Compare / Claude Opus 4.8 vs DeepSeek V3.2 Exp
Claude Opus 4.8 vs DeepSeek V3.2 Exp
18 results from 4 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Claude Opus 4.8 | DeepSeek V3.2 Exp |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,469 | 1,446 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,490 | 1,422 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,467 | 1,409 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,525 | 1,449 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,491 | 1,416 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,480 | 1,425 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,474 | 1,410 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 41.8 | 16.6 |
| Artificial Analysisreported | GPQA Diamond% of questions | 92.0% | 79.7% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 48.7% | 14.9% |
| Artificial Analysisreported | IFBench% of instructions | 62.2% | 54.1% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 77.7% | 72.3% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 58.3% | 31.1% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 94.4% | 33.9% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 6.0% | 25.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.40 | 0.35 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 65.9 | 54.0 |
| Vending-Bench 2reported | Money after a yearUS dollars | $5,787.43 | $1,034.00 |
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.