# Grok 4 vs Grok 4.6

> Grok 4.6 is the stronger model overall, scoring 56.9 to 48.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-4-vs-grok-4-6
- Last updated: 2026-10-10
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. Grok 4 scores higher in 2 categories and Grok 4.6 in 8 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.6 leads 61.4 to 36.7.
- The biggest single-benchmark swing is ARC-AGI-2: 16% for Grok 4 and 67.1% for Grok 4.6.

## Snapshot

| | Grok 4 | Grok 4.6 |
|---|---|---|
| Provider | xAI | xAI |
| Noometry Index | 48.1 | 56.9 |
| Rank | 56 | 21 |
| Context | — | 500K |
| Input $/M | — | $2 |
| Output $/M | — | $6 |
| Weights | Proprietary | Proprietary |

## Coding

- Grok 4: 50.3 (#46)
- Grok 4.6: 58.5 (#16)

| Benchmark | Grok 4 | Grok 4.6 |
|---|---|---|
| WeirdML | 45.7% | 67.3% |
| LMArena Coding | 1408 | 1465 |
| DeepSWE | — | 67.5% |
| FrontierCode | — | 48% |
| Aider Polyglot | 79.6% | — |
| CursorBench | — | 41.4% |
| LMArena WebDev | — | 1617 |
| FrontierSWE | — | 25.3% |
| SciCode | — | 56.5% |
| ALE-Bench | — | 1,508 |

## Agentic & Tool Use

- Grok 4: 32.3 (#68)
- Grok 4.6: 39.4 (#27)

| Benchmark | Grok 4 | Grok 4.6 |
|---|---|---|
| Terminal-Bench | 27.2% | — |
| APEX-Agents | — | 65.3% |
| Berkeley Function Calling Leaderboard | 63% | — |
| GDPval | 21.1% | — |
| Cybench | 43% | — |
| DeepResearch Bench | 47.3% | — |
| BALROG | 43.6% | — |
| GDP.pdf | — | 17.2% |
| LMArena Search | 1142 | — |
| METR Time Horizons | 66.6% | — |
| Vending-Bench 2 | — | 9,047 |

## Reasoning

- Grok 4: 36.7 (#65)
- Grok 4.6: 61.4 (#20)

| Benchmark | Grok 4 | Grok 4.6 |
|---|---|---|
| ARC-AGI-2 | 16% | 67.1% |
| SimpleBench | 60.5% | 75.9% |
| ARC-AGI-1 | 66.7% | 87.5% |
| Chess Puzzles | 28% | 40% |
| LMArena Hard Prompts | 1409 | 1447 |
| Epoch Capabilities Index | 146.44 | 156.44 |
| Kagi LLM Benchmark | 73.6% | — |
| NYT Connections (extended) | — | 80% |
| CritPt | — | 19.7% |
| EBR-Bench | — | 30.5% |
| Mystery Game Puzzles | — | 34% |
| DTBench | — | 97.3% |
| LMCA | — | 48.5% |
| ForecastBench | 60.9 | — |

## Math

- Grok 4: 48.4 (#64)
- Grok 4.6: 67.0 (#24)

| Benchmark | Grok 4 | Grok 4.6 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 84% | 99.2% |
| LMArena Math | 1422 | 1423 |
| FrontierMath (Tiers 1-3) | — | 66% |
| FrontierMath Tier 4 | — | 31.7% |
| ProofBench | — | 51% |
| Omni-MATH | 60.3% | — |
| FrontierMath (Feb 2025 set) | 19.7% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- Grok 4: 53.8 (#55)
- Grok 4.6: 63.3 (#20)

| Benchmark | Grok 4 | Grok 4.6 |
|---|---|---|
| GPQA Diamond | 87% | 94% |
| LMArena Expert | 1415 | 1467 |
| SimpleQA Verified | — | 49.3% |
| MMLU-Pro | 85.1% | — |
| Confabulations | 12.4% | — |
| GPQA (HELM) | 72.7% | — |

## Multimodal

- Grok 4: 33.7 (#94)
- Grok 4.6: 43.6 (#23)

| Benchmark | Grok 4 | Grok 4.6 |
|---|---|---|
| LMArena Vision | 1210 | 1263 |
| GeoBench | 45% | — |
| Blueprint-Bench 2 | — | 33.2% |
| Furniture Assembly | — | 40% |
| LMArena Document | — | 1452 |

## Multilingual

- Grok 4: 51.8 (#103)
- Grok 4.6: 53.0 (#74)

| Benchmark | Grok 4 | Grok 4.6 |
|---|---|---|
| LMArena Non-English | 1403 | 1420 |
| LMArena Chinese | 1427 | 1480 |
| LMArena French | 1418 | 1461 |
| LMArena German | 1429 | 1431 |
| LMArena Japanese | 1394 | 1376 |
| LMArena Korean | 1377 | 1397 |
| LMArena Russian | 1410 | 1422 |
| LMArena Spanish | 1420 | 1404 |

## Instruction Following

- Grok 4: 79.2 (#5)
- Grok 4.6: 75.4 (#63)

| Benchmark | Grok 4 | Grok 4.6 |
|---|---|---|
| LMArena Instruction Following | 1387 | 1431 |
| IFEval | 94.9% | — |

## Long Context

- Grok 4: 63.1 (#4)
- Grok 4.6: 44.5 (#66)

| Benchmark | Grok 4 | Grok 4.6 |
|---|---|---|
| LMArena Longer Query | 1409 | 1454 |
| Fiction.LiveBench | 94.4% | — |

## Writing & Preference

- Grok 4: 58.5 (#116)
- Grok 4.6: 62.3 (#80)

| Benchmark | Grok 4 | Grok 4.6 |
|---|---|---|
| LMArena Text | 1411 | 1428 |
| LMArena Creative Writing | 1397 | 1428 |
| LMArena Multi-Turn | 1416 | 1425 |
| Short-Story Creative Writing | 76.9% | — |
| WildBench | 79.7% | — |

## FAQ

### Is Grok 4 better than Grok 4.6?

Grok 4.6 is the stronger model overall, scoring 56.9 to 48.1 on the Noometry Index.

### Is Grok 4 or Grok 4.6 better for coding?

Grok 4.6 scores higher on coding benchmarks: 58.5 versus 50.3 in the Noometry coding category.

### How many benchmarks do Grok 4 and Grok 4.6 share?

26 benchmarks have published results for both models. Grok 4 has 48 scored results on Noometry and Grok 4.6 has 49.