# Gemini 3.1 Pro Preview vs GPT-4o mini

> Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 25.4 on the Noometry Index. GPT-4o mini costs 17× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-3-1-pro-preview-vs-gpt-4o-mini
- Last updated: 2026-10-10
- Shared benchmarks: 32

## Summary

- They share 32 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 10 categories and GPT-4o mini in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 8.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Gemini 3.1 Pro Preview and 6.9% for GPT-4o mini.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
- Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 128K.

## Snapshot

| | Gemini 3.1 Pro Preview | GPT-4o mini |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 56.7 | 25.4 |
| Rank | 20 | 337 |
| Context | 1.05M | 128K |
| Input $/M | $2 | $0.15 |
| Output $/M | $12 | $0.60 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3.1 Pro Preview: 42.7 (#88)
- GPT-4o mini: 21.6 (#330)

| Benchmark | Gemini 3.1 Pro Preview | GPT-4o mini |
|---|---|---|
| WeirdML | 72.1% | 11.8% |
| LMArena Coding | 1483 | 1290 |
| SWE-bench Verified | 75.6% | — |
| DeepSWE | 11.7% | — |
| Aider Polyglot | — | 3.6% |
| LMArena WebDev | 1446 | — |
| SciCode | 58.9% | — |
| GSO | 22.6% | — |
| BigCodeBench Instruct | — | 46.1% |
| LiveBench Coding | — | 43.1% |
| MirrorCode | 8.9% | — |
| BigCodeBench Complete | — | 57.4% |
| ALE-Bench | 1,161 | — |
| AlgoTune | 2.02 | — |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 72.2% |

## Agentic & Tool Use

- Gemini 3.1 Pro Preview: 37.7 (#33)
- GPT-4o mini: 27.2 (#95)

| Benchmark | Gemini 3.1 Pro Preview | GPT-4o mini |
|---|---|---|
| BALROG | 57% | 17.4% |
| Terminal-Bench | 80.2% | — |
| APEX-Agents | 35.3% | — |
| τ²-bench Banking | 26% | — |
| DeepResearch Bench | 47.8% | — |
| PostTrainBench | 22% | — |
| ExploitBench | 26.1% | — |
| GBAEval | 0.8% | — |
| GDP.pdf | 17% | — |
| LMArena Search | 1211 | — |
| METR Time Horizons | 77% | — |
| Vending-Bench 2 | 3,774 | — |

## Reasoning

- Gemini 3.1 Pro Preview: 71.7 (#9)
- GPT-4o mini: 8.7 (#343)

| Benchmark | Gemini 3.1 Pro Preview | GPT-4o mini |
|---|---|---|
| ARC-AGI-2 | 77.1% | 0% |
| SimpleBench | 79.6% | 10.7% |
| Chess Puzzles | 55% | 0% |
| LMArena Hard Prompts | 1484 | 1267 |
| Mystery Game Puzzles | 34% | 12% |
| DTBench | 97.1% | 54.4% |
| LMCA | 53.8% | 10.4% |
| Epoch Capabilities Index | 154.92 | 126.56 |
| Kagi LLM Benchmark | — | 28.8% |
| NYT Connections (extended) | 97.4% | — |
| ARC-AGI-1 | 98% | — |
| CritPt | 17.7% | — |
| EnigmaEval | 36.8% | — |
| Thematic Generalization | 79.4% | — |
| EBR-Bench | 14.3% | — |
| LiveBench Reasoning | — | 32.8% |
| LiveBench Data Analysis | — | 50% |
| ForecastBench | 59 | — |
| LiveBench | — | 41.3% |
| PIQA | — | 88.7% |

## Math

- Gemini 3.1 Pro Preview: 61.8 (#28)
- GPT-4o mini: 9.9 (#307)

| Benchmark | Gemini 3.1 Pro Preview | GPT-4o mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 59.6% | 0.7% |
| OTIS Mock AIME 2024-2025 | 95.6% | 6.9% |
| LMArena Math | 1485 | 1267 |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 86.5% | — |
| ProofBench | 26% | — |
| Omni-MATH | — | 28% |
| LiveBench Math | — | 36.3% |
| MATH Level 5 | — | 52.6% |
| FrontierMath (Feb 2025 set) | 36.9% | — |
| FrontierMath Tier 4 (v1) | 16.7% | — |
| GSM8K | — | 91.3% |

