# Grok 3 vs Grok 4.1

> Grok 4.1 is the stronger model overall, scoring 41.5 to 39.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-3-vs-grok-4-1
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Grok 3 scores higher in 3 categories and Grok 4.1 in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.1 leads 29.5 to 13.7.

## Snapshot

| | Grok 3 | Grok 4.1 |
|---|---|---|
| Provider | xAI | xAI |
| Noometry Index | 39.9 | 41.5 |
| Rank | 157 | 134 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Proprietary |

## Coding

- Grok 3: 41.9 (#115)
- Grok 4.1: 33.7 (#253)

| Benchmark | Grok 3 | Grok 4.1 |
|---|---|---|
| LMArena Coding | 1432 | 1445 |
| Aider Polyglot | 53.3% | — |
| LMArena WebDev | — | 1214 |
| WeirdML | 37.2% | — |

## Agentic & Tool Use

- Grok 3: 30.5 (#76)
- Grok 4.1: 34.1 (#49)

| Benchmark | Grok 3 | Grok 4.1 |
|---|---|---|
| Cybench | — | 39% |
| BALROG | 29.5% | — |

## Reasoning

- Grok 3: 13.7 (#333)
- Grok 4.1: 29.5 (#91)

| Benchmark | Grok 3 | Grok 4.1 |
|---|---|---|
| LMArena Hard Prompts | 1434 | 1435 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 36.1% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 5.5% | — |
| Epoch Capabilities Index | 138.33 | — |

## Math

- Grok 3: 38.0 (#145)
- Grok 4.1: 38.9 (#120)

| Benchmark | Grok 3 | Grok 4.1 |
|---|---|---|
| LMArena Math | 1391 | 1422 |
| OTIS Mock AIME 2024-2025 | 55.6% | — |
| Omni-MATH | 46.4% | — |
| MATH Level 5 | 88.7% | — |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- Grok 3: 46.2 (#82)
- Grok 4.1: 39.5 (#133)

| Benchmark | Grok 3 | Grok 4.1 |
|---|---|---|
| LMArena Expert | 1421 | 1417 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 78.8% | — |
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 5.8% | — |
| GPQA (HELM) | 65% | — |

## Multilingual

- Grok 3: 52.3 (#87)
- Grok 4.1: 53.4 (#68)

| Benchmark | Grok 3 | Grok 4.1 |
|---|---|---|
| LMArena Non-English | 1410 | 1425 |
| LMArena Chinese | 1448 | 1465 |
| LMArena French | 1460 | 1448 |
| LMArena German | 1431 | 1446 |
| LMArena Japanese | 1387 | 1397 |
| LMArena Korean | 1373 | 1407 |
| LMArena Russian | 1416 | 1434 |
| LMArena Spanish | 1417 | 1438 |

## Instruction Following

- Grok 3: 75.0 (#73)
- Grok 4.1: 73.8 (#111)

| Benchmark | Grok 3 | Grok 4.1 |
|---|---|---|
| LMArena Instruction Following | 1409 | 1400 |
| IFEval | 88.4% | — |

## Long Context

- Grok 3: 38.7 (#192)
- Grok 4.1: 43.2 (#100)

| Benchmark | Grok 3 | Grok 4.1 |
|---|---|---|
| LMArena Longer Query | 1439 | 1416 |
| Fiction.LiveBench | 58.3% | — |

## Writing & Preference

- Grok 3: 55.8 (#141)
- Grok 4.1: 62.4 (#75)

| Benchmark | Grok 3 | Grok 4.1 |
|---|---|---|
| LMArena Text | 1426 | 1437 |
| LMArena Creative Writing | 1414 | 1411 |
| LMArena Multi-Turn | 1425 | 1437 |
| Short-Story Creative Writing | 76.4% | — |
| EQ-Bench Creative Writing | 1186 | — |
| WildBench | 84.9% | — |

## FAQ

### Is Grok 3 better than Grok 4.1?

Grok 4.1 is the stronger model overall, scoring 41.5 to 39.9 on the Noometry Index.

### Is Grok 3 or Grok 4.1 better for coding?

Grok 3 scores higher on coding benchmarks: 41.9 versus 33.7 in the Noometry coding category.

### How many benchmarks do Grok 3 and Grok 4.1 share?

17 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Grok 4.1 has 19.