Compare / Claude Sonnet 4.6 vs Grok 4.6
Claude Sonnet 4.6 vs Grok 4.6
24 results from 7 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Claude Sonnet 4.6 | Grok 4.6 |
|---|---|---|---|
| APEX-Agentsreported | Tasks passed% of tasks | 43.0% | 65.3% |
| Arena (formerly LMArena)reported | OverallArena rating | 1,478 | 1,461 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,461 | 1,449 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,482 | 1,447 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,449 | 1,445 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,506 | 1,490 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,475 | 1,451 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,472 | 1,453 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,455 | 1,446 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 63.0 | 76.8 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 30.1 | 44.3 |
| Artificial Analysisreported | GPQA Diamond% of questions | 87.5% | 94.9% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 33.6% | 44.1% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 80.0% | 81.0% |
| Artificial Analysisreported | SciCode% of problems | 50.1% | 56.5% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 71.2% | 88.4% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 3.0% | 21.2% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 34.4% | 50.7% |
| GDP.pdfreported | Professional document tasks% of rubric | 18.0% | 17.2% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 35.5% | 49.3% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 2.0% | 25.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.41 | 0.36 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 64.5 | 63.3 |
| Vending-Bench 2reported | Money after a yearUS dollars | $7,204.14 | $9,047.03 |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.