Model comparison
Claude 3.7 Sonnet vs Grok 4.1 Fast
Grok 4.1 Fast is the stronger model overall, scoring 40.9 to 39.4 on the Noometry Index.
Last verified . 21 shared benchmarks.
Summary
- They share 21 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 5 categories and Grok 4.1 Fast in 5 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.1 Fast leads 42.3 to 18.7.
- The biggest single-benchmark swing is SimpleBench: 46.4% for Claude 3.7 Sonnet and 56% for Grok 4.1 Fast.
Side by side
| Claude 3.7 Sonnet | Grok 4.1 Fast | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 39.4 | 40.9 |
| Released | 2025-02-24 | 2025-06-27 |
| Weights | Proprietary | Proprietary |
| Context window | — | 128K |
| Max output | — | 30K |
| Input $ / M tokens | — | $0.20 |
| Output $ / M tokens | — | $0.50 |
| Results tracked | 58 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 41.1 (#120), Grok 4.1 Fast: 33.8 (#236)
| Benchmark | Claude 3.7 Sonnet | Grok 4.1 Fast |
|---|---|---|
| LMArena Coding | 1361 | 1411 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| LMArena WebDev | — | 1241 |
| GSO | 3.8% | — |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
| ALE-Bench | — | 394.93 |
Agentic & Tool Use Grok 4.1 Fast leads
Claude 3.7 Sonnet: 33.9 (#46), Grok 4.1 Fast: 36.1 (#35)
| Benchmark | Claude 3.7 Sonnet | Grok 4.1 Fast |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 69.6% |
| TheAgentCompany | 30.9% | — |
| τ²-bench Banking | — | 13.1% |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| LMArena Search | — | 1171 |
| METR Time Horizons | 60% | — |
| Vending-Bench 2 | — | 1,107 |
Reasoning Grok 4.1 Fast leads
Claude 3.7 Sonnet: 18.7 (#252), Grok 4.1 Fast: 42.3 (#45)
| Benchmark | Claude 3.7 Sonnet | Grok 4.1 Fast |
|---|---|---|
| SimpleBench | 46.4% | 56% |
| LMArena Hard Prompts | 1333 | 1407 |
| ForecastBench | 61.8 | 61 |
| ARC-AGI-2 | 0.9% | — |
| NYT Connections (extended) | — | 87.4% |
| ARC-AGI-1 | 28.6% | — |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| DTBench | — | 87.7% |
| LiveBench Data Analysis | 74% | — |
| Epoch Capabilities Index | 141.16 | — |
| LiveBench | 76.1% | — |
Math Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 35.7 (#137), Grok 4.1 Fast: 30.9 (#201)
| Benchmark | Claude 3.7 Sonnet | Grok 4.1 Fast |
|---|---|---|
| LMArena Math | 1336 | 1408 |
| MathArena Final-Answer Competitions | — | 60.9% |
| OTIS Mock AIME 2024-2025 | 57.8% | — |
| ProofBench | — | 4% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 39.7 (#117), Grok 4.1 Fast: 32.6 (#203)
| Benchmark | Claude 3.7 Sonnet | Grok 4.1 Fast |
|---|---|---|
| LMArena Expert | 1321 | 1398 |
| GPQA Diamond | 79.7% | — |
| Humanity's Last Exam | 8% | — |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| Vectara Hallucination Rate | — | 17.8% |
| GPQA (HELM) | 60.8% | — |
Multimodal Grok 4.1 Fast leads
Claude 3.7 Sonnet: 33.1 (#90), Grok 4.1 Fast: 36.3 (#71)
| Benchmark | Claude 3.7 Sonnet | Grok 4.1 Fast |
|---|---|---|
| LMArena Vision | 1169 | 1201 |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual Grok 4.1 Fast leads
Claude 3.7 Sonnet: 44.3 (#174), Grok 4.1 Fast: 51.1 (#110)
| Benchmark | Claude 3.7 Sonnet | Grok 4.1 Fast |
|---|---|---|
| LMArena Non-English | 1296 | 1391 |
| LMArena Chinese | 1299 | 1441 |
| LMArena French | 1302 | 1416 |
| LMArena German | 1301 | 1404 |
| LMArena Japanese | 1268 | 1347 |
| LMArena Korean | 1249 | 1361 |
| LMArena Russian | 1311 | 1387 |
| LMArena Spanish | 1299 | 1411 |
Instruction Following Too close to call
Claude 3.7 Sonnet: 73.1 (#120), Grok 4.1 Fast: 72.8 (#127)
| Benchmark | Claude 3.7 Sonnet | Grok 4.1 Fast |
|---|---|---|
| LMArena Instruction Following | 1352 | 1376 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.2 (#10), Grok 4.1 Fast: 42.4 (#121)
| Benchmark | Claude 3.7 Sonnet | Grok 4.1 Fast |
|---|---|---|
| LMArena Longer Query | 1373 | 1390 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference Grok 4.1 Fast leads
Claude 3.7 Sonnet: 54.6 (#145), Grok 4.1 Fast: 57.4 (#126)
| Benchmark | Claude 3.7 Sonnet | Grok 4.1 Fast |
|---|---|---|
| LMArena Text | 1314 | 1408 |
| LMArena Creative Writing | 1332 | 1394 |
| EQ-Bench Creative Writing | 1412 | 1327 |
| LMArena Multi-Turn | 1339 | 1389 |
| Short-Story Creative Writing | 81.1% | — |
| WildBench | 81.4% | — |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Grok 4.1 Fast?
Grok 4.1 Fast is the stronger model overall, scoring 40.9 to 39.4 on the Noometry Index.
Is Claude 3.7 Sonnet or Grok 4.1 Fast better for coding?
Claude 3.7 Sonnet scores higher on coding benchmarks: 41.1 versus 33.8 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Grok 4.1 Fast share?
21 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Grok 4.1 Fast has 32.