# Gemini 2.5 Pro vs o4-mini

> Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 41.6 on the Noometry Index. o4-mini costs 1.8× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-2-5-pro-vs-o4-mini
- Last updated: 2026-10-10
- Shared benchmarks: 57

## Summary

- They share 57 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 7 categories and o4-mini in 3 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where Gemini 2.5 Pro leads 59.8 to 45.5.
- The biggest single-benchmark swing is Omni-MATH: 41.6% for Gemini 2.5 Pro and 72% for o4-mini.
- o4-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
- Gemini 2.5 Pro accepts more context: 1.05M tokens versus 200K.

## Snapshot

| | Gemini 2.5 Pro | o4-mini |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 45.0 | 41.6 |
| Rank | 75 | 132 |
| Context | 1.05M | 200K |
| Input $/M | $1.25 | $1.10 |
| Output $/M | $10 | $4.40 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 2.5 Pro: 42.4 (#101)
- o4-mini: 40.9 (#127)

| Benchmark | Gemini 2.5 Pro | o4-mini |
|---|---|---|
| SWE-bench Verified (bash only) | 53.6% | 45% |
| Aider Polyglot | 83.1% | 72% |
| GSO | 3.9% | 3.6% |
| WeirdML | 54% | 52.6% |
| LMArena Coding | 1452 | 1368 |
| CadEval | 64% | 62% |
| ALE-Bench | 785.52 | 826.17 |
| AlgoTune | 1.51 | 1.72 |
| SWE-bench Verified | 57.6% | — |
| LMArena WebDev | 1227 | — |
| SciCode | 42.8% | — |
| LiveBench Coding | 85.9% | — |

## Agentic & Tool Use

- Gemini 2.5 Pro: 29.2 (#88)
- o4-mini: 32.6 (#61)

| Benchmark | Gemini 2.5 Pro | o4-mini |
|---|---|---|
| GDPval | 23.3% | 25.3% |
| METR Time Horizons | 55.4% | 63.9% |
| Terminal-Bench | 32.6% | — |
| Berkeley Function Calling Leaderboard | — | 53.2% |
| Remote Labor Index | 0.8% | — |
| TheAgentCompany | 30.3% | — |
| τ²-bench Banking | 13.7% | — |
| DeepResearch Bench | 42.8% | — |
| BALROG | 43.3% | — |
| LMArena Search | 1142 | — |
| Vending-Bench 2 | 573.64 | — |

## Reasoning

- Gemini 2.5 Pro: 28.8 (#99)
- o4-mini: 24.6 (#162)

| Benchmark | Gemini 2.5 Pro | o4-mini |
|---|---|---|
| ARC-AGI-2 | 4.9% | 6.1% |
| SimpleBench | 62.4% | 38.7% |
| Kagi LLM Benchmark | 70.3% | 67.6% |
| ARC-AGI-1 | 41% | 58.7% |
| CritPt | 2% | 0.6% |
| Chess Puzzles | 20% | 26% |
| EnigmaEval | 5.6% | 9.2% |
| LMArena Hard Prompts | 1455 | 1351 |
| DTBench | 82.4% | 77.6% |
| LMCA | 34.8% | 26.5% |
| Epoch Capabilities Index | 145.32 | 145.64 |
| ForecastBench | 61.3 | 61.8 |
| LiveBench Reasoning | 89.8% | — |
| Mystery Game Puzzles | — | 5% |
| LiveBench Data Analysis | 79.9% | — |
| LiveBench | 82.3% | — |

## Math

- Gemini 2.5 Pro: 32.5 (#213)
- o4-mini: 40.8 (#89)

| Benchmark | Gemini 2.5 Pro | o4-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 24.6% | 36.1% |
| FrontierMath Tier 4 | 0% | 4.9% |
| OTIS Mock AIME 2024-2025 | 84.7% | 81.7% |
| Omni-MATH | 41.6% | 72% |
| LMArena Math | 1450 | 1389 |
| MATH Level 5 | 95.9% | 97.8% |
| FrontierMath (Feb 2025 set) | 14.1% | 24.8% |
| FrontierMath Tier 4 (v1) | 4.2% | 6.3% |
| LiveBench Math | 90.2% | — |

