Model comparison
Claude Sonnet 4.5 vs Grok 3
Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 39.9 on the Noometry Index.
Last verified . 35 shared benchmarks.
Summary
- They share 35 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 7 categories and Grok 3 in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Sonnet 4.5 leads 26.9 to 13.7.
- The biggest single-benchmark swing is ARC-AGI-1: 63.7% for Claude Sonnet 4.5 and 5.5% for Grok 3.
Side by side
| Claude Sonnet 4.5 | Grok 3 | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 44.1 | 39.9 |
| Released | 2025-09-29 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $3 | — |
| Output $ / M tokens | $15 | — |
| Results tracked | 73 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 47.3 (#61), Grok 3: 41.9 (#115)
| Benchmark | Claude Sonnet 4.5 | Grok 3 |
|---|---|---|
| WeirdML | 47.7% | 37.2% |
| LMArena Coding | 1489 | 1432 |
| SWE-bench Verified | 71.3% | — |
| SWE-bench Verified (bash only) | 71.4% | — |
| Aider Polyglot | — | 53.3% |
| LMArena WebDev | 1393 | — |
| SWE-bench Multilingual | 67% | — |
| SciCode | 44.7% | — |
| GSO | 14.7% | — |
| ALE-Bench | 796.15 | — |
| AlgoTune | 1.52 | — |
Agentic & Tool Use Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 38.3 (#32), Grok 3: 30.5 (#76)
| Benchmark | Claude Sonnet 4.5 | Grok 3 |
|---|---|---|
| Terminal-Bench | 46.5% | — |
| Berkeley Function Calling Leaderboard | 73.2% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| τ²-bench Airline | 72% | — |
| τ²-bench Banking | 25.3% | — |
| τ²-bench Retail | 72.4% | — |
| τ²-bench Telecom | 84.9% | — |
| Cybench | 60% | — |
| DeepResearch Bench | 52.6% | — |
| OSWorld | 62.9% | — |
| BALROG | — | 29.5% |
| LMArena Search | 1159 | — |
| METR Time Horizons | 67.4% | — |
| Vending-Bench 2 | 3,839 | — |
Reasoning Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 26.9 (#125), Grok 3: 13.7 (#333)
| Benchmark | Claude Sonnet 4.5 | Grok 3 |
|---|---|---|
| ARC-AGI-2 | 13.6% | 0% |
| SimpleBench | 54.3% | 36.1% |
| Kagi LLM Benchmark | 57.9% | 61.3% |
| ARC-AGI-1 | 63.7% | 5.5% |
| LMArena Hard Prompts | 1462 | 1434 |
| Epoch Capabilities Index | 146.84 | 138.33 |
| NYT Connections (extended) | 37.3% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 6% | — |
| EBR-Bench | 2.4% | — |
| Mystery Game Puzzles | 17% | — |
| DTBench | 83.2% | — |
| LMCA | 38.8% | — |
| ForecastBench | 61.9 | — |
Math Grok 3 leads
Claude Sonnet 4.5: 32.3 (#216), Grok 3: 38.0 (#145)
| Benchmark | Claude Sonnet 4.5 | Grok 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 55.6% |
| Omni-MATH | 55.3% | 46.4% |
| LMArena Math | 1449 | 1391 |
| MATH Level 5 | 97.7% | 88.7% |
| FrontierMath (Feb 2025 set) | 15.2% | 3.8% |
| FrontierMath Tier 4 (v1) | 4.2% | 0% |
| FrontierMath (Tiers 1-3) | 23.9% | — |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | 19% | — |
Knowledge Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 48.4 (#76), Grok 3: 46.2 (#82)
| Benchmark | Claude Sonnet 4.5 | Grok 3 |
|---|---|---|
| GPQA Diamond | 82.3% | 75.8% |
| MMLU-Pro | 86.9% | 78.8% |
| Vectara Hallucination Rate | 12% | 5.8% |
| GPQA (HELM) | 68.6% | 65% |
| LMArena Expert | 1482 | 1421 |
| Humanity's Last Exam | 13.7% | — |
| SimpleQA Verified | 30.7% | — |
| Confabulations | — | 14.2% |
Multimodal Not comparable
Claude Sonnet 4.5: 34.8 (#89), Grok 3: —
| Benchmark | Claude Sonnet 4.5 | Grok 3 |
|---|---|---|
| VPCT | 39.8% | — |
| LMArena Document | 1450 | — |
Multilingual Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 53.4 (#69), Grok 3: 52.3 (#87)
| Benchmark | Claude Sonnet 4.5 | Grok 3 |
|---|---|---|
| LMArena Non-English | 1425 | 1410 |
| LMArena Chinese | 1459 | 1448 |
| LMArena French | 1458 | 1460 |
| LMArena German | 1427 | 1431 |
| LMArena Japanese | 1390 | 1387 |
| LMArena Korean | 1403 | 1373 |
| LMArena Russian | 1437 | 1416 |
| LMArena Spanish | 1457 | 1417 |
Instruction Following Too close to call
Claude Sonnet 4.5: 75.0 (#78), Grok 3: 75.0 (#73)
| Benchmark | Claude Sonnet 4.5 | Grok 3 |
|---|---|---|
| IFEval | 85% | 88.4% |
| LMArena Instruction Following | 1459 | 1409 |
Long Context Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 45.2 (#46), Grok 3: 38.7 (#192)
| Benchmark | Claude Sonnet 4.5 | Grok 3 |
|---|---|---|
| LMArena Longer Query | 1476 | 1439 |
| Fiction.LiveBench | — | 58.3% |
Writing & Preference Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 66.5 (#34), Grok 3: 55.8 (#141)
| Benchmark | Claude Sonnet 4.5 | Grok 3 |
|---|---|---|
| LMArena Text | 1439 | 1426 |
| LMArena Creative Writing | 1442 | 1414 |
| EQ-Bench Creative Writing | 1678 | 1186 |
| WildBench | 85.4% | 84.9% |
| LMArena Multi-Turn | 1465 | 1425 |
| Short-Story Creative Writing | — | 76.4% |
Frequently asked questions
Is Claude Sonnet 4.5 better than Grok 3?
Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 39.9 on the Noometry Index.
Is Claude Sonnet 4.5 or Grok 3 better for coding?
Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 41.9 in the Noometry coding category.
How many benchmarks do Claude Sonnet 4.5 and Grok 3 share?
35 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Grok 3 has 40.