# Gemini 1.5 Flash (May 2024) vs GPT-4o mini

> Gemini 1.5 Flash (May 2024) is the stronger model overall, scoring 32.9 to 25.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-1-5-flash-vs-gpt-4o-mini
- Last updated: 2026-10-10
- Shared benchmarks: 40

## Summary

- They share 40 benchmarks with published results for both. Gemini 1.5 Flash (May 2024) scores higher in 8 categories and GPT-4o mini in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Gemini 1.5 Flash (May 2024) leads 33.9 to 21.6.
- The biggest single-benchmark swing is WeirdML: 24.9% for Gemini 1.5 Flash (May 2024) and 11.8% for GPT-4o mini.

## Snapshot

| | Gemini 1.5 Flash (May 2024) | GPT-4o mini |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 32.9 | 25.4 |
| Rank | 240 | 337 |
| Context | — | 128K |
| Input $/M | — | $0.15 |
| Output $/M | — | $0.60 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 1.5 Flash (May 2024): 33.9 (#233)
- GPT-4o mini: 21.6 (#330)

| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-4o mini |
|---|---|---|
| WeirdML | 24.9% | 11.8% |
| BigCodeBench Instruct | 43.5% | 46.1% |
| LMArena Coding | 1262 | 1290 |
| BigCodeBench Complete | 55.1% | 57.4% |
| HumanEval+ | 75.6% | 83.5% |
| MBPP+ | 67.5% | 72.2% |
| Aider Polyglot | — | 3.6% |
| LiveBench Coding | — | 43.1% |

## Agentic & Tool Use

- Gemini 1.5 Flash (May 2024): 26.3 (#97)
- GPT-4o mini: 27.2 (#95)

| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-4o mini |
|---|---|---|
| BALROG | 14.6% | 17.4% |

## Reasoning

- Gemini 1.5 Flash (May 2024): 20.8 (#212)
- GPT-4o mini: 8.7 (#343)

| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-4o mini |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1267 |
| DTBench | 53.8% | 54.4% |
| Epoch Capabilities Index | 129.37 | 126.56 |
| PIQA | 87.5% | 88.7% |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 10.7% |
| Kagi LLM Benchmark | — | 28.8% |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 32.8% |
| Mystery Game Puzzles | — | 12% |
| LiveBench Data Analysis | — | 50% |
| LMCA | — | 10.4% |
| ForecastBench | 53.9 | — |
| LiveBench | — | 41.3% |

## Math

- Gemini 1.5 Flash (May 2024): 20.8 (#274)
- GPT-4o mini: 9.9 (#307)

| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-4o mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.3% | 6.9% |
| Omni-MATH | 30.4% | 28% |
| LMArena Math | 1269 | 1267 |
| MATH Level 5 | 61.9% | 52.6% |
| GSM8K | 82.4% | 91.3% |
| FrontierMath (Tiers 1-3) | — | 0.7% |
| LiveBench Math | — | 36.3% |
| FrontierMath (Feb 2025 set) | 0% | — |

## Knowledge

- Gemini 1.5 Flash (May 2024): 26.2 (#253)
- GPT-4o mini: 17.7 (#279)

| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-4o mini |
|---|---|---|
| GPQA Diamond | 47.3% | 37.7% |
| MMLU-Pro | 67.8% | 60.3% |
| GPQA (HELM) | 43.7% | 36.8% |
| LMArena Expert | 1233 | 1235 |
| BoolQ | 85.8% | 88.7% |
| MMLU | 77.9% | 81.8% |
| SimpleQA Verified | — | 8.3% |
| Confabulations | — | 37.2% |

## Multimodal

- Gemini 1.5 Flash (May 2024): 35.3 (#76)
- GPT-4o mini: 25.3 (#117)

| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-4o mini |
|---|---|---|
| LMArena Vision | 1141 | 1066 |
| Video-MME | 70.3% | 64.8% |
| GeoBench | 76% | 64% |
| VPCT | — | 34% |

## Multilingual

- Gemini 1.5 Flash (May 2024): 43.1 (#184)
- GPT-4o mini: 42.2 (#194)

| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-4o mini |
|---|---|---|
| LMArena Non-English | 1278 | 1266 |
| LMArena Chinese | 1295 | 1264 |
| LMArena French | 1257 | 1296 |
| LMArena German | 1262 | 1272 |
| LMArena Japanese | 1252 | 1216 |
| LMArena Korean | 1220 | 1195 |
| LMArena Russian | 1288 | 1275 |
| LMArena Spanish | 1242 | 1276 |

## Instruction Following

- Gemini 1.5 Flash (May 2024): 67.0 (#199)
- GPT-4o mini: 62.1 (#234)

| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-4o mini |
|---|---|---|
| IFEval | 83.1% | 78.2% |
| LMArena Instruction Following | 1258 | 1259 |
| LiveBench Instruction Following | — | 56.8% |

## Long Context

- Gemini 1.5 Flash (May 2024): 39.0 (#182)
- GPT-4o mini: 39.1 (#181)

| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-4o mini |
|---|---|---|
| LMArena Longer Query | 1284 | 1289 |

## Writing & Preference

- Gemini 1.5 Flash (May 2024): 48.9 (#190)
- GPT-4o mini: 39.7 (#243)

| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-4o mini |
|---|---|---|
| LMArena Text | 1287 | 1286 |
| LMArena Creative Writing | 1285 | 1268 |
| WildBench | 79.2% | 79.1% |
| LMArena Multi-Turn | 1253 | 1285 |
| Short-Story Creative Writing | — | 67.2% |
| EQ-Bench Creative Writing | — | 873 |
| LiveBench Language | — | 28.6% |

## FAQ

### Is Gemini 1.5 Flash (May 2024) better than GPT-4o mini?

Gemini 1.5 Flash (May 2024) is the stronger model overall, scoring 32.9 to 25.4 on the Noometry Index.

### Is Gemini 1.5 Flash (May 2024) or GPT-4o mini better for coding?

Gemini 1.5 Flash (May 2024) scores higher on coding benchmarks: 33.9 versus 21.6 in the Noometry coding category.

### How many benchmarks do Gemini 1.5 Flash (May 2024) and GPT-4o mini share?

40 benchmarks have published results for both models. Gemini 1.5 Flash (May 2024) has 42 scored results on Noometry and GPT-4o mini has 60.