# Claude Sonnet 4.6 vs Grok 4

> Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 48.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-sonnet-4-6-vs-grok-4
- Last updated: 2026-10-12
- Shared benchmarks: 31

## Summary

- They share 31 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 6 categories and Grok 4 in 4 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in long context, where Grok 4 leads 63.1 to 45.3.
- The biggest single-benchmark swing is ARC-AGI-2: 60.4% for Claude Sonnet 4.6 and 16% for Grok 4.

## Snapshot

| | Claude Sonnet 4.6 | Grok 4 |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 50.3 | 48.1 |
| Rank | 50 | 56 |
| Context | 1M | — |
| Input $/M | $3 | — |
| Output $/M | $15 | — |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 4.6: 46.3 (#67)
- Grok 4: 50.3 (#46)

| Benchmark | Claude Sonnet 4.6 | Grok 4 |
|---|---|---|
| WeirdML | 66.1% | 45.7% |
| LMArena Coding | 1504 | 1408 |
| SWE-bench Verified | 75.2% | — |
| DeepSWE | 29.9% | — |
| FrontierCode | 24.3% | — |
| Aider Polyglot | — | 79.6% |
| LMArena WebDev | 1522 | — |
| SciCode | 46.8% | — |
| ALE-Bench | 1,327 | — |

## Agentic & Tool Use

- Claude Sonnet 4.6: 39.1 (#28)
- Grok 4: 32.3 (#68)

| Benchmark | Claude Sonnet 4.6 | Grok 4 |
|---|---|---|
| Terminal-Bench | 53.4% | 27.2% |
| DeepResearch Bench | 54.9% | 47.3% |
| LMArena Search | 1221 | 1142 |
| APEX-Agents | 43% | — |
| Berkeley Function Calling Leaderboard | — | 63% |
| OSWorld 2.0 | 9.3% | — |
| GDPval | — | 21.1% |
| Cybench | — | 43% |
| OSWorld | 72.1% | — |
| BALROG | — | 43.6% |
| ExploitBench | 23.6% | — |
| GBAEval | 48.8% | — |
| GDP.pdf | 18% | — |
| METR Time Horizons | — | 66.6% |
| Vending-Bench 2 | 7,204 | — |

## Reasoning

- Claude Sonnet 4.6: 46.1 (#45)
- Grok 4: 36.7 (#65)

| Benchmark | Claude Sonnet 4.6 | Grok 4 |
|---|---|---|
| ARC-AGI-2 | 60.4% | 16% |
| ARC-AGI-1 | 86.5% | 66.7% |
| Chess Puzzles | 13% | 28% |
| LMArena Hard Prompts | 1484 | 1409 |
| Epoch Capabilities Index | 152.24 | 146.44 |
| ForecastBench | 62 | 60.9 |
| SimpleBench | — | 60.5% |
| Kagi LLM Benchmark | — | 73.6% |
| NYT Connections (extended) | 80.9% | — |
| CritPt | 3.1% | — |
| Thematic Generalization | 76.3% | — |
| Mystery Game Puzzles | 16% | — |
| DTBench | 89.9% | — |
| LMCA | 46.5% | — |

## Math

- Claude Sonnet 4.6: 52.9 (#49)
- Grok 4: 48.4 (#64)

| Benchmark | Claude Sonnet 4.6 | Grok 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 85.8% | 84% |
| LMArena Math | 1462 | 1422 |
| FrontierMath (Feb 2025 set) | 32.4% | 19.7% |
| FrontierMath Tier 4 (v1) | 8.3% | 2.1% |
| ProofBench | 45% | — |
| Omni-MATH | — | 60.3% |

## Knowledge

- Claude Sonnet 4.6: 51.7 (#65)
- Grok 4: 53.8 (#55)

| Benchmark | Claude Sonnet 4.6 | Grok 4 |
|---|---|---|
| GPQA Diamond | 87.4% | 87% |
| LMArena Expert | 1500 | 1415 |
| SimpleQA Verified | 35.5% | — |
| MMLU-Pro | — | 85.1% |
| Confabulations | — | 12.4% |
| Vectara Hallucination Rate | 10.6% | — |
| GPQA (HELM) | — | 72.7% |

## Multimodal

- Claude Sonnet 4.6: 38.0 (#68)
- Grok 4: 33.7 (#94)

| Benchmark | Claude Sonnet 4.6 | Grok 4 |
|---|---|---|
| LMArena Vision | 1283 | 1210 |
| GeoBench | — | 45% |
| Blueprint-Bench 2 | 6.7% | — |
| LMArena Document | 1482 | — |

## Multilingual

- Claude Sonnet 4.6: 54.4 (#41)
- Grok 4: 51.8 (#103)

| Benchmark | Claude Sonnet 4.6 | Grok 4 |
|---|---|---|
| LMArena Non-English | 1440 | 1403 |
| LMArena Chinese | 1491 | 1427 |
| LMArena French | 1465 | 1418 |
| LMArena German | 1428 | 1429 |
| LMArena Japanese | 1420 | 1394 |
| LMArena Korean | 1411 | 1377 |
| LMArena Russian | 1440 | 1410 |
| LMArena Spanish | 1464 | 1420 |

## Instruction Following

- Claude Sonnet 4.6: 77.4 (#25)
- Grok 4: 79.2 (#5)

| Benchmark | Claude Sonnet 4.6 | Grok 4 |
|---|---|---|
| LMArena Instruction Following | 1475 | 1387 |
| IFEval | — | 94.9% |

## Long Context

- Claude Sonnet 4.6: 45.3 (#44)
- Grok 4: 63.1 (#4)

| Benchmark | Claude Sonnet 4.6 | Grok 4 |
|---|---|---|
| LMArena Longer Query | 1479 | 1409 |
| Fiction.LiveBench | — | 94.4% |

## Writing & Preference

- Claude Sonnet 4.6: 70.2 (#22)
- Grok 4: 58.5 (#116)

| Benchmark | Claude Sonnet 4.6 | Grok 4 |
|---|---|---|
| LMArena Text | 1458 | 1411 |
| LMArena Creative Writing | 1435 | 1397 |
| LMArena Multi-Turn | 1464 | 1416 |
| Short-Story Creative Writing | — | 76.9% |
| EQ-Bench Creative Writing | 1810 | — |
| WildBench | — | 79.7% |
| EQ-Bench 4 | 1207 | — |

## FAQ

### Is Claude Sonnet 4.6 better than Grok 4?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 48.1 on the Noometry Index.

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

Grok 4 scores higher on coding benchmarks: 50.3 versus 46.3 in the Noometry coding category.

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

31 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Grok 4 has 48.