Model comparison
Claude 3.7 Sonnet vs Grok 4.3
Grok 4.3 is the stronger model overall, scoring 43.6 to 39.4 on the Noometry Index.
Last verified . 22 shared benchmarks.
Summary
- They share 22 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 4 categories and Grok 4.3 in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.3 leads 34.9 to 18.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Claude 3.7 Sonnet and 93.3% for Grok 4.3.
Side by side
| Claude 3.7 Sonnet | Grok 4.3 | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 39.4 | 43.6 |
| Released | 2025-02-24 | 2026-04-17 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 30K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 58 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude 3.7 Sonnet: 41.1 (#120), Grok 4.3: 41.3 (#117)
| Benchmark | Claude 3.7 Sonnet | Grok 4.3 |
|---|---|---|
| LMArena Coding | 1361 | 1415 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| LMArena WebDev | — | 1357 |
| SciCode | — | 47.3% |
| GSO | 3.8% | — |
| WeirdML | — | 49.9% |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
| ALE-Bench | — | 944.17 |
Agentic & Tool Use Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 33.9 (#46), Grok 4.3: 27.6 (#93)
| Benchmark | Claude 3.7 Sonnet | Grok 4.3 |
|---|---|---|
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| GDP.pdf | — | 8% |
| LMArena Search | — | 1165 |
| METR Time Horizons | 60% | — |
| Vending-Bench 2 | — | 35.26 |
Reasoning Grok 4.3 leads
Claude 3.7 Sonnet: 18.7 (#252), Grok 4.3: 34.9 (#60)
| Benchmark | Claude 3.7 Sonnet | Grok 4.3 |
|---|---|---|
| LMArena Hard Prompts | 1333 | 1397 |
| Epoch Capabilities Index | 141.16 | 149.13 |
| ForecastBench | 61.8 | 60.3 |
| ARC-AGI-2 | 0.9% | — |
| SimpleBench | 46.4% | — |
| NYT Connections (extended) | — | 55.2% |
| ARC-AGI-1 | 28.6% | — |
| CritPt | — | 8% |
| Chess Puzzles | — | 25% |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| DTBench | — | 90.7% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 38.3% |
| LiveBench | 76.1% | — |
Math Grok 4.3 leads
Claude 3.7 Sonnet: 35.7 (#137), Grok 4.3: 45.8 (#60)
| Benchmark | Claude 3.7 Sonnet | Grok 4.3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 93.3% |
| LMArena Math | 1336 | 1388 |
| FrontierMath (Tiers 1-3) | — | 42.8% |
| FrontierMath Tier 4 | — | 14.6% |
| ProofBench | — | 11% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge Grok 4.3 leads
Claude 3.7 Sonnet: 39.7 (#117), Grok 4.3: 52.5 (#57)
| Benchmark | Claude 3.7 Sonnet | Grok 4.3 |
|---|---|---|
| GPQA Diamond | 79.7% | 88.8% |
| LMArena Expert | 1321 | 1385 |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | — | 33.2% |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| GPQA (HELM) | 60.8% | — |
Multimodal Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 33.1 (#90), Grok 4.3: 31.6 (#96)
| Benchmark | Claude 3.7 Sonnet | Grok 4.3 |
|---|---|---|
| LMArena Vision | 1169 | 1231 |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| Blueprint-Bench 2 | — | 0% |
| SpatialViz-Bench | 33.9% | — |
Multilingual Grok 4.3 leads
Claude 3.7 Sonnet: 44.3 (#174), Grok 4.3: 50.7 (#114)
| Benchmark | Claude 3.7 Sonnet | Grok 4.3 |
|---|---|---|
| LMArena Non-English | 1296 | 1385 |
| LMArena Chinese | 1299 | 1423 |
| LMArena French | 1302 | 1412 |
| LMArena German | 1301 | 1395 |
| LMArena Japanese | 1268 | 1379 |
| LMArena Korean | 1249 | 1357 |
| LMArena Russian | 1311 | 1399 |
| LMArena Spanish | 1299 | 1402 |
Instruction Following Too close to call
Claude 3.7 Sonnet: 73.1 (#120), Grok 4.3: 72.3 (#135)
| Benchmark | Claude 3.7 Sonnet | Grok 4.3 |
|---|---|---|
| LMArena Instruction Following | 1352 | 1366 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.2 (#10), Grok 4.3: 42.5 (#118)
| Benchmark | Claude 3.7 Sonnet | Grok 4.3 |
|---|---|---|
| LMArena Longer Query | 1373 | 1393 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference Grok 4.3 leads
Claude 3.7 Sonnet: 54.6 (#145), Grok 4.3: 58.6 (#112)
| Benchmark | Claude 3.7 Sonnet | Grok 4.3 |
|---|---|---|
| LMArena Text | 1314 | 1397 |
| LMArena Creative Writing | 1332 | 1380 |
| LMArena Multi-Turn | 1339 | 1406 |
| Short-Story Creative Writing | 81.1% | — |
| EQ-Bench Creative Writing | 1412 | — |
| WildBench | 81.4% | — |
| EQ-Bench 4 | — | 1075 |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Grok 4.3?
Grok 4.3 is the stronger model overall, scoring 43.6 to 39.4 on the Noometry Index.
Is Claude 3.7 Sonnet or Grok 4.3 better for coding?
They score almost the same on coding (41.1 vs 41.3); test both on your own repository before choosing.
How many benchmarks do Claude 3.7 Sonnet and Grok 4.3 share?
22 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Grok 4.3 has 40.