Compare / Claude Opus 5 vs GPT-5.4 Mini
Claude Opus 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 Opus 5 | GPT-5.4 Mini |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,488 | 1,447 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,486 | 1,460 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,472 | 1,402 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,543 | 1,480 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,497 | 1,434 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,491 | 1,447 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,482 | 1,424 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 78.0 | 56.1 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 50.8 | 24.1 |
| Artificial Analysisreported | GPQA Diamond% of questions | 93.7% | 87.5% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 54.9% | 28.1% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 82.0% | 77.0% |
| Artificial Analysisreported | SciCode% of problems | 56.4% | 52.1% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 89.1% | 59.2% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 49.0% | 2.0% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 44.7% | 25.6% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 59.9% | 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.