## Knowledge

- Gemini 3.1 Pro Preview: 71.8 (#3)
- GPT-4o mini: 17.7 (#279)

| Benchmark | Gemini 3.1 Pro Preview | GPT-4o mini |
|---|---|---|
| GPQA Diamond | 94.4% | 37.7% |
| SimpleQA Verified | 73.5% | 8.3% |
| LMArena Expert | 1484 | 1235 |
| Humanity's Last Exam | 46.4% | — |
| MMLU-Pro | — | 60.3% |
| Confabulations | — | 37.2% |
| Vectara Hallucination Rate | 10.4% | — |
| GPQA (HELM) | — | 36.8% |
| BoolQ | — | 88.7% |
| MMLU | — | 81.8% |

## Multimodal

- Gemini 3.1 Pro Preview: 38.1 (#60)
- GPT-4o mini: 25.3 (#117)

| Benchmark | Gemini 3.1 Pro Preview | GPT-4o mini |
|---|---|---|
| LMArena Vision | 1296 | 1066 |
| Video-MME | — | 64.8% |
| GeoBench | — | 64% |
| VPCT | — | 34% |
| Blueprint-Bench 2 | 26.5% | — |
| Furniture Assembly | 26.7% | — |
| LMArena Document | 1444 | — |

## Multilingual

- Gemini 3.1 Pro Preview: 57.1 (#11)
- GPT-4o mini: 42.2 (#194)

| Benchmark | Gemini 3.1 Pro Preview | GPT-4o mini |
|---|---|---|
| LMArena Non-English | 1475 | 1266 |
| LMArena Chinese | 1528 | 1264 |
| LMArena French | 1488 | 1296 |
| LMArena German | 1491 | 1272 |
| LMArena Japanese | 1494 | 1216 |
| LMArena Korean | 1458 | 1195 |
| LMArena Russian | 1496 | 1275 |
| LMArena Spanish | 1480 | 1276 |

## Instruction Following

- Gemini 3.1 Pro Preview: 77.1 (#31)
- GPT-4o mini: 62.1 (#234)

| Benchmark | Gemini 3.1 Pro Preview | GPT-4o mini |
|---|---|---|
| LMArena Instruction Following | 1465 | 1259 |
| LiveBench Instruction Following | — | 56.8% |
| IFEval | — | 78.2% |

## Long Context

- Gemini 3.1 Pro Preview: 47.3 (#17)
- GPT-4o mini: 39.1 (#181)

| Benchmark | Gemini 3.1 Pro Preview | GPT-4o mini |
|---|---|---|
| LMArena Longer Query | 1482 | 1289 |
| CL-bench | 20.8% | — |
| CL-bench Life | 16.9% | — |

## Writing & Preference

- Gemini 3.1 Pro Preview: 66.3 (#36)
- GPT-4o mini: 39.7 (#243)

| Benchmark | Gemini 3.1 Pro Preview | GPT-4o mini |
|---|---|---|
| LMArena Text | 1480 | 1286 |
| LMArena Creative Writing | 1482 | 1268 |
| EQ-Bench Creative Writing | 1491 | 873 |
| LMArena Multi-Turn | 1486 | 1285 |
| Short-Story Creative Writing | — | 67.2% |
| WildBench | — | 79.1% |
| EQ-Bench 4 | 1142 | — |
| LiveBench Language | — | 28.6% |

## FAQ

### Is Gemini 3.1 Pro Preview better than GPT-4o mini?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 25.4 on the Noometry Index. GPT-4o mini costs 17× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

### Which is cheaper, Gemini 3.1 Pro Preview 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 3.1 Pro Preview lists at $2 and $12.

### Is Gemini 3.1 Pro Preview or GPT-4o mini better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.7 versus 21.6 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 128K.

### How many benchmarks do Gemini 3.1 Pro Preview and GPT-4o mini share?

32 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and GPT-4o mini has 60.