Compare / DeepSeek V4 Pro 0423 vs GPT-6 Sol
DeepSeek V4 Pro 0423 vs GPT-6 Sol
19 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 V4 Pro 0423 | GPT-6 Sol |
|---|---|---|---|
| BulletBenchmeasured by us | Ladder Eloladder Elo | 0 | 0 |
| BulletBenchmeasured by us | Median move timemilliseconds | 6.4 s | 8.2 s |
| ROASBenchmeasured by us | Cost of a runUS dollars | $0.20 | $0.24 |
| ROASBenchmeasured by us | Months over budgetmonths of 12 | 0 | 0 |
| ROASBenchmeasured by us | Overall scorescore out of 100 | 28.2 | 54.1 |
| ROASBenchmeasured by us | Return on ad spendprofit per £1 spent | £0.26 | £0.65 |
| Arena (formerly LMArena)reported | Confirmed task successIPS effect estimate | -0.04 | 0.11 |
| Arena (formerly LMArena)reported | Praise over complaintIPS effect estimate | -0.02 | 0.11 |
| Arena (formerly LMArena)reported | SteerabilityIPS effect estimate | -0.03 | 0.15 |
| Arena (formerly LMArena)reported | Tool groundingIPS effect estimate | -0.00 | 0.00 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,455 | 1,424 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,460 | 1,465 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,446 | 1,451 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,480 | 1,507 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,452 | 1,447 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,458 | 1,457 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,451 | 1,440 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 97.2% | 100.0% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 8.6% | 6.5% |
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.