# Gemini 3 Flash Preview vs GPT-3.5-turbo

> Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 23.2 on the Noometry Index. GPT-3.5-turbo costs 1.5× less per token, which makes it the better buy when Gemini 3 Flash Preview's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-3-flash-preview-vs-gpt-3-5-turbo
- Last updated: 2026-10-10
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 8 categories and GPT-3.5-turbo in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3 Flash Preview leads 58.8 to 10.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Gemini 3 Flash Preview and 2.2% for GPT-3.5-turbo.
- GPT-3.5-turbo is cheaper at $0.50 / $1.50 per million input/output tokens, against $0.50 / $3 for Gemini 3 Flash Preview.
- Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 16K.

## Snapshot

| | Gemini 3 Flash Preview | GPT-3.5-turbo |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 52.3 | 23.2 |
| Rank | 40 | 350 |
| Context | 1.05M | 16K |
| Input $/M | $0.50 | $0.50 |
| Output $/M | $3 | $1.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3 Flash Preview: 50.9 (#42)
- GPT-3.5-turbo: 23.9 (#331)

| Benchmark | Gemini 3 Flash Preview | GPT-3.5-turbo |
|---|---|---|
| WeirdML | 61.6% | 3.5% |
| LMArena Coding | 1460 | 1136 |
| SWE-bench Verified | 75.4% | — |
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1439 | — |
| SWE-bench Multilingual | 72.7% | — |
| GSO | 9.8% | — |
| BigCodeBench Instruct | — | 39.1% |
| BigCodeBench Complete | — | 50.6% |
| ALE-Bench | 1,367 | — |
| HumanEval+ | — | 70.7% |
| MBPP+ | — | 69.7% |

## Agentic & Tool Use

- Gemini 3 Flash Preview: 38.7 (#29)
- GPT-3.5-turbo: —

| Benchmark | Gemini 3 Flash Preview | GPT-3.5-turbo |
|---|---|---|
| Terminal-Bench | 64.3% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 27.3% | — |
| τ²-bench Retail | 76.8% | — |
| τ²-bench Telecom | 91.2% | — |
| DeepResearch Bench | 49.8% | — |
| BALROG | 48.1% | — |
| GDP.pdf | 10% | — |
| LMArena Search | 1198 | — |
| METR Time Horizons | — | 21.5% |
| Vending-Bench 2 | 3,635 | — |

## Reasoning

- Gemini 3 Flash Preview: 49.2 (#37)
- GPT-3.5-turbo: 13.8 (#332)

| Benchmark | Gemini 3 Flash Preview | GPT-3.5-turbo |
|---|---|---|
| Chess Puzzles | 40% | 0% |
| LMArena Hard Prompts | 1465 | 1108 |
| Mystery Game Puzzles | 26% | 3% |
| DTBench | 89.1% | 48.5% |
| LMCA | 43.1% | 9.7% |
| Epoch Capabilities Index | 151.8 | 118.55 |
| ForecastBench | 58.5 | 50.4 |
| ARC-AGI-2 | 33.6% | — |
| SimpleBench | 61.1% | — |
| NYT Connections (extended) | 83.1% | — |
| ARC-AGI-1 | 84.7% | — |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 61.6% |
| CommonsenseQA 2.0 | — | 57% |
| WinoGrande | — | 81.6% |

## Math

- Gemini 3 Flash Preview: 51.7 (#55)
- GPT-3.5-turbo: 6.3 (#327)

| Benchmark | Gemini 3 Flash Preview | GPT-3.5-turbo |
|---|---|---|
| FrontierMath (Tiers 1-3) | 51.2% | 0% |
| OTIS Mock AIME 2024-2025 | 95.6% | 2.2% |
| LMArena Math | 1473 | 1142 |
| FrontierMath Tier 4 | 17.1% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| ProofBench | 15% | — |
| MATH Level 5 | — | 15.9% |
| FrontierMath (Feb 2025 set) | 35.6% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
| GSM8K | — | 57.8% |

## Knowledge

- Gemini 3 Flash Preview: 58.8 (#33)
- GPT-3.5-turbo: 10.0 (#303)

| Benchmark | Gemini 3 Flash Preview | GPT-3.5-turbo |
|---|---|---|
| GPQA Diamond | 89.4% | 28% |
| LMArena Expert | 1462 | 1070 |
| SimpleQA Verified | 66.8% | — |
| Vectara Hallucination Rate | 13.5% | — |
| ARC (AI2) Challenge | — | 87.4% |
| BoolQ | — | 87% |
| MMLU | — | 71.4% |
| OpenBookQA | — | 86% |
| TriviaQA | — | 85.8% |

## Multimodal

- Gemini 3 Flash Preview: 45.5 (#16)
- GPT-3.5-turbo: —

| Benchmark | Gemini 3 Flash Preview | GPT-3.5-turbo |
|---|---|---|
| LMArena Vision | 1285 | — |
| GeoBench | 88% | — |
| VPCT | 72.6% | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1413 | — |

## Multilingual

- Gemini 3 Flash Preview: 55.7 (#27)
- GPT-3.5-turbo: 31.5 (#258)

| Benchmark | Gemini 3 Flash Preview | GPT-3.5-turbo |
|---|---|---|
| LMArena Non-English | 1458 | 1108 |
| LMArena Chinese | 1511 | 1075 |
| LMArena French | 1477 | 1118 |
| LMArena German | 1497 | 1090 |
| LMArena Japanese | 1489 | 1043 |
| LMArena Korean | 1443 | 1019 |
| LMArena Russian | 1480 | 1123 |
| LMArena Spanish | 1469 | 1121 |

## Instruction Following

- Gemini 3 Flash Preview: 75.7 (#56)
- GPT-3.5-turbo: 57.9 (#262)

| Benchmark | Gemini 3 Flash Preview | GPT-3.5-turbo |
|---|---|---|
| LMArena Instruction Following | 1437 | 1119 |

## Long Context

- Gemini 3 Flash Preview: 44.4 (#67)
- GPT-3.5-turbo: 34.0 (#254)

| Benchmark | Gemini 3 Flash Preview | GPT-3.5-turbo |
|---|---|---|
| LMArena Longer Query | 1452 | 1121 |

## Writing & Preference

- Gemini 3 Flash Preview: 65.5 (#45)
- GPT-3.5-turbo: 25.3 (#305)

| Benchmark | Gemini 3 Flash Preview | GPT-3.5-turbo |
|---|---|---|
| LMArena Text | 1466 | 1125 |
| LMArena Creative Writing | 1457 | 1092 |
| LMArena Multi-Turn | 1471 | 1117 |
| EQ-Bench Creative Writing | — | 451 |

## FAQ

### Is Gemini 3 Flash Preview better than GPT-3.5-turbo?

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 23.2 on the Noometry Index. GPT-3.5-turbo costs 1.5× less per token, which makes it the better buy when Gemini 3 Flash Preview's lead doesn't matter for your workload.

### Which is cheaper, Gemini 3 Flash Preview or GPT-3.5-turbo?

GPT-3.5-turbo is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; Gemini 3 Flash Preview lists at $0.50 and $3.

### Is Gemini 3 Flash Preview or GPT-3.5-turbo better for coding?

Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 23.9 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3 Flash Preview does, with 1.05M tokens against 16K.

### How many benchmarks do Gemini 3 Flash Preview and GPT-3.5-turbo share?

27 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and GPT-3.5-turbo has 44.