | Gemini 3.6 Flash | GPT-5.2 |
|---|---|---|
| ARC-AGI-2 | 60.4% | 52.9% |
| NYT Connections (extended) | 89% | 83.6% |
| ARC-AGI-1 | 91.2% | 86.2% |
| Chess Puzzles | 43% | 49% |
| LMArena Hard Prompts | 1485 | 1445 |
| Mystery Game Puzzles | 30% | 23% |
| DTBench | 95.5% | 90.9% |
| LMCA | 44.9% | 43.9% |
| Epoch Capabilities Index | 154.25 | 153.45 |
| SimpleBench | — | 45.8% |
| Kagi LLM Benchmark | — | 73.3% |
| CritPt | 10.6% | — |
| EnigmaEval | — | 10.4% |
| EBR-Bench | — | 23% |
| ForecastBench | — | 60.1 |

## Math

- Gemini 3.6 Flash: 57.3 (#40)
- GPT-5.2: 60.0 (#38)

| Benchmark | Gemini 3.6 Flash | GPT-5.2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 58.9% | 67.4% |
| FrontierMath Tier 4 | 22% | 31.7% |
| MathArena Final-Answer Competitions | 70.8% | 72% |
| OTIS Mock AIME 2024-2025 | 94.2% | 96.1% |
| ProofBench | 36% | 15% |
| LMArena Math | 1505 | 1440 |
| FrontierMath (Feb 2025 set) | — | 40.7% |
| FrontierMath Tier 4 (v1) | — | 18.8% |

## Knowledge

- Gemini 3.6 Flash: 67.8 (#8)
- GPT-5.2: 59.3 (#32)

| Benchmark | Gemini 3.6 Flash | GPT-5.2 |
|---|---|---|
| GPQA Diamond | 94.1% | 91.4% |
| SimpleQA Verified | 66.2% | 37.1% |
| LMArena Expert | 1488 | 1445 |
| Humanity's Last Exam | — | 27.8% |
| Vectara Hallucination Rate | — | 8.4% |

## Multimodal

- Gemini 3.6 Flash: 38.5 (#64)
- GPT-5.2: 51.3 (#7)

| Benchmark | Gemini 3.6 Flash | GPT-5.2 |
|---|---|---|
| LMArena Vision | 1298 | 1268 |
| Furniture Assembly | 23.3% | 38.3% |
| LMArena Document | 1456 | 1405 |
| VPCT | — | 84% |
| Blueprint-Bench 2 | 31.2% | — |

## Multilingual

- Gemini 3.6 Flash: 56.5 (#19)
- GPT-5.2: 53.4 (#67)

| Benchmark | Gemini 3.6 Flash | GPT-5.2 |
|---|---|---|
| LMArena Non-English | 1469 | 1425 |
| LMArena Chinese | 1531 | 1460 |
| LMArena French | 1504 | 1455 |
| LMArena German | 1478 | 1448 |
| LMArena Japanese | 1476 | 1420 |
| LMArena Korean | 1431 | 1392 |
| LMArena Russian | 1487 | 1440 |
| LMArena Spanish | 1475 | 1433 |

## Instruction Following

- Gemini 3.6 Flash: 77.0 (#33)
- GPT-5.2: 74.7 (#89)

| Benchmark | Gemini 3.6 Flash | GPT-5.2 |
|---|---|---|
| LMArena Instruction Following | 1466 | 1417 |

## Long Context

- Gemini 3.6 Flash: 45.1 (#50)
- GPT-5.2: 44.0 (#78)

| Benchmark | Gemini 3.6 Flash | GPT-5.2 |
|---|---|---|
| LMArena Longer Query | 1474 | 1428 |
| CL-bench | — | 18.2% |

## Writing & Preference

- Gemini 3.6 Flash: 68.2 (#27)
- GPT-5.2: 66.8 (#32)

| Benchmark | Gemini 3.6 Flash | GPT-5.2 |
|---|---|---|
| LMArena Text | 1479 | 1439 |
| LMArena Creative Writing | 1465 | 1401 |
| EQ-Bench Creative Writing | 1604 | 1703 |
| LMArena Multi-Turn | 1481 | 1458 |

## FAQ

### Is Gemini 3.6 Flash better than GPT-5.2?

Gemini 3.6 Flash and GPT-5.2 score almost the same on the Noometry Index (54.1 vs 54.1), so choose on price, context window or the category you care about most.

### Which is cheaper, Gemini 3.6 Flash or GPT-5.2?

Gemini 3.6 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; GPT-5.2 lists at $1.75 and $14.

### Is Gemini 3.6 Flash or GPT-5.2 better for coding?

GPT-5.2 scores higher on coding benchmarks: 51.6 versus 50.0 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-5.2 share?

39 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and GPT-5.2 has 67.