Compare / GPT-5.4 Mini vs GPT-5.6 Sol
GPT-5.4 Mini vs GPT-5.6 Sol
22 results from 4 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | GPT-5.4 Mini | GPT-5.6 Sol |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,447 | 1,476 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,460 | 1,485 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,402 | 1,470 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,480 | 1,534 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,434 | 1,489 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,447 | 1,483 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,424 | 1,483 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 56.1 | 78.3 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 24.1 | 47.0 |
| Artificial Analysisreported | GPQA Diamond% of questions | 87.5% | 94.1% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 28.1% | 49.5% |
| Artificial Analysisreported | IFBench% of instructions | 73.3% | 72.7% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 77.0% | 84.0% |
| Artificial Analysisreported | SciCode% of problems | 52.1% | 57.8% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 59.2% | 89.5% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 2.0% | 39.9% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 52.3% | 65.9% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 25.6% | 44.3% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 83.3% | 85.1% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 29.4% | 69.7% |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 100.0% | 99.1% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 5.5% | 12.4% |
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.