# Claude 3 Sonnet vs Grok 4

> Grok 4 is the stronger model overall, scoring 48.1 to 29.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-sonnet-vs-grok-4
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Grok 4 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4 leads 48.4 to 10.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 84% for Grok 4.

## Snapshot

| | Claude 3 Sonnet | Grok 4 |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 29.0 | 48.1 |
| Rank | 319 | 56 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3 Sonnet: 29.6 (#302)
- Grok 4: 50.3 (#46)

| Benchmark | Claude 3 Sonnet | Grok 4 |
|---|---|---|
| WeirdML | 10.2% | 45.7% |
| LMArena Coding | 1223 | 1408 |
| Aider Polyglot | — | 79.6% |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |

## Agentic & Tool Use

- Claude 3 Sonnet: —
- Grok 4: 32.3 (#68)

| Benchmark | Claude 3 Sonnet | Grok 4 |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 21.1% |
| Cybench | — | 43% |
| DeepResearch Bench | — | 47.3% |
| BALROG | — | 43.6% |
| LMArena Search | — | 1142 |
| METR Time Horizons | — | 66.6% |

## Reasoning

- Claude 3 Sonnet: 20.5 (#237)
- Grok 4: 36.7 (#65)

| Benchmark | Claude 3 Sonnet | Grok 4 |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1409 |
| Epoch Capabilities Index | 120.7 | 146.44 |
| ARC-AGI-2 | — | 16% |
| SimpleBench | — | 60.5% |
| Kagi LLM Benchmark | — | 73.6% |
| ARC-AGI-1 | — | 66.7% |
| Chess Puzzles | — | 28% |
| DTBench | 53.6% | — |
| ForecastBench | — | 60.9 |
| WinoGrande | 75.1% | — |

## Math

- Claude 3 Sonnet: 10.7 (#310)
- Grok 4: 48.4 (#64)

| Benchmark | Claude 3 Sonnet | Grok 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 84% |
| LMArena Math | 1213 | 1422 |
| Omni-MATH | — | 60.3% |
| MATH Level 5 | 18.2% | — |
| FrontierMath (Feb 2025 set) | — | 19.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- Claude 3 Sonnet: 21.1 (#276)
- Grok 4: 53.8 (#55)

| Benchmark | Claude 3 Sonnet | Grok 4 |
|---|---|---|
| GPQA Diamond | 40.6% | 87% |
| LMArena Expert | 1173 | 1415 |
| MMLU-Pro | — | 85.1% |
| Confabulations | — | 12.4% |
| GPQA (HELM) | — | 72.7% |
| MMLU | 75.9% | — |

## Multimodal

- Claude 3 Sonnet: 25.2 (#125)
- Grok 4: 33.7 (#94)

| Benchmark | Claude 3 Sonnet | Grok 4 |
|---|---|---|
| LMArena Vision | 984 | 1210 |
| GeoBench | — | 45% |

## Multilingual

- Claude 3 Sonnet: 37.8 (#234)
- Grok 4: 51.8 (#103)

| Benchmark | Claude 3 Sonnet | Grok 4 |
|---|---|---|
| LMArena Non-English | 1205 | 1403 |
| LMArena Chinese | 1189 | 1427 |
| LMArena French | 1229 | 1418 |
| LMArena German | 1204 | 1429 |
| LMArena Japanese | 1131 | 1394 |
| LMArena Korean | 1128 | 1377 |
| LMArena Russian | 1227 | 1410 |
| LMArena Spanish | 1204 | 1420 |

## Instruction Following

- Claude 3 Sonnet: 62.8 (#235)
- Grok 4: 79.2 (#5)

| Benchmark | Claude 3 Sonnet | Grok 4 |
|---|---|---|
| LMArena Instruction Following | 1199 | 1387 |
| IFEval | — | 94.9% |

## Long Context

- Claude 3 Sonnet: 36.7 (#228)
- Grok 4: 63.1 (#4)

| Benchmark | Claude 3 Sonnet | Grok 4 |
|---|---|---|
| LMArena Longer Query | 1211 | 1409 |
| Fiction.LiveBench | — | 94.4% |

## Writing & Preference

- Claude 3 Sonnet: 42.1 (#238)
- Grok 4: 58.5 (#116)

| Benchmark | Claude 3 Sonnet | Grok 4 |
|---|---|---|
| LMArena Text | 1218 | 1411 |
| LMArena Creative Writing | 1186 | 1397 |
| LMArena Multi-Turn | 1227 | 1416 |
| Short-Story Creative Writing | — | 76.9% |
| WildBench | — | 79.7% |

## FAQ

### Is Claude 3 Sonnet better than Grok 4?

Grok 4 is the stronger model overall, scoring 48.1 to 29.0 on the Noometry Index.

### Is Claude 3 Sonnet or Grok 4 better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 29.6 in the Noometry coding category.

### How many benchmarks do Claude 3 Sonnet and Grok 4 share?

22 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Grok 4 has 48.