Model comparison
Claude Sonnet 4 vs Grok-2 (Dec 2024)
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 33.7 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. Claude Sonnet 4 scores higher in 7 categories and Grok-2 (Dec 2024) in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 4 leads 43.3 to 20.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 71.1% for Claude Sonnet 4 and 11.5% for Grok-2 (Dec 2024).
Side by side
| Claude Sonnet 4 | Grok-2 (Dec 2024) | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 40.8 | 33.7 |
| Released | 2025-05-22 | 2024-08-13 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $3 | — |
| Output $ / M tokens | $15 | — |
| Results tracked | 58 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 43.5 (#88), Grok-2 (Dec 2024): 33.3 (#258)
| Benchmark | Claude Sonnet 4 | Grok-2 (Dec 2024) |
|---|---|---|
| WeirdML | 46.1% | 22.2% |
| LMArena Coding | 1414 | 1287 |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| SciCode | 40% | — |
| GSO | 4.9% | — |
| LiveBench Coding | — | 46.4% |
| ALE-Bench | 655.35 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4: 38.5 (#31), Grok-2 (Dec 2024): —
| Benchmark | Claude Sonnet 4 | Grok-2 (Dec 2024) |
|---|---|---|
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Claude Sonnet 4 leads
Claude Sonnet 4: 22.9 (#187), Grok-2 (Dec 2024): 16.9 (#299)
| Benchmark | Claude Sonnet 4 | Grok-2 (Dec 2024) |
|---|---|---|
| SimpleBench | 45.5% | 22.7% |
| LMArena Hard Prompts | 1372 | 1272 |
| DTBench | 77.1% | 65.2% |
| Epoch Capabilities Index | 141.69 | 130.48 |
| ARC-AGI-2 | 5.9% | — |
| Kagi LLM Benchmark | 73% | — |
| ARC-AGI-1 | 40% | — |
| CritPt | 0.3% | — |
| EnigmaEval | 3.1% | — |
| LiveBench Reasoning | — | 54.8% |
| LiveBench Data Analysis | — | 54.5% |
| LMCA | 29% | — |
| ForecastBench | 60.2 | — |
| LiveBench | — | 54.3% |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 43.3 (#80), Grok-2 (Dec 2024): 20.8 (#284)
| Benchmark | Claude Sonnet 4 | Grok-2 (Dec 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 11.5% |
| LMArena Math | 1375 | 1283 |
| MATH Level 5 | 84.4% | 63.5% |
| FrontierMath (Feb 2025 set) | 4.1% | 0.7% |
| Omni-MATH | 60.2% | — |
| LiveBench Math | — | 54.9% |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.8 (#108), Grok-2 (Dec 2024): 29.8 (#233)
| Benchmark | Claude Sonnet 4 | Grok-2 (Dec 2024) |
|---|---|---|
| GPQA Diamond | 79.2% | 53.8% |
| Confabulations | 13.2% | 20.1% |
| LMArena Expert | 1372 | 1254 |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Vectara Hallucination Rate | 10.3% | — |
| GPQA (HELM) | 70.6% | — |
Multimodal Not comparable
Claude Sonnet 4: 26.2 (#121), Grok-2 (Dec 2024): —
| Benchmark | Claude Sonnet 4 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Claude Sonnet 4 leads
Claude Sonnet 4: 46.7 (#156), Grok-2 (Dec 2024): 43.1 (#188)
| Benchmark | Claude Sonnet 4 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Non-English | 1333 | 1282 |
| LMArena Chinese | 1350 | 1289 |
| LMArena French | 1363 | 1318 |
| LMArena German | 1331 | 1287 |
| LMArena Japanese | 1302 | 1244 |
| LMArena Korean | 1291 | 1237 |
| LMArena Russian | 1355 | 1286 |
| LMArena Spanish | 1357 | 1281 |
Instruction Following Claude Sonnet 4 leads
Claude Sonnet 4: 71.7 (#145), Grok-2 (Dec 2024): 66.9 (#202)
| Benchmark | Claude Sonnet 4 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Instruction Following | 1376 | 1270 |
| LiveBench Instruction Following | — | 69.6% |
| IFEval | 84% | — |
Long Context Grok-2 (Dec 2024) leads
Claude Sonnet 4: 33.7 (#259), Grok-2 (Dec 2024): 38.8 (#190)
| Benchmark | Claude Sonnet 4 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Longer Query | 1398 | 1276 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference Claude Sonnet 4 leads
Claude Sonnet 4: 57.1 (#132), Grok-2 (Dec 2024): 48.6 (#198)
| Benchmark | Claude Sonnet 4 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Text | 1351 | 1305 |
| LMArena Creative Writing | 1345 | 1284 |
| Short-Story Creative Writing | 81.4% | 63.6% |
| LMArena Multi-Turn | 1376 | 1290 |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |
| LiveBench Language | — | 45.6% |
Frequently asked questions
Is Claude Sonnet 4 better than Grok-2 (Dec 2024)?
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 33.7 on the Noometry Index.
Is Claude Sonnet 4 or Grok-2 (Dec 2024) better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 33.3 in the Noometry coding category.
How many benchmarks do Claude Sonnet 4 and Grok-2 (Dec 2024) share?
27 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Grok-2 (Dec 2024) has 34.