## Knowledge

- Gemini 2.5 Pro: 56.0 (#46)
- o4-mini: 43.6 (#91)

| Benchmark | Gemini 2.5 Pro | o4-mini |
|---|---|---|
| GPQA Diamond | 85.3% | 79.6% |
| Humanity's Last Exam | 21.6% | 18.1% |
| MMLU-Pro | 86.3% | 82% |
| Confabulations | 10.6% | 15.8% |
| Vectara Hallucination Rate | 7% | 18.6% |
| GPQA (HELM) | 74.9% | 73.5% |
| LMArena Expert | 1452 | 1343 |
| SimpleQA Verified | — | 19.6% |

## Multimodal

- Gemini 2.5 Pro: 45.2 (#18)
- o4-mini: 40.2 (#49)

| Benchmark | Gemini 2.5 Pro | o4-mini |
|---|---|---|
| LMArena Vision | 1263 | 1194 |
| GeoBench | 86% | 64% |
| VPCT | 48% | 57.5% |
| LMArena Document | 1421 | — |
| SpatialViz-Bench | 44.7% | — |

## Multilingual

- Gemini 2.5 Pro: 55.3 (#31)
- o4-mini: 47.0 (#154)

| Benchmark | Gemini 2.5 Pro | o4-mini |
|---|---|---|
| LMArena Non-English | 1451 | 1337 |
| LMArena Chinese | 1507 | 1354 |
| LMArena French | 1472 | 1364 |
| LMArena German | 1487 | 1336 |
| LMArena Japanese | 1461 | 1308 |
| LMArena Korean | 1434 | 1312 |
| LMArena Russian | 1461 | 1334 |
| LMArena Spanish | 1473 | 1347 |

## Instruction Following

- Gemini 2.5 Pro: 75.0 (#75)
- o4-mini: 75.2 (#68)

| Benchmark | Gemini 2.5 Pro | o4-mini |
|---|---|---|
| IFEval | 84% | 92.8% |
| LMArena Instruction Following | 1437 | 1321 |
| LiveBench Instruction Following | 80.6% | — |

## Long Context

- Gemini 2.5 Pro: 59.8 (#5)
- o4-mini: 45.5 (#33)

| Benchmark | Gemini 2.5 Pro | o4-mini |
|---|---|---|
| Fiction.LiveBench | 91.7% | 77.8% |
| LMArena Longer Query | 1449 | 1315 |

## Writing & Preference

- Gemini 2.5 Pro: 63.7 (#62)
- o4-mini: 54.0 (#152)

| Benchmark | Gemini 2.5 Pro | o4-mini |
|---|---|---|
| LMArena Text | 1458 | 1353 |
| LMArena Creative Writing | 1454 | 1294 |
| Short-Story Creative Writing | 83.8% | 75% |
| WildBench | 85.7% | 85.4% |
| LMArena Multi-Turn | 1453 | 1350 |
| EQ-Bench Creative Writing | 1421 | — |
| LiveBench Language | 67.8% | — |

## FAQ

### Is Gemini 2.5 Pro better than o4-mini?

Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 41.6 on the Noometry Index. o4-mini costs 1.8× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.

### Which is cheaper, Gemini 2.5 Pro or o4-mini?

o4-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.

### Is Gemini 2.5 Pro or o4-mini better for coding?

Gemini 2.5 Pro scores higher on coding benchmarks: 42.4 versus 40.9 in the Noometry coding category.

### Which has the bigger context window?

Gemini 2.5 Pro does, with 1.05M tokens against 200K.

### How many benchmarks do Gemini 2.5 Pro and o4-mini share?

57 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and o4-mini has 60.