Model comparison
Claude 3.5 Sonnet vs Grok 3
Grok 3 is the stronger model overall, scoring 39.9 to 34.6 on the Noometry Index.
Last verified . 35 shared benchmarks.
Summary
- They share 35 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 3 categories and Grok 3 in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 3 leads 38.0 to 19.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 55.6% for Grok 3.
Side by side
| Claude 3.5 Sonnet | Grok 3 | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 34.6 | 39.9 |
| Released | 2024-06-20 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 60 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
Claude 3.5 Sonnet: 39.0 (#165), Grok 3: 41.9 (#115)
| Benchmark | Claude 3.5 Sonnet | Grok 3 |
|---|---|---|
| Aider Polyglot | 51.6% | 53.3% |
| WeirdML | 40% | 37.2% |
| LMArena Coding | 1342 | 1432 |
| GSO | 4.6% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 32.3 (#67), Grok 3: 30.5 (#76)
| Benchmark | Claude 3.5 Sonnet | Grok 3 |
|---|---|---|
| BALROG | 32.6% | 29.5% |
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| METR Time Horizons | 45.2% | — |
Reasoning Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 23.1 (#183), Grok 3: 13.7 (#333)
| Benchmark | Claude 3.5 Sonnet | Grok 3 |
|---|---|---|
| SimpleBench | 41.4% | 36.1% |
| LMArena Hard Prompts | 1305 | 1434 |
| Epoch Capabilities Index | 133.55 | 138.33 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 61.3% |
| ARC-AGI-1 | — | 5.5% |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| DTBench | 67.8% | — |
| LiveBench Data Analysis | 55% | — |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
Math Grok 3 leads
Claude 3.5 Sonnet: 19.2 (#288), Grok 3: 38.0 (#145)
| Benchmark | Claude 3.5 Sonnet | Grok 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 55.6% |
| Omni-MATH | 27.6% | 46.4% |
| LMArena Math | 1307 | 1391 |
| MATH Level 5 | 56.9% | 88.7% |
| FrontierMath (Feb 2025 set) | 2.1% | 3.8% |
| FrontierMath Tier 4 (v1) | 0% | 0% |
| LiveBench Math | 52.3% | — |
Knowledge Grok 3 leads
Claude 3.5 Sonnet: 28.6 (#245), Grok 3: 46.2 (#82)
| Benchmark | Claude 3.5 Sonnet | Grok 3 |
|---|---|---|
| GPQA Diamond | 55.3% | 75.8% |
| MMLU-Pro | 77.7% | 78.8% |
| Confabulations | 19.9% | 14.2% |
| GPQA (HELM) | 56.5% | 65% |
| LMArena Expert | 1265 | 1421 |
| Humanity's Last Exam | 4.1% | — |
| Vectara Hallucination Rate | — | 5.8% |
| MMLU | 87.3% | — |
Multimodal Not comparable
Claude 3.5 Sonnet: 26.5 (#120), Grok 3: —
| Benchmark | Claude 3.5 Sonnet | Grok 3 |
|---|---|---|
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual Grok 3 leads
Claude 3.5 Sonnet: 43.2 (#185), Grok 3: 52.3 (#87)
| Benchmark | Claude 3.5 Sonnet | Grok 3 |
|---|---|---|
| LMArena Non-English | 1283 | 1410 |
| LMArena Chinese | 1272 | 1448 |
| LMArena French | 1305 | 1460 |
| LMArena German | 1297 | 1431 |
| LMArena Japanese | 1234 | 1387 |
| LMArena Korean | 1200 | 1373 |
| LMArena Russian | 1306 | 1416 |
| LMArena Spanish | 1290 | 1417 |
Instruction Following Grok 3 leads
Claude 3.5 Sonnet: 68.8 (#182), Grok 3: 75.0 (#73)
| Benchmark | Claude 3.5 Sonnet | Grok 3 |
|---|---|---|
| IFEval | 85.5% | 88.4% |
| LMArena Instruction Following | 1297 | 1409 |
| LiveBench Instruction Following | 69.3% | — |
Long Context Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.9 (#167), Grok 3: 38.7 (#192)
| Benchmark | Claude 3.5 Sonnet | Grok 3 |
|---|---|---|
| LMArena Longer Query | 1311 | 1439 |
| Fiction.LiveBench | — | 58.3% |
Writing & Preference Grok 3 leads
Claude 3.5 Sonnet: 52.9 (#164), Grok 3: 55.8 (#141)
| Benchmark | Claude 3.5 Sonnet | Grok 3 |
|---|---|---|
| LMArena Text | 1298 | 1426 |
| LMArena Creative Writing | 1292 | 1414 |
| Short-Story Creative Writing | 80.3% | 76.4% |
| EQ-Bench Creative Writing | 1451 | 1186 |
| WildBench | 79.2% | 84.9% |
| LMArena Multi-Turn | 1326 | 1425 |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Grok 3?
Grok 3 is the stronger model overall, scoring 39.9 to 34.6 on the Noometry Index.
Is Claude 3.5 Sonnet or Grok 3 better for coding?
Grok 3 scores higher on coding benchmarks: 41.9 versus 39.0 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Grok 3 share?
35 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Grok 3 has 40.