Model comparison
Claude 3.5 Sonnet vs Grok 4
Grok 4 is the stronger model overall, scoring 47.8 to 34.4 on the Noometry Index.
Last verified . 38 shared benchmarks.
Summary
- They share 38 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 1 category and Grok 4 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4 leads 46.5 to 18.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 84% for Grok 4.
Side by side
| Claude 3.5 Sonnet | Grok 4 | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 34.4 | 47.8 |
| Released | 2024-06-20 | 2025-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 60 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4 leads
Claude 3.5 Sonnet: 39.5 (#145), Grok 4: 49.9 (#44)
| Benchmark | Claude 3.5 Sonnet | Grok 4 |
|---|---|---|
| Aider Polyglot | 51.6% | 79.6% |
| WeirdML | 40% | 45.7% |
| LMArena Coding | 1343 | 1408 |
| 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 Too close to call
Claude 3.5 Sonnet: 32.1 (#61), Grok 4: 32.1 (#62)
| Benchmark | Claude 3.5 Sonnet | Grok 4 |
|---|---|---|
| Cybench | 17.5% | 43% |
| BALROG | 32.6% | 43.6% |
| METR Time Horizons | 45.2% | 66.6% |
| Terminal-Bench | — | 27.2% |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 21.1% |
| TheAgentCompany | 24% | — |
| DeepResearch Bench | — | 47.3% |
| LMArena Search | — | 1142 |
Reasoning Grok 4 leads
Claude 3.5 Sonnet: 22.5 (#176), Grok 4: 36.9 (#59)
| Benchmark | Claude 3.5 Sonnet | Grok 4 |
|---|---|---|
| SimpleBench | 41.4% | 60.5% |
| LMArena Hard Prompts | 1305 | 1409 |
| Epoch Capabilities Index | 133.55 | 146.46 |
| ForecastBench | 60.7 | 60.9 |
| ARC-AGI-2 | — | 16% |
| Kagi LLM Benchmark | — | 73.6% |
| ARC-AGI-1 | — | 66.7% |
| Chess Puzzles | — | 28% |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| DTBench | 67.8% | — |
| LiveBench Data Analysis | 55% | — |
| LiveBench | 59% | — |
Math Grok 4 leads
Claude 3.5 Sonnet: 18.0 (#282), Grok 4: 46.5 (#58)
| Benchmark | Claude 3.5 Sonnet | Grok 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 84% |
| Omni-MATH | 27.6% | 60.3% |
| LMArena Math | 1306 | 1422 |
| FrontierMath (Feb 2025 set) | 2.1% | 19.7% |
| FrontierMath Tier 4 (v1) | 0% | 2.1% |
| LiveBench Math | 52.3% | — |
| MATH Level 5 | 56.9% | — |
Knowledge Grok 4 leads
Claude 3.5 Sonnet: 28.5 (#236), Grok 4: 53.7 (#50)
| Benchmark | Claude 3.5 Sonnet | Grok 4 |
|---|---|---|
| GPQA Diamond | 55.3% | 87% |
| MMLU-Pro | 77.7% | 85.1% |
| Confabulations | 19.9% | 12.4% |
| GPQA (HELM) | 56.5% | 72.7% |
| LMArena Expert | 1264 | 1417 |
| Humanity's Last Exam | 4.1% | — |
| MMLU | 87.3% | — |
Multimodal Grok 4 leads
Claude 3.5 Sonnet: 26.0 (#115), Grok 4: 33.1 (#89)
| Benchmark | Claude 3.5 Sonnet | Grok 4 |
|---|---|---|
| LMArena Vision | 1125 | 1211 |
| GeoBench | 62% | 45% |
| Video-MME | 60% | — |
| VPCT | 33% | — |
Multilingual Grok 4 leads
Claude 3.5 Sonnet: 43.4 (#180), Grok 4: 52.0 (#98)
| Benchmark | Claude 3.5 Sonnet | Grok 4 |
|---|---|---|
| LMArena Non-English | 1283 | 1403 |
| LMArena Chinese | 1271 | 1428 |
| LMArena French | 1304 | 1418 |
| LMArena German | 1297 | 1429 |
| LMArena Japanese | 1234 | 1396 |
| LMArena Korean | 1200 | 1376 |
| LMArena Russian | 1305 | 1409 |
| LMArena Spanish | 1289 | 1419 |
Instruction Following Grok 4 leads
Claude 3.5 Sonnet: 69.0 (#177), Grok 4: 79.4 (#4)
| Benchmark | Claude 3.5 Sonnet | Grok 4 |
|---|---|---|
| IFEval | 85.5% | 94.9% |
| LMArena Instruction Following | 1297 | 1387 |
| LiveBench Instruction Following | 69.3% | — |
Long Context Grok 4 leads
Claude 3.5 Sonnet: 39.9 (#162), Grok 4: 63.1 (#4)
| Benchmark | Claude 3.5 Sonnet | Grok 4 |
|---|---|---|
| LMArena Longer Query | 1311 | 1409 |
| Fiction.LiveBench | — | 94.4% |
Writing & Preference Grok 4 leads
Claude 3.5 Sonnet: 53.0 (#159), Grok 4: 58.7 (#111)
| Benchmark | Claude 3.5 Sonnet | Grok 4 |
|---|---|---|
| LMArena Text | 1298 | 1412 |
| LMArena Creative Writing | 1292 | 1397 |
| Short-Story Creative Writing | 80.3% | 76.9% |
| WildBench | 79.2% | 79.7% |
| LMArena Multi-Turn | 1326 | 1416 |
| EQ-Bench Creative Writing | 1451 | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Grok 4?
Grok 4 is the stronger model overall, scoring 47.8 to 34.4 on the Noometry Index.
Is Claude 3.5 Sonnet or Grok 4 better for coding?
Grok 4 scores higher on coding benchmarks: 49.9 versus 39.5 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Grok 4 share?
38 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Grok 4 has 48.