# Claude 3.7 Sonnet vs Grok-2 (Dec 2024)

> Claude 3.7 Sonnet is the stronger model overall, scoring 39.4 to 33.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-7-sonnet-vs-grok-2
- Last updated: 2026-10-10
- Shared benchmarks: 32

## Summary

- They share 32 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 8 categories and Grok-2 (Dec 2024) in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude 3.7 Sonnet leads 35.7 to 19.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Claude 3.7 Sonnet and 11.5% for Grok-2 (Dec 2024).

## Snapshot

| | Claude 3.7 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 39.4 | 33.4 |
| Rank | 154 | 233 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3.7 Sonnet: 41.1 (#120)
- Grok-2 (Dec 2024): 32.9 (#254)

| Benchmark | Claude 3.7 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| LiveBench Coding | 74.5% | 46.4% |
| LMArena Coding | 1361 | 1288 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| GSO | 3.8% | — |
| WeirdML | — | 22.2% |
| CadEval | 54% | — |

## Agentic & Tool Use

- Claude 3.7 Sonnet: 33.9 (#46)
- Grok-2 (Dec 2024): —

| Benchmark | Claude 3.7 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |

## Reasoning

- Claude 3.7 Sonnet: 18.7 (#252)
- Grok-2 (Dec 2024): 16.4 (#294)

| Benchmark | Claude 3.7 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| SimpleBench | 46.4% | 22.7% |
| LiveBench Reasoning | 87.8% | 54.8% |
| LMArena Hard Prompts | 1333 | 1272 |
| LiveBench Data Analysis | 74% | 54.5% |
| Epoch Capabilities Index | 141.16 | 130.48 |
| LiveBench | 76.1% | 54.3% |
| ARC-AGI-2 | 0.9% | — |
| ARC-AGI-1 | 28.6% | — |
| EnigmaEval | 4.2% | — |
| DTBench | — | 65.2% |
| ForecastBench | 61.8 | — |

## Math

- Claude 3.7 Sonnet: 35.7 (#137)
- Grok-2 (Dec 2024): 19.6 (#278)

| Benchmark | Claude 3.7 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 11.5% |
| LiveBench Math | 79% | 54.9% |
| LMArena Math | 1336 | 1283 |
| MATH Level 5 | 91.2% | 63.5% |
| FrontierMath (Feb 2025 set) | 4.1% | 0.7% |
| Omni-MATH | 33% | — |

## Knowledge

- Claude 3.7 Sonnet: 39.7 (#117)
- Grok-2 (Dec 2024): 29.8 (#225)

| Benchmark | Claude 3.7 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| GPQA Diamond | 79.7% | 53.8% |
| Confabulations | 14.7% | 20.1% |
| LMArena Expert | 1321 | 1254 |
| Humanity's Last Exam | 8% | — |
| MMLU-Pro | 78.4% | — |
| GPQA (HELM) | 60.8% | — |

## Multimodal

- Claude 3.7 Sonnet: 33.1 (#90)
- Grok-2 (Dec 2024): —

| Benchmark | Claude 3.7 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |

## Multilingual

- Claude 3.7 Sonnet: 44.3 (#174)
- Grok-2 (Dec 2024): 43.3 (#183)

| Benchmark | Claude 3.7 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Non-English | 1296 | 1282 |
| LMArena Chinese | 1299 | 1289 |
| LMArena French | 1302 | 1317 |
| LMArena German | 1301 | 1287 |
| LMArena Japanese | 1268 | 1244 |
| LMArena Korean | 1249 | 1237 |
| LMArena Russian | 1311 | 1286 |
| LMArena Spanish | 1299 | 1281 |

## Instruction Following

- Claude 3.7 Sonnet: 73.1 (#120)
- Grok-2 (Dec 2024): 67.1 (#197)

| Benchmark | Claude 3.7 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| LiveBench Instruction Following | 81.3% | 69.6% |
| LMArena Instruction Following | 1352 | 1270 |
| IFEval | 83.4% | — |

## Long Context

- Claude 3.7 Sonnet: 50.2 (#10)
- Grok-2 (Dec 2024): 38.7 (#186)

| Benchmark | Claude 3.7 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Longer Query | 1373 | 1276 |
| Fiction.LiveBench | 83.3% | — |

## Writing & Preference

- Claude 3.7 Sonnet: 54.6 (#145)
- Grok-2 (Dec 2024): 48.8 (#192)

| Benchmark | Claude 3.7 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Text | 1314 | 1305 |
| LMArena Creative Writing | 1332 | 1284 |
| Short-Story Creative Writing | 81.1% | 63.6% |
| LMArena Multi-Turn | 1339 | 1290 |
| LiveBench Language | 59.9% | 45.6% |
| EQ-Bench Creative Writing | 1412 | — |
| WildBench | 81.4% | — |

## FAQ

### Is Claude 3.7 Sonnet better than Grok-2 (Dec 2024)?

Claude 3.7 Sonnet is the stronger model overall, scoring 39.4 to 33.4 on the Noometry Index.

### Is Claude 3.7 Sonnet or Grok-2 (Dec 2024) better for coding?

Claude 3.7 Sonnet scores higher on coding benchmarks: 41.1 versus 32.9 in the Noometry coding category.

### How many benchmarks do Claude 3.7 Sonnet and Grok-2 (Dec 2024) share?

32 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Grok-2 (Dec 2024) has 34.