# Grok 4.6 vs Grok 4 Fast

> Grok 4.6 is the stronger model overall, scoring 56.8 to 39.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-4-6-vs-grok-4-fast
- Last updated: 2026-10-10
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. Grok 4.6 scores higher in 8 categories and Grok 4 Fast in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.6 leads 61.3 to 22.5.
- The biggest single-benchmark swing is ARC-AGI-2: 67.1% for Grok 4.6 and 5.3% for Grok 4 Fast.

## Snapshot

| | Grok 4.6 | Grok 4 Fast |
|---|---|---|
| Provider | xAI | xAI |
| Noometry Index | 56.8 | 39.0 |
| Rank | 19 | 164 |
| Context | 500K | — |
| Input $/M | $2 | — |
| Output $/M | $6 | — |
| Weights | Proprietary | Proprietary |

## Coding

- Grok 4.6: 58.0 (#14)
- Grok 4 Fast: 32.3 (#264)

| Benchmark | Grok 4.6 | Grok 4 Fast |
|---|---|---|
| LMArena WebDev | 1620 | 1160 |
| WeirdML | 67.3% | 42.9% |
| LMArena Coding | 1464 | 1429 |
| DeepSWE | 67.5% | — |
| FrontierCode | 48% | — |
| CursorBench | 41.4% | — |
| FrontierSWE | 25.3% | — |
| SciCode | 56.5% | — |
| ALE-Bench | 1,508 | — |

## Agentic & Tool Use

- Grok 4.6: 39.4 (#25)
- Grok 4 Fast: 29.3 (#80)

| Benchmark | Grok 4.6 | Grok 4 Fast |
|---|---|---|
| APEX-Agents | 65.3% | — |
| τ²-bench Banking | — | 15.7% |
| Cybench | — | 30% |
| GDP.pdf | 17.2% | — |
| LMArena Search | — | 1171 |
| Vending-Bench 2 | 9,047 | — |

## Reasoning

- Grok 4.6: 61.3 (#18)
- Grok 4 Fast: 22.5 (#179)

| Benchmark | Grok 4.6 | Grok 4 Fast |
|---|---|---|
| ARC-AGI-2 | 67.1% | 5.3% |
| ARC-AGI-1 | 87.5% | 48.5% |
| LMArena Hard Prompts | 1445 | 1413 |
| DTBench | 97.3% | 82.7% |
| Epoch Capabilities Index | 156.48 | 144.21 |
| SimpleBench | 75.9% | — |
| Kagi LLM Benchmark | — | 66.1% |
| NYT Connections (extended) | 80% | — |
| CritPt | 19.7% | — |
| Chess Puzzles | 40% | — |
| EBR-Bench | 30.5% | — |
| Mystery Game Puzzles | 34% | — |
| LMCA | 48.5% | — |
| ForecastBench | — | 60.5 |

## Math

- Grok 4.6: 66.8 (#19)
- Grok 4 Fast: 36.1 (#126)

| Benchmark | Grok 4.6 | Grok 4 Fast |
|---|---|---|
| LMArena Math | 1416 | 1419 |
| FrontierMath (Tiers 1-3) | 66% | — |
| FrontierMath Tier 4 | 31.7% | — |
| OTIS Mock AIME 2024-2025 | 99.2% | — |
| ProofBench | 51% | — |

## Knowledge

- Grok 4.6: 63.3 (#18)
- Grok 4 Fast: 31.5 (#211)

| Benchmark | Grok 4.6 | Grok 4 Fast |
|---|---|---|
| LMArena Expert | 1463 | 1411 |
| GPQA Diamond | 94% | — |
| SimpleQA Verified | 49.3% | — |
| Vectara Hallucination Rate | — | 19.7% |

## Multimodal

- Grok 4.6: 43.9 (#18)
- Grok 4 Fast: —

| Benchmark | Grok 4.6 | Grok 4 Fast |
|---|---|---|
| LMArena Vision | 1265 | — |
| Blueprint-Bench 2 | 33.2% | — |
| Furniture Assembly | 40% | — |
| LMArena Document | 1452 | — |

## Multilingual

- Grok 4.6: 53.3 (#67)
- Grok 4 Fast: 51.5 (#106)

| Benchmark | Grok 4.6 | Grok 4 Fast |
|---|---|---|
| LMArena Non-English | 1422 | 1397 |
| LMArena Chinese | 1479 | 1458 |
| LMArena French | 1458 | 1433 |
| LMArena German | 1425 | 1383 |
| LMArena Japanese | 1383 | 1358 |
| LMArena Korean | 1395 | 1359 |
| LMArena Russian | 1427 | 1387 |
| LMArena Spanish | 1408 | 1414 |

## Instruction Following

- Grok 4.6: 75.6 (#59)
- Grok 4 Fast: 73.4 (#116)

| Benchmark | Grok 4.6 | Grok 4 Fast |
|---|---|---|
| LMArena Instruction Following | 1431 | 1388 |

## Long Context

- Grok 4.6: 44.4 (#62)
- Grok 4 Fast: 63.2 (#3)

| Benchmark | Grok 4.6 | Grok 4 Fast |
|---|---|---|
| LMArena Longer Query | 1453 | 1415 |
| Fiction.LiveBench | — | 94.4% |

## Writing & Preference

- Grok 4.6: 62.5 (#77)
- Grok 4 Fast: 60.2 (#96)

| Benchmark | Grok 4.6 | Grok 4 Fast |
|---|---|---|
| LMArena Text | 1427 | 1407 |
| LMArena Creative Writing | 1430 | 1388 |
| LMArena Multi-Turn | 1422 | 1414 |

## FAQ

### Is Grok 4.6 better than Grok 4 Fast?

Grok 4.6 is the stronger model overall, scoring 56.8 to 39.0 on the Noometry Index.

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

Grok 4.6 scores higher on coding benchmarks: 58.0 versus 32.3 in the Noometry coding category.

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

23 benchmarks have published results for both models. Grok 4.6 has 49 scored results on Noometry and Grok 4 Fast has 30.