Claude Sonnet 5 vs Step 5 Preview
Claude Sonnet 5 
Step 5 Preview Verdict
- Step 5 Preview leads on quality: 65.0 vs 62.2.
- Claude Sonnet 5 (high) is stronger in agents & tools, coding, human preference, maths, multimodal.
- Step 5 Preview is stronger in composite, knowledge, long context, reasoning.
- Step 5 Preview is 2.8× cheaper ($1.43 vs $4.00 per 1M blended).
| Metric | Claude Sonnet 5 (high) | Step 5 Preview |
|---|---|---|
| BenchLeader Index | 62.2 | 65.0 |
| Agents & tools score | 62.0 | – |
| Coding score | 61.5 | – |
| Composite score | 69.6 | 84.4 |
| Human preference score | 65.9 | – |
| Knowledge score | 62.4 | 72.0 |
| Long context score | 64.7 | 70.8 |
| Maths score | 66.9 | – |
| Multimodal score | 62.6 | 60.8 |
| Reasoning score | 69.6 | 82.1 |
| Blended price $/M | $4.00 | $1.43 |
| Output speed | 64 tok/s | – |
| Time to first answer | 2.9 s | – |
| Context window | 1M | 1M |
| SciCode | 48.6% | – |
| WeirdML | 68.8% | – |
| LMArena Text | 1461 | – |
| LMArena Hard Prompts | 1489 | – |
| LMArena Coding | 1521 | – |
| LMArena WebDev | 1537 | – |
| LMArena Vision | 1277 | – |
| LMArena Agent | 6 | – |
| AA Intelligence Index | 32.0 | 43.6 |
| AA-LCR | 76.7% | 88.3% |
| MMMU-Pro | – | 76.4% |
| AA-Omniscience | -3.7 | 16.4 |
| Humanity's Last Exam (AA) | 35.7% | 46.5% |
| SciCode (AA) | 54.3% | 58.9% |
| CritPt | 15.1% | 20.9% |
| GDPval (AA) | 40.4% | 53.6% |
| LMArena Maths | 1476 | – |
| LMArena Creative Writing | 1437 | – |
| LMArena Instruction Following | 1465 | – |
| LMArena Multi-turn | 1473 | – |
| LMArena Longer Queries | 1482 | – |
| LMArena Document | 1476 | – |
| DeepSWE | 48.2% | – |
| CursorBench | 56.9% | – |
| ALE-Bench | 1463.1 | – |
Data as of 2026-09-19. Best configuration of each model; every score links to its source on the model pages.
Claude Sonnet 5 vs Step 5 Preview: questions
- Is Claude Sonnet 5 better than Step 5 Preview?
- Step 5 Preview leads on quality: 65.0 vs 62.2. The BenchLeader Index combines every independent quality benchmark; Step 5 Preview is ahead overall as of 2026-09-19, but check the category scores for your use.
- Which is cheaper, Claude Sonnet 5 or Step 5 Preview?
- Step 5 Preview is cheaper: $1.43 against $4.00 per million tokens, blended at three input tokens per output token.
- Which has the larger context window?
- Both accept 1M tokens of context.