Compare / Claude Sonnet 5 vs GPT-5.4 Mini
Claude Sonnet 5 vs GPT-5.4 Mini
17 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Claude Sonnet 5 | GPT-5.4 Mini |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,452 | 1,447 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,465 | 1,460 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,435 | 1,402 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,512 | 1,480 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,467 | 1,434 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,462 | 1,447 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,452 | 1,424 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 71.5 | 56.1 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 38.2 | 24.1 |
| Artificial Analysisreported | GPQA Diamond% of questions | 91.1% | 87.5% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 41.3% | 28.1% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 82.0% | 77.0% |
| Artificial Analysisreported | SciCode% of problems | 54.3% | 52.1% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 80.5% | 59.2% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 14.1% | 2.0% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 37.3% | 25.6% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 33.7% | 29.4% |
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.