# Gemini 2.5 Flash vs GPT-4o mini

> Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 25.5 on the Noometry Index. GPT-4o mini costs 3.2× less per token, which makes it the better buy when Gemini 2.5 Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-2-5-flash-vs-gpt-4o-mini
- Last updated: 2026-10-11
- Shared benchmarks: 38

## Summary

- They share 38 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 10 categories and GPT-4o mini in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.5 Flash leads 39.9 to 10.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 73.1% for Gemini 2.5 Flash and 6.9% for GPT-4o mini.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.30 / $2.50 for Gemini 2.5 Flash.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 128K.

## Snapshot

| | Gemini 2.5 Flash | GPT-4o mini |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 39.3 | 25.5 |
| Rank | 170 | 343 |
| Context | 1.05M | 128K |
| Input $/M | $0.30 | $0.15 |
| Output $/M | $2.50 | $0.60 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 2.5 Flash: 35.8 (#220)
- GPT-4o mini: 22.0 (#335)

| Benchmark | Gemini 2.5 Flash | GPT-4o mini |
|---|---|---|
| Aider Polyglot | 55.1% | 3.6% |
| WeirdML | 41.9% | 11.8% |
| LMArena Coding | 1424 | 1290 |
| SWE-bench Verified (bash only) | 28.7% | — |
| BigCodeBench Instruct | — | 46.1% |
| LiveBench Coding | — | 43.1% |
| BigCodeBench Complete | — | 57.4% |
| ALE-Bench | 661.88 | — |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 72.2% |

## Agentic & Tool Use

- Gemini 2.5 Flash: 30.8 (#74)
- GPT-4o mini: 27.5 (#101)

| Benchmark | Gemini 2.5 Flash | GPT-4o mini |
|---|---|---|
| BALROG | 33.5% | 17.4% |
| Terminal-Bench | 17.1% | — |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| Vending-Bench 2 | 548.84 | — |

## Reasoning

- Gemini 2.5 Flash: 18.1 (#286)
- GPT-4o mini: 8.7 (#347)

| Benchmark | Gemini 2.5 Flash | GPT-4o mini |
|---|---|---|
| ARC-AGI-2 | 2.5% | 0% |
| SimpleBench | 41.2% | 10.7% |
| Kagi LLM Benchmark | 56.8% | 28.8% |
| LMArena Hard Prompts | 1422 | 1267 |
| DTBench | 76.5% | 54.4% |
| LMCA | 27.5% | 10.4% |
| Epoch Capabilities Index | 143.03 | 126.56 |
| ARC-AGI-1 | 33.3% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | — | 0% |
| EnigmaEval | 2.7% | — |
| LiveBench Reasoning | — | 32.8% |
| Mystery Game Puzzles | — | 12% |
| LiveBench Data Analysis | — | 50% |
| ForecastBench | 60.6 | — |
| LiveBench | — | 41.3% |
| PIQA | — | 88.7% |

## Math

- Gemini 2.5 Flash: 39.9 (#98)
- GPT-4o mini: 10.4 (#314)

| Benchmark | Gemini 2.5 Flash | GPT-4o mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 6.9% |
| Omni-MATH | 38.5% | 28% |
| LMArena Math | 1415 | 1267 |
| FrontierMath (Tiers 1-3) | — | 0.7% |
| LiveBench Math | — | 36.3% |
| MATH Level 5 | — | 52.6% |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
| GSM8K | — | 91.3% |

## Knowledge

- Gemini 2.5 Flash: 36.4 (#168)
- GPT-4o mini: 17.7 (#284)

| Benchmark | Gemini 2.5 Flash | GPT-4o mini |
|---|---|---|
| MMLU-Pro | 63.9% | 60.3% |
| Confabulations | 16.8% | 37.2% |
| GPQA (HELM) | 39% | 36.8% |
| LMArena Expert | 1426 | 1235 |
| GPQA Diamond | — | 37.7% |
| Humanity's Last Exam | 12.1% | — |
| SimpleQA Verified | — | 8.3% |
| Vectara Hallucination Rate | 7.8% | — |
| BoolQ | — | 88.7% |
| MMLU | — | 81.8% |

## Multimodal

- Gemini 2.5 Flash: 41.8 (#32)
- GPT-4o mini: 25.9 (#122)

| Benchmark | Gemini 2.5 Flash | GPT-4o mini |
|---|---|---|
| LMArena Vision | 1253 | 1066 |
| GeoBench | 76% | 64% |
| VPCT | 46.2% | 34% |
| Video-MME | — | 64.8% |
| SpatialViz-Bench | 36.9% | — |

## Multilingual

- Gemini 2.5 Flash: 52.3 (#88)
- GPT-4o mini: 42.0 (#199)

| Benchmark | Gemini 2.5 Flash | GPT-4o mini |
|---|---|---|
| LMArena Non-English | 1409 | 1266 |
| LMArena Chinese | 1450 | 1265 |
| LMArena French | 1433 | 1297 |
| LMArena German | 1418 | 1272 |
| LMArena Japanese | 1405 | 1216 |
| LMArena Korean | 1385 | 1195 |
| LMArena Russian | 1415 | 1275 |
| LMArena Spanish | 1421 | 1276 |

## Instruction Following

- Gemini 2.5 Flash: 75.7 (#54)
- GPT-4o mini: 61.9 (#239)

| Benchmark | Gemini 2.5 Flash | GPT-4o mini |
|---|---|---|
| IFEval | 89.8% | 78.2% |
| LMArena Instruction Following | 1405 | 1258 |
| LiveBench Instruction Following | — | 56.8% |

## Long Context

- Gemini 2.5 Flash: 47.5 (#17)
- GPT-4o mini: 39.1 (#186)

| Benchmark | Gemini 2.5 Flash | GPT-4o mini |
|---|---|---|
| LMArena Longer Query | 1419 | 1289 |
| Fiction.LiveBench | 77.8% | — |

## Writing & Preference

- Gemini 2.5 Flash: 53.8 (#157)
- GPT-4o mini: 39.5 (#248)

| Benchmark | Gemini 2.5 Flash | GPT-4o mini |
|---|---|---|
| LMArena Text | 1417 | 1286 |
| LMArena Creative Writing | 1400 | 1268 |
| Short-Story Creative Writing | 76.5% | 67.2% |
| EQ-Bench Creative Writing | 1137 | 873 |
| WildBench | 81.7% | 79.1% |
| LMArena Multi-Turn | 1408 | 1285 |
| LiveBench Language | — | 28.6% |

## FAQ

### Is Gemini 2.5 Flash better than GPT-4o mini?

Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 25.5 on the Noometry Index. GPT-4o mini costs 3.2× less per token, which makes it the better buy when Gemini 2.5 Flash's lead doesn't matter for your workload.

### Which is cheaper, Gemini 2.5 Flash or GPT-4o mini?

GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Gemini 2.5 Flash lists at $0.30 and $2.50.

### Is Gemini 2.5 Flash or GPT-4o mini better for coding?

Gemini 2.5 Flash scores higher on coding benchmarks: 35.8 versus 22.0 in the Noometry coding category.

### Which has the bigger context window?

Gemini 2.5 Flash does, with 1.05M tokens against 128K.

### How many benchmarks do Gemini 2.5 Flash and GPT-4o mini share?

38 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and GPT-4o mini has 60.