# Claude 3 Sonnet vs Grok 4.20 (Non-Reasoning)

> Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-sonnet-vs-grok-4-20
- 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 4.20 (Non-Reasoning) in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4.20 (Non-Reasoning) leads 48.0 to 10.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 92.2% for Grok 4.20 (Non-Reasoning).

## Snapshot

| | Claude 3 Sonnet | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 28.8 | 48.5 |
| Rank | 311 | 48 |
| Context | — | 1M |
| Input $/M | — | $1.25 |
| Output $/M | — | $2.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3 Sonnet: 29.2 (#296)
- Grok 4.20 (Non-Reasoning): 41.8 (#104)

| Benchmark | Claude 3 Sonnet | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| WeirdML | 10.2% | 52.3% |
| LMArena Coding | 1223 | 1458 |
| LMArena WebDev | — | 1374 |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| ALE-Bench | — | 1,150 |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |

## Agentic & Tool Use

- Claude 3 Sonnet: —
- Grok 4.20 (Non-Reasoning): 34.3 (#43)

| Benchmark | Claude 3 Sonnet | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | — | 57.3% |
| τ²-bench Banking | — | 18% |
| LMArena Search | — | 1189 |
| Vending-Bench 2 | — | 4,663 |

## Reasoning

- Claude 3 Sonnet: 19.7 (#232)
- Grok 4.20 (Non-Reasoning): 52.2 (#30)

| Benchmark | Claude 3 Sonnet | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1451 |
| DTBench | 53.6% | 90.1% |
| Epoch Capabilities Index | 120.69 | 152.01 |
| ARC-AGI-2 | — | 65.1% |
| Kagi LLM Benchmark | — | 75% |
| NYT Connections (extended) | — | 85.4% |
| ARC-AGI-1 | — | 89.5% |
| Chess Puzzles | — | 24% |
| Thematic Generalization | — | 63.8% |
| LMCA | — | 38.7% |
| ForecastBench | — | 61.4 |
| WinoGrande | 75.1% | — |

## Math

- Claude 3 Sonnet: 10.0 (#305)
- Grok 4.20 (Non-Reasoning): 48.0 (#54)

| Benchmark | Claude 3 Sonnet | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 92.2% |
| LMArena Math | 1213 | 1455 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 14% |
| MATH Level 5 | 18.2% | — |

## Knowledge

- Claude 3 Sonnet: 21.1 (#271)
- Grok 4.20 (Non-Reasoning): 52.8 (#54)

| Benchmark | Claude 3 Sonnet | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | 40.6% | 89.3% |
| LMArena Expert | 1173 | 1440 |
| SimpleQA Verified | — | 30.2% |
| MMLU | 75.9% | — |

## Multimodal

- Claude 3 Sonnet: 24.7 (#120)
- Grok 4.20 (Non-Reasoning): 33.2 (#88)

| Benchmark | Claude 3 Sonnet | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | 984 | 1263 |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |

## Multilingual

- Claude 3 Sonnet: 38.0 (#229)
- Grok 4.20 (Non-Reasoning): 54.7 (#38)

| Benchmark | Claude 3 Sonnet | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1205 | 1440 |
| LMArena Chinese | 1188 | 1481 |
| LMArena French | 1228 | 1477 |
| LMArena German | 1204 | 1463 |
| LMArena Japanese | 1131 | 1450 |
| LMArena Korean | 1128 | 1417 |
| LMArena Russian | 1227 | 1457 |
| LMArena Spanish | 1204 | 1442 |

## Instruction Following

- Claude 3 Sonnet: 63.1 (#230)
- Grok 4.20 (Non-Reasoning): 75.0 (#79)

| Benchmark | Claude 3 Sonnet | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1200 | 1420 |

## Long Context

- Claude 3 Sonnet: 36.7 (#223)
- Grok 4.20 (Non-Reasoning): 45.4 (#33)

| Benchmark | Claude 3 Sonnet | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1211 | 1436 |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |

## Writing & Preference

- Claude 3 Sonnet: 42.3 (#233)
- Grok 4.20 (Non-Reasoning): 65.9 (#42)

| Benchmark | Claude 3 Sonnet | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1218 | 1451 |
| LMArena Creative Writing | 1186 | 1439 |
| LMArena Multi-Turn | 1227 | 1456 |
| EQ-Bench Creative Writing | — | 1574 |

## FAQ

### Is Claude 3 Sonnet better than Grok 4.20 (Non-Reasoning)?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 28.8 on the Noometry Index.

### Is Claude 3 Sonnet or Grok 4.20 (Non-Reasoning) better for coding?

Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 41.8 versus 29.2 in the Noometry coding category.

### How many benchmarks do Claude 3 Sonnet and Grok 4.20 (Non-Reasoning) share?

23 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.