Model comparison
Claude 3.7 Sonnet vs Grok 3
Claude 3.7 Sonnet and Grok 3 score almost the same on the Noometry Index (39.5 vs 39.9), so choose on price, context window or the category you care about most.
Last verified . 35 shared benchmarks.
Summary
- They share 35 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 3 categories and Grok 3 in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Claude 3.7 Sonnet leads 50.3 to 38.7.
- The biggest single-benchmark swing is Fiction.LiveBench: 83.3% for Claude 3.7 Sonnet and 58.3% for Grok 3.
Side by side
| Claude 3.7 Sonnet | Grok 3 | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 39.5 | 39.9 |
| Released | 2025-02-24 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 58 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
Claude 3.7 Sonnet: 40.6 (#136), Grok 3: 41.9 (#115)
| Benchmark | Claude 3.7 Sonnet | Grok 3 |
|---|---|---|
| Aider Polyglot | 64.9% | 53.3% |
| LMArena Coding | 1361 | 1432 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| GSO | 3.8% | — |
| WeirdML | — | 37.2% |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
Agentic & Tool Use Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 34.1 (#50), Grok 3: 30.5 (#76)
| Benchmark | Claude 3.7 Sonnet | Grok 3 |
|---|---|---|
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| BALROG | — | 29.5% |
| METR Time Horizons | 60% | — |
Reasoning Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 18.6 (#277), Grok 3: 13.7 (#333)
| Benchmark | Claude 3.7 Sonnet | Grok 3 |
|---|---|---|
| ARC-AGI-2 | 0.9% | 0% |
| SimpleBench | 46.4% | 36.1% |
| ARC-AGI-1 | 28.6% | 5.5% |
| LMArena Hard Prompts | 1333 | 1434 |
| Epoch Capabilities Index | 141.16 | 138.33 |
| Kagi LLM Benchmark | — | 61.3% |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| LiveBench Data Analysis | 74% | — |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |
Math Too close to call
Claude 3.7 Sonnet: 37.5 (#153), Grok 3: 38.0 (#145)
| Benchmark | Claude 3.7 Sonnet | Grok 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 55.6% |
| Omni-MATH | 33% | 46.4% |
| LMArena Math | 1337 | 1391 |
| MATH Level 5 | 91.2% | 88.7% |
| FrontierMath (Feb 2025 set) | 4.1% | 3.8% |
| LiveBench Math | 79% | — |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Grok 3 leads
Claude 3.7 Sonnet: 39.8 (#130), Grok 3: 46.2 (#82)
| Benchmark | Claude 3.7 Sonnet | Grok 3 |
|---|---|---|
| GPQA Diamond | 79.7% | 75.8% |
| MMLU-Pro | 78.4% | 78.8% |
| Confabulations | 14.7% | 14.2% |
| GPQA (HELM) | 60.8% | 65% |
| LMArena Expert | 1321 | 1421 |
| Humanity's Last Exam | 8% | — |
| Vectara Hallucination Rate | — | 5.8% |
Multimodal Not comparable
Claude 3.7 Sonnet: 33.7 (#95), Grok 3: —
| Benchmark | Claude 3.7 Sonnet | Grok 3 |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual Grok 3 leads
Claude 3.7 Sonnet: 44.1 (#179), Grok 3: 52.3 (#87)
| Benchmark | Claude 3.7 Sonnet | Grok 3 |
|---|---|---|
| LMArena Non-English | 1296 | 1410 |
| LMArena Chinese | 1299 | 1448 |
| LMArena French | 1303 | 1460 |
| LMArena German | 1301 | 1431 |
| LMArena Japanese | 1267 | 1387 |
| LMArena Korean | 1249 | 1373 |
| LMArena Russian | 1311 | 1416 |
| LMArena Spanish | 1298 | 1417 |
Instruction Following Grok 3 leads
Claude 3.7 Sonnet: 72.9 (#125), Grok 3: 75.0 (#73)
| Benchmark | Claude 3.7 Sonnet | Grok 3 |
|---|---|---|
| IFEval | 83.4% | 88.4% |
| LMArena Instruction Following | 1352 | 1409 |
| LiveBench Instruction Following | 81.3% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.3 (#10), Grok 3: 38.7 (#192)
| Benchmark | Claude 3.7 Sonnet | Grok 3 |
|---|---|---|
| Fiction.LiveBench | 83.3% | 58.3% |
| LMArena Longer Query | 1373 | 1439 |
Writing & Preference Grok 3 leads
Claude 3.7 Sonnet: 54.4 (#150), Grok 3: 55.8 (#141)
| Benchmark | Claude 3.7 Sonnet | Grok 3 |
|---|---|---|
| LMArena Text | 1314 | 1426 |
| LMArena Creative Writing | 1332 | 1414 |
| Short-Story Creative Writing | 81.1% | 76.4% |
| EQ-Bench Creative Writing | 1412 | 1186 |
| WildBench | 81.4% | 84.9% |
| LMArena Multi-Turn | 1339 | 1425 |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Grok 3?
Claude 3.7 Sonnet and Grok 3 score almost the same on the Noometry Index (39.5 vs 39.9), so choose on price, context window or the category you care about most.
Is Claude 3.7 Sonnet or Grok 3 better for coding?
Grok 3 scores higher on coding benchmarks: 41.9 versus 40.6 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Grok 3 share?
35 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Grok 3 has 40.