# Gemini 3.1 Pro Preview vs Grok 3

> Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 39.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-1-pro-preview-vs-grok-3
- Last updated: 2026-10-10
- Shared benchmarks: 29

## Summary

- They share 29 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 9 categories and Grok 3 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 13.7.
- The biggest single-benchmark swing is ARC-AGI-1: 98% for Gemini 3.1 Pro Preview and 5.5% for Grok 3.

## Snapshot

| | Gemini 3.1 Pro Preview | Grok 3 |
|---|---|---|
| Provider | Google | xAI |
| Noometry Index | 56.7 | 39.9 |
| Rank | 23 | 157 |
| Context | 1.05M | — |
| Input $/M | $2 | — |
| Output $/M | $12 | — |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3.1 Pro Preview: 42.5 (#99)
- Grok 3: 41.9 (#115)

| Benchmark | Gemini 3.1 Pro Preview | Grok 3 |
|---|---|---|
| WeirdML | 72.1% | 37.2% |
| LMArena Coding | 1484 | 1432 |
| SWE-bench Verified | 75.6% | — |
| DeepSWE | 11.7% | — |
| Aider Polyglot | — | 53.3% |
| LMArena WebDev | 1447 | — |
| SciCode | 58.9% | — |
| GSO | 22.6% | — |
| MirrorCode | 8.9% | — |
| ALE-Bench | 1,161 | — |
| AlgoTune | 2.02 | — |

## Agentic & Tool Use

- Gemini 3.1 Pro Preview: 37.7 (#34)
- Grok 3: 30.5 (#76)

| Benchmark | Gemini 3.1 Pro Preview | Grok 3 |
|---|---|---|
| BALROG | 57% | 29.5% |
| 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 (#12)
- Grok 3: 13.7 (#333)

| Benchmark | Gemini 3.1 Pro Preview | Grok 3 |
|---|---|---|
| ARC-AGI-2 | 77.1% | 0% |
| SimpleBench | 79.6% | 36.1% |
| ARC-AGI-1 | 98% | 5.5% |
| LMArena Hard Prompts | 1485 | 1434 |
| Epoch Capabilities Index | 154.77 | 138.33 |
| Kagi LLM Benchmark | — | 61.3% |
| NYT Connections (extended) | 97.4% | — |
| CritPt | 17.7% | — |
| Chess Puzzles | 55% | — |
| EnigmaEval | 36.8% | — |
| Thematic Generalization | 79.4% | — |
| EBR-Bench | 14.3% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 97.1% | — |
| LMCA | 53.8% | — |
| ForecastBench | 59 | — |

## Math

- Gemini 3.1 Pro Preview: 62.1 (#34)
- Grok 3: 38.0 (#145)

| Benchmark | Gemini 3.1 Pro Preview | Grok 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 55.6% |
| LMArena Math | 1485 | 1391 |
| FrontierMath (Feb 2025 set) | 36.9% | 3.8% |
| FrontierMath Tier 4 (v1) | 16.7% | 0% |
| FrontierMath (Tiers 1-3) | 59.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 86.5% | — |
| ProofBench | 26% | — |
| Omni-MATH | — | 46.4% |
| MATH Level 5 | — | 88.7% |

## Knowledge

- Gemini 3.1 Pro Preview: 71.8 (#3)
- Grok 3: 46.2 (#82)

| Benchmark | Gemini 3.1 Pro Preview | Grok 3 |
|---|---|---|
| GPQA Diamond | 94.4% | 75.8% |
| Vectara Hallucination Rate | 10.4% | 5.8% |
| LMArena Expert | 1485 | 1421 |
| Humanity's Last Exam | 46.4% | — |
| SimpleQA Verified | 73.5% | — |
| MMLU-Pro | — | 78.8% |
| Confabulations | — | 14.2% |
| GPQA (HELM) | — | 65% |

## Multimodal

- Gemini 3.1 Pro Preview: 37.9 (#69)
- Grok 3: —

| Benchmark | Gemini 3.1 Pro Preview | Grok 3 |
|---|---|---|
| LMArena Vision | 1296 | — |
| Blueprint-Bench 2 | 26.5% | — |
| Furniture Assembly | 26.7% | — |
| LMArena Document | 1444 | — |

## Multilingual

- Gemini 3.1 Pro Preview: 57.0 (#12)
- Grok 3: 52.3 (#87)

| Benchmark | Gemini 3.1 Pro Preview | Grok 3 |
|---|---|---|
| LMArena Non-English | 1477 | 1410 |
| LMArena Chinese | 1529 | 1448 |
| LMArena French | 1487 | 1460 |
| LMArena German | 1491 | 1431 |
| LMArena Japanese | 1493 | 1387 |
| LMArena Korean | 1455 | 1373 |
| LMArena Russian | 1498 | 1416 |
| LMArena Spanish | 1479 | 1417 |

## Instruction Following

- Gemini 3.1 Pro Preview: 77.0 (#32)
- Grok 3: 75.0 (#73)

| Benchmark | Gemini 3.1 Pro Preview | Grok 3 |
|---|---|---|
| LMArena Instruction Following | 1466 | 1409 |
| IFEval | — | 88.4% |

## Long Context

- Gemini 3.1 Pro Preview: 47.4 (#18)
- Grok 3: 38.7 (#192)

| Benchmark | Gemini 3.1 Pro Preview | Grok 3 |
|---|---|---|
| LMArena Longer Query | 1483 | 1439 |
| Fiction.LiveBench | — | 58.3% |
| CL-bench | 20.8% | — |
| CL-bench Life | 16.9% | — |

## Writing & Preference

- Gemini 3.1 Pro Preview: 66.1 (#37)
- Grok 3: 55.8 (#141)

| Benchmark | Gemini 3.1 Pro Preview | Grok 3 |
|---|---|---|
| LMArena Text | 1481 | 1426 |
| LMArena Creative Writing | 1482 | 1414 |
| EQ-Bench Creative Writing | 1491 | 1186 |
| LMArena Multi-Turn | 1488 | 1425 |
| Short-Story Creative Writing | — | 76.4% |
| WildBench | — | 84.9% |
| EQ-Bench 4 | 1142 | — |

## FAQ

### Is Gemini 3.1 Pro Preview better than Grok 3?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 39.9 on the Noometry Index.

### Is Gemini 3.1 Pro Preview or Grok 3 better for coding?

They score almost the same on coding (42.5 vs 41.9); test both on your own repository before choosing.

### How many benchmarks do Gemini 3.1 Pro Preview and Grok 3 share?

29 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Grok 3 has 40.