# Gemini 3.1 Pro Preview vs o1

> Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 40.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-1-pro-preview-vs-o1
- Last updated: 2026-10-10
- Shared benchmarks: 33

## Summary

- They share 33 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 8 categories and o1 in 2 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 27.9.
- The biggest single-benchmark swing is ARC-AGI-1: 98% for Gemini 3.1 Pro Preview and 30.7% for o1.
- Gemini 3.1 Pro Preview is cheaper at $2 / $12 per million input/output tokens, against $15 / $60 for o1.
- Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 200K.

## Snapshot

| | Gemini 3.1 Pro Preview | o1 |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 56.7 | 40.9 |
| Rank | 23 | 143 |
| Context | 1.05M | 200K |
| Input $/M | $2 | $15 |
| Output $/M | $12 | $60 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3.1 Pro Preview: 42.5 (#99)
- o1: 46.1 (#70)

| Benchmark | Gemini 3.1 Pro Preview | o1 |
|---|---|---|
| WeirdML | 72.1% | 47.6% |
| LMArena Coding | 1484 | 1367 |
| SWE-bench Verified | 75.6% | — |
| DeepSWE | 11.7% | — |
| Aider Polyglot | — | 61.7% |
| LMArena WebDev | 1447 | — |
| SciCode | 58.9% | — |
| GSO | 22.6% | — |
| LiveBench Coding | — | 69.7% |
| MirrorCode | 8.9% | — |
| CadEval | — | 56% |
| ALE-Bench | 1,161 | — |
| AlgoTune | 2.02 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |

## Agentic & Tool Use

- Gemini 3.1 Pro Preview: 37.7 (#34)
- o1: 24.6 (#117)

| Benchmark | Gemini 3.1 Pro Preview | o1 |
|---|---|---|
| METR Time Horizons | 77% | 51.1% |
| Terminal-Bench | 80.2% | — |
| APEX-Agents | 35.3% | — |
| τ²-bench Banking | 26% | — |
| Cybench | — | 10% |
| DeepResearch Bench | 47.8% | — |
| PostTrainBench | 22% | — |
| BALROG | 57% | — |
| ExploitBench | 26.1% | — |
| GBAEval | 0.8% | — |
| GDP.pdf | 17% | — |
| LMArena Search | 1211 | — |
| Vending-Bench 2 | 3,774 | — |

## Reasoning

- Gemini 3.1 Pro Preview: 71.7 (#12)
- o1: 27.9 (#111)

| Benchmark | Gemini 3.1 Pro Preview | o1 |
|---|---|---|
| SimpleBench | 79.6% | 41.7% |
| ARC-AGI-1 | 98% | 30.7% |
| Chess Puzzles | 55% | 15% |
| EnigmaEval | 36.8% | 5.7% |
| LMArena Hard Prompts | 1485 | 1371 |
| DTBench | 97.1% | 74.7% |
| LMCA | 53.8% | 22.3% |
| Epoch Capabilities Index | 154.77 | 141.91 |
| ARC-AGI-2 | 77.1% | — |
| NYT Connections (extended) | 97.4% | — |
| CritPt | 17.7% | — |
| Thematic Generalization | 79.4% | — |
| EBR-Bench | 14.3% | — |
| LiveBench Reasoning | — | 91.6% |
| Mystery Game Puzzles | 34% | — |
| LiveBench Data Analysis | — | 65.5% |
| ForecastBench | 59 | — |
| LiveBench | — | 75.7% |

## Math

- Gemini 3.1 Pro Preview: 62.1 (#34)
- o1: 36.1 (#175)

| Benchmark | Gemini 3.1 Pro Preview | o1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 59.6% | 14.7% |
| OTIS Mock AIME 2024-2025 | 95.6% | 73.3% |
| LMArena Math | 1485 | 1388 |
| FrontierMath (Feb 2025 set) | 36.9% | 9.3% |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 86.5% | — |
| ProofBench | 26% | — |
| LiveBench Math | — | 80.3% |
| MATH Level 5 | — | 94.7% |
| FrontierMath Tier 4 (v1) | 16.7% | — |

## Knowledge

- Gemini 3.1 Pro Preview: 71.8 (#3)
- o1: 41.5 (#110)

| Benchmark | Gemini 3.1 Pro Preview | o1 |
|---|---|---|
| GPQA Diamond | 94.4% | 76.8% |
| Humanity's Last Exam | 46.4% | 8% |
| SimpleQA Verified | 73.5% | 41.1% |
| LMArena Expert | 1485 | 1361 |
| Confabulations | — | 11.7% |
| Vectara Hallucination Rate | 10.4% | — |

## Multimodal

- Gemini 3.1 Pro Preview: 37.9 (#69)
- o1: 34.2 (#93)

| Benchmark | Gemini 3.1 Pro Preview | o1 |
|---|---|---|
| LMArena Vision | 1296 | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| Blueprint-Bench 2 | 26.5% | — |
| Furniture Assembly | 26.7% | — |
| LMArena Document | 1444 | — |
| SpatialViz-Bench | — | 41.4% |

## Multilingual

- Gemini 3.1 Pro Preview: 57.0 (#12)
- o1: 48.6 (#142)

| Benchmark | Gemini 3.1 Pro Preview | o1 |
|---|---|---|
| LMArena Non-English | 1477 | 1358 |
| LMArena Chinese | 1529 | 1394 |
| LMArena French | 1487 | 1344 |
| LMArena German | 1491 | 1337 |
| LMArena Japanese | 1493 | 1346 |
| LMArena Korean | 1455 | 1396 |
| LMArena Russian | 1498 | 1356 |
| LMArena Spanish | 1479 | 1345 |

## Instruction Following

- Gemini 3.1 Pro Preview: 77.0 (#32)
- o1: 74.8 (#86)

| Benchmark | Gemini 3.1 Pro Preview | o1 |
|---|---|---|
| LMArena Instruction Following | 1466 | 1367 |
| LiveBench Instruction Following | — | 81.5% |

## Long Context

- Gemini 3.1 Pro Preview: 47.4 (#18)
- o1: 50.3 (#9)

| Benchmark | Gemini 3.1 Pro Preview | o1 |
|---|---|---|
| LMArena Longer Query | 1483 | 1378 |
| Fiction.LiveBench | — | 83.3% |
| CL-bench | 20.8% | — |
| CL-bench Life | 16.9% | — |

## Writing & Preference

- Gemini 3.1 Pro Preview: 66.1 (#37)
- o1: 55.6 (#144)

| Benchmark | Gemini 3.1 Pro Preview | o1 |
|---|---|---|
| LMArena Text | 1481 | 1366 |
| LMArena Creative Writing | 1482 | 1348 |
| LMArena Multi-Turn | 1488 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| EQ-Bench Creative Writing | 1491 | — |
| EQ-Bench 4 | 1142 | — |
| LiveBench Language | — | 65.4% |

## FAQ

### Is Gemini 3.1 Pro Preview better than o1?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 40.9 on the Noometry Index.

### Which is cheaper, Gemini 3.1 Pro Preview or o1?

Gemini 3.1 Pro Preview is cheaper. It lists at $2 per million input tokens and $12 per million output tokens; o1 lists at $15 and $60.

### Is Gemini 3.1 Pro Preview or o1 better for coding?

o1 scores higher on coding benchmarks: 46.1 versus 42.5 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 200K.

### How many benchmarks do Gemini 3.1 Pro Preview and o1 share?

33 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and o1 has 52.