# Gemini 3 Pro vs o3-mini

> Gemini 3 Pro is the stronger model overall, scoring 54.7 to 36.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-pro-vs-o3-mini
- Last updated: 2026-10-10
- Shared benchmarks: 30

## Summary

- They share 30 benchmarks with published results for both. Gemini 3 Pro scores higher in 9 categories and o3-mini in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Pro leads 52.5 to 16.3.
- The biggest single-benchmark swing is SimpleBench: 76.4% for Gemini 3 Pro and 22.8% for o3-mini.

## Snapshot

| | Gemini 3 Pro | o3-mini |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 54.7 | 36.7 |
| Rank | 23 | 205 |
| Context | — | 200K |
| Input $/M | — | $1.10 |
| Output $/M | — | $4.40 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3 Pro: 52.1 (#33)
- o3-mini: 41.4 (#116)

| Benchmark | Gemini 3 Pro | o3-mini |
|---|---|---|
| GSO | 18.6% | 1.3% |
| WeirdML | 69.9% | 43.7% |
| LMArena Coding | 1482 | 1378 |
| SWE-bench Verified | 72.9% | — |
| SWE-bench Verified (bash only) | 74.2% | — |
| Aider Polyglot | — | 60.4% |
| LMArena WebDev | 1439 | — |
| SWE-bench Multilingual | 68.7% | — |
| SciCode | — | 39.8% |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
| ALE-Bench | 1,177 | — |
| AlgoTune | 1.83 | — |

## Agentic & Tool Use

- Gemini 3 Pro: 40.5 (#21)
- o3-mini: 29.3 (#79)

| Benchmark | Gemini 3 Pro | o3-mini |
|---|---|---|
| Terminal-Bench | 69.4% | — |
| Berkeley Function Calling Leaderboard | 72.5% | — |
| GDPval | 40.3% | — |
| Remote Labor Index | 1.3% | — |
| τ²-bench Airline | 80.5% | — |
| τ²-bench Banking | 18% | — |
| τ²-bench Retail | 75.9% | — |
| τ²-bench Telecom | 91% | — |
| Cybench | — | 22.5% |
| DeepResearch Bench | 46.3% | — |
| BALROG | 58.1% | — |
| LMArena Search | 1207 | — |
| METR Time Horizons | 71% | — |
| Vending-Bench 2 | 5,478 | — |

## Reasoning

- Gemini 3 Pro: 52.5 (#28)
- o3-mini: 16.3 (#295)

| Benchmark | Gemini 3 Pro | o3-mini |
|---|---|---|
| ARC-AGI-2 | 31.1% | 3% |
| SimpleBench | 76.4% | 22.8% |
| ARC-AGI-1 | 75% | 34.5% |
| CritPt | 6.9% | 0.3% |
| Chess Puzzles | 31% | 17% |
| LMArena Hard Prompts | 1481 | 1366 |
| Epoch Capabilities Index | 152.96 | 140.35 |
| ForecastBench | 61.2 | 59.6 |
| Kagi LLM Benchmark | 80.1% | — |
| NYT Connections (extended) | 94.4% | — |
| EnigmaEval | 18.2% | — |
| LiveBench Reasoning | — | 89.6% |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 68.8% |
| LiveBench Data Analysis | — | 70.6% |
| LMCA | — | 19% |
| LiveBench | — | 75.9% |

## Math

- Gemini 3 Pro: 48.8 (#50)
- o3-mini: 27.6 (#236)

| Benchmark | Gemini 3 Pro | o3-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 91.4% | 76.9% |
| LMArena Math | 1475 | 1396 |
| FrontierMath (Feb 2025 set) | 37.6% | 12.4% |
| FrontierMath Tier 4 (v1) | 18.8% | 4.2% |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| MathArena Final-Answer Competitions | 67% | — |
| ProofBench | 20% | — |
| Omni-MATH | 55.5% | — |
| LiveBench Math | — | 77.3% |
| MATH Level 5 | — | 96.5% |

## Knowledge

- Gemini 3 Pro: 64.3 (#15)
- o3-mini: 38.3 (#135)

| Benchmark | Gemini 3 Pro | o3-mini |
|---|---|---|
| GPQA Diamond | 92.6% | 77% |
| LMArena Expert | 1475 | 1364 |
| Humanity's Last Exam | 37.5% | — |
| SimpleQA Verified | — | 15.3% |
| MMLU-Pro | 90.3% | — |
| Confabulations | — | 17.9% |
| Vectara Hallucination Rate | 13.6% | — |
| GPQA (HELM) | 80.3% | — |

## Multimodal

- Gemini 3 Pro: 56.9 (#1)
- o3-mini: —

| Benchmark | Gemini 3 Pro | o3-mini |
|---|---|---|
| LMArena Vision | 1305 | — |
| GeoBench | 84% | — |
| VPCT | 91% | — |
| LMArena Document | 1434 | — |

## Multilingual

- Gemini 3 Pro: 57.1 (#14)
- o3-mini: 45.9 (#159)

| Benchmark | Gemini 3 Pro | o3-mini |
|---|---|---|
| LMArena Non-English | 1474 | 1319 |
| LMArena Chinese | 1522 | 1379 |
| LMArena French | 1492 | 1333 |
| LMArena German | 1517 | 1303 |
| LMArena Japanese | 1513 | 1286 |
| LMArena Korean | 1449 | 1314 |
| LMArena Russian | 1493 | 1304 |
| LMArena Spanish | 1468 | 1321 |

## Instruction Following

- Gemini 3 Pro: 76.4 (#42)
- o3-mini: 75.3 (#67)

| Benchmark | Gemini 3 Pro | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1458 | 1338 |
| LiveBench Instruction Following | — | 84.4% |
| IFEval | 87.7% | — |

## Long Context

- Gemini 3 Pro: 44.0 (#75)
- o3-mini: 33.8 (#251)

| Benchmark | Gemini 3 Pro | o3-mini |
|---|---|---|
| LMArena Longer Query | 1472 | 1343 |
| Fiction.LiveBench | — | 50% |
| CL-bench | 15.8% | — |

## Writing & Preference

- Gemini 3 Pro: 66.6 (#34)
- o3-mini: 50.4 (#177)

| Benchmark | Gemini 3 Pro | o3-mini |
|---|---|---|
| LMArena Text | 1479 | 1337 |
| LMArena Creative Writing | 1482 | 1286 |
| LMArena Multi-Turn | 1484 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| EQ-Bench Creative Writing | 1525 | — |
| WildBench | 85.9% | — |
| LiveBench Language | — | 50.7% |

## FAQ

### Is Gemini 3 Pro better than o3-mini?

Gemini 3 Pro is the stronger model overall, scoring 54.7 to 36.7 on the Noometry Index.

### Is Gemini 3 Pro or o3-mini better for coding?

Gemini 3 Pro scores higher on coding benchmarks: 52.1 versus 41.4 in the Noometry coding category.

### How many benchmarks do Gemini 3 Pro and o3-mini share?

30 benchmarks have published results for both models. Gemini 3 Pro has 67 scored results on Noometry and o3-mini has 51.