Compare / DeepSeek V3.2 Exp vs GPT-6 Sol
DeepSeek V3.2 Exp vs GPT-6 Sol
13 results from 4 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | DeepSeek V3.2 Exp | GPT-6 Sol |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,446 | 1,424 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,422 | 1,465 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,409 | 1,451 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,449 | 1,507 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,416 | 1,447 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,425 | 1,457 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,410 | 1,440 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 16.6 | 47.6 |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 14.9% | 47.9% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 72.3% | 83.7% |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 96.6% | 100.0% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 5.3% | 6.5% |
| Vending-Bench 2reported | Money after a yearUS dollars | $1,034.00 | $14,427.85 |
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.