Compare / DeepSeek V4 Pro 0423 vs GPT-5.6 Sol
DeepSeek V4 Pro 0423 vs GPT-5.6 Sol
16 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | DeepSeek V4 Pro 0423 | GPT-5.6 Sol |
|---|---|---|---|
| Arena (formerly LMArena)reported | Confirmed task successIPS effect estimate | -0.04 | 0.03 |
| Arena (formerly LMArena)reported | Praise over complaintIPS effect estimate | -0.02 | 0.19 |
| Arena (formerly LMArena)reported | SteerabilityIPS effect estimate | -0.03 | 0.07 |
| Arena (formerly LMArena)reported | Tool groundingIPS effect estimate | -0.00 | 0.00 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,455 | 1,476 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,460 | 1,485 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,446 | 1,470 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,480 | 1,534 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,452 | 1,489 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,458 | 1,483 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,451 | 1,483 |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 34.0% | 1.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.36 | 0.37 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 68.4 | 65.4 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 97.2% | 99.1% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 8.6% | 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.