Model comparison
Claude 3.7 Sonnet vs Grok 4.6
Grok 4.6 is the stronger model overall, scoring 56.8 to 39.4 on the Noometry Index.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 1 category and Grok 4.6 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.6 leads 61.3 to 18.7.
- The biggest single-benchmark swing is ARC-AGI-2: 0.9% for Claude 3.7 Sonnet and 67.1% for Grok 4.6.
Side by side
| Claude 3.7 Sonnet | Grok 4.6 | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 39.4 | 56.8 |
| Released | 2025-02-24 | 2026-08-12 |
| Weights | Proprietary | Proprietary |
| Context window | — | 500K |
| Max output | — | 500K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 58 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.6 leads
Claude 3.7 Sonnet: 41.1 (#120), Grok 4.6: 58.0 (#14)
| Benchmark | Claude 3.7 Sonnet | Grok 4.6 |
|---|---|---|
| LMArena Coding | 1361 | 1464 |
| SWE-bench Verified | 61% | — |
| DeepSWE | — | 67.5% |
| FrontierCode | — | 48% |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| CursorBench | — | 41.4% |
| LMArena WebDev | — | 1620 |
| FrontierSWE | — | 25.3% |
| SciCode | — | 56.5% |
| GSO | 3.8% | — |
| WeirdML | — | 67.3% |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
| ALE-Bench | — | 1,508 |
Agentic & Tool Use Grok 4.6 leads
Claude 3.7 Sonnet: 33.9 (#46), Grok 4.6: 39.4 (#25)
| Benchmark | Claude 3.7 Sonnet | Grok 4.6 |
|---|---|---|
| APEX-Agents | — | 65.3% |
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| GDP.pdf | — | 17.2% |
| METR Time Horizons | 60% | — |
| Vending-Bench 2 | — | 9,047 |
Reasoning Grok 4.6 leads
Claude 3.7 Sonnet: 18.7 (#252), Grok 4.6: 61.3 (#18)
| Benchmark | Claude 3.7 Sonnet | Grok 4.6 |
|---|---|---|
| ARC-AGI-2 | 0.9% | 67.1% |
| SimpleBench | 46.4% | 75.9% |
| ARC-AGI-1 | 28.6% | 87.5% |
| LMArena Hard Prompts | 1333 | 1445 |
| Epoch Capabilities Index | 141.16 | 156.48 |
| NYT Connections (extended) | — | 80% |
| CritPt | — | 19.7% |
| Chess Puzzles | — | 40% |
| EnigmaEval | 4.2% | — |
| EBR-Bench | — | 30.5% |
| LiveBench Reasoning | 87.8% | — |
| Mystery Game Puzzles | — | 34% |
| DTBench | — | 97.3% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 48.5% |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |
Math Grok 4.6 leads
Claude 3.7 Sonnet: 35.7 (#137), Grok 4.6: 66.8 (#19)
| Benchmark | Claude 3.7 Sonnet | Grok 4.6 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 99.2% |
| LMArena Math | 1336 | 1416 |
| FrontierMath (Tiers 1-3) | — | 66% |
| FrontierMath Tier 4 | — | 31.7% |
| ProofBench | — | 51% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge Grok 4.6 leads
Claude 3.7 Sonnet: 39.7 (#117), Grok 4.6: 63.3 (#18)
| Benchmark | Claude 3.7 Sonnet | Grok 4.6 |
|---|---|---|
| GPQA Diamond | 79.7% | 94% |
| LMArena Expert | 1321 | 1463 |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | — | 49.3% |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| GPQA (HELM) | 60.8% | — |
Multimodal Grok 4.6 leads
Claude 3.7 Sonnet: 33.1 (#90), Grok 4.6: 43.9 (#18)
| Benchmark | Claude 3.7 Sonnet | Grok 4.6 |
|---|---|---|
| LMArena Vision | 1169 | 1265 |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| Blueprint-Bench 2 | — | 33.2% |
| Furniture Assembly | — | 40% |
| LMArena Document | — | 1452 |
| SpatialViz-Bench | 33.9% | — |
Multilingual Grok 4.6 leads
Claude 3.7 Sonnet: 44.3 (#174), Grok 4.6: 53.3 (#67)
| Benchmark | Claude 3.7 Sonnet | Grok 4.6 |
|---|---|---|
| LMArena Non-English | 1296 | 1422 |
| LMArena Chinese | 1299 | 1479 |
| LMArena French | 1302 | 1458 |
| LMArena German | 1301 | 1425 |
| LMArena Japanese | 1268 | 1383 |
| LMArena Korean | 1249 | 1395 |
| LMArena Russian | 1311 | 1427 |
| LMArena Spanish | 1299 | 1408 |
Instruction Following Grok 4.6 leads
Claude 3.7 Sonnet: 73.1 (#120), Grok 4.6: 75.6 (#59)
| Benchmark | Claude 3.7 Sonnet | Grok 4.6 |
|---|---|---|
| LMArena Instruction Following | 1352 | 1431 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.2 (#10), Grok 4.6: 44.4 (#62)
| Benchmark | Claude 3.7 Sonnet | Grok 4.6 |
|---|---|---|
| LMArena Longer Query | 1373 | 1453 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference Grok 4.6 leads
Claude 3.7 Sonnet: 54.6 (#145), Grok 4.6: 62.5 (#77)
| Benchmark | Claude 3.7 Sonnet | Grok 4.6 |
|---|---|---|
| LMArena Text | 1314 | 1427 |
| LMArena Creative Writing | 1332 | 1430 |
| LMArena Multi-Turn | 1339 | 1422 |
| Short-Story Creative Writing | 81.1% | — |
| EQ-Bench Creative Writing | 1412 | — |
| WildBench | 81.4% | — |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Grok 4.6?
Grok 4.6 is the stronger model overall, scoring 56.8 to 39.4 on the Noometry Index.
Is Claude 3.7 Sonnet or Grok 4.6 better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.0 versus 41.1 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Grok 4.6 share?
24 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Grok 4.6 has 49.