# Claude 3 Sonnet vs Grok 4.6

> Grok 4.6 is the stronger model overall, scoring 56.8 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-sonnet-vs-grok-4-6
- Last updated: 2026-10-10
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Grok 4.6 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4.6 leads 66.8 to 10.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 99.2% for Grok 4.6.

## Snapshot

| | Claude 3 Sonnet | Grok 4.6 |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 28.8 | 56.8 |
| Rank | 311 | 19 |
| Context | — | 500K |
| Input $/M | — | $2 |
| Output $/M | — | $6 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3 Sonnet: 29.2 (#296)
- Grok 4.6: 58.0 (#14)

| Benchmark | Claude 3 Sonnet | Grok 4.6 |
|---|---|---|
| WeirdML | 10.2% | 67.3% |
| LMArena Coding | 1223 | 1464 |
| DeepSWE | — | 67.5% |
| FrontierCode | — | 48% |
| CursorBench | — | 41.4% |
| LMArena WebDev | — | 1620 |
| FrontierSWE | — | 25.3% |
| SciCode | — | 56.5% |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| ALE-Bench | — | 1,508 |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |

## Agentic & Tool Use

- Claude 3 Sonnet: —
- Grok 4.6: 39.4 (#25)

| Benchmark | Claude 3 Sonnet | Grok 4.6 |
|---|---|---|
| APEX-Agents | — | 65.3% |
| GDP.pdf | — | 17.2% |
| Vending-Bench 2 | — | 9,047 |

## Reasoning

- Claude 3 Sonnet: 19.7 (#232)
- Grok 4.6: 61.3 (#18)

| Benchmark | Claude 3 Sonnet | Grok 4.6 |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1445 |
| DTBench | 53.6% | 97.3% |
| Epoch Capabilities Index | 120.69 | 156.48 |
| ARC-AGI-2 | — | 67.1% |
| SimpleBench | — | 75.9% |
| NYT Connections (extended) | — | 80% |
| ARC-AGI-1 | — | 87.5% |
| CritPt | — | 19.7% |
| Chess Puzzles | — | 40% |
| EBR-Bench | — | 30.5% |
| Mystery Game Puzzles | — | 34% |
| LMCA | — | 48.5% |
| WinoGrande | 75.1% | — |

## Math

- Claude 3 Sonnet: 10.0 (#305)
- Grok 4.6: 66.8 (#19)

| Benchmark | Claude 3 Sonnet | Grok 4.6 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 99.2% |
| LMArena Math | 1213 | 1416 |
| FrontierMath (Tiers 1-3) | — | 66% |
| FrontierMath Tier 4 | — | 31.7% |
| ProofBench | — | 51% |
| MATH Level 5 | 18.2% | — |

## Knowledge

- Claude 3 Sonnet: 21.1 (#271)
- Grok 4.6: 63.3 (#18)

| Benchmark | Claude 3 Sonnet | Grok 4.6 |
|---|---|---|
| GPQA Diamond | 40.6% | 94% |
| LMArena Expert | 1173 | 1463 |
| SimpleQA Verified | — | 49.3% |
| MMLU | 75.9% | — |

## Multimodal

- Claude 3 Sonnet: 24.7 (#120)
- Grok 4.6: 43.9 (#18)

| Benchmark | Claude 3 Sonnet | Grok 4.6 |
|---|---|---|
| LMArena Vision | 984 | 1265 |
| Blueprint-Bench 2 | — | 33.2% |
| Furniture Assembly | — | 40% |
| LMArena Document | — | 1452 |

## Multilingual

- Claude 3 Sonnet: 38.0 (#229)
- Grok 4.6: 53.3 (#67)

| Benchmark | Claude 3 Sonnet | Grok 4.6 |
|---|---|---|
| LMArena Non-English | 1205 | 1422 |
| LMArena Chinese | 1188 | 1479 |
| LMArena French | 1228 | 1458 |
| LMArena German | 1204 | 1425 |
| LMArena Japanese | 1131 | 1383 |
| LMArena Korean | 1128 | 1395 |
| LMArena Russian | 1227 | 1427 |
| LMArena Spanish | 1204 | 1408 |

## Instruction Following

- Claude 3 Sonnet: 63.1 (#230)
- Grok 4.6: 75.6 (#59)

| Benchmark | Claude 3 Sonnet | Grok 4.6 |
|---|---|---|
| LMArena Instruction Following | 1200 | 1431 |

## Long Context

- Claude 3 Sonnet: 36.7 (#223)
- Grok 4.6: 44.4 (#62)

| Benchmark | Claude 3 Sonnet | Grok 4.6 |
|---|---|---|
| LMArena Longer Query | 1211 | 1453 |

## Writing & Preference

- Claude 3 Sonnet: 42.3 (#233)
- Grok 4.6: 62.5 (#77)

| Benchmark | Claude 3 Sonnet | Grok 4.6 |
|---|---|---|
| LMArena Text | 1218 | 1427 |
| LMArena Creative Writing | 1186 | 1430 |
| LMArena Multi-Turn | 1227 | 1422 |

## FAQ

### Is Claude 3 Sonnet better than Grok 4.6?

Grok 4.6 is the stronger model overall, scoring 56.8 to 28.8 on the Noometry Index.

### Is Claude 3 Sonnet or Grok 4.6 better for coding?

Grok 4.6 scores higher on coding benchmarks: 58.0 versus 29.2 in the Noometry coding category.

### How many benchmarks do Claude 3 Sonnet and Grok 4.6 share?

23 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Grok 4.6 has 49.