Claude Fable 5 vs Step 5 Preview
Claude Fable 5 
Step 5 Preview Verdict
- Claude Fable 5 (thinking) leads on quality: 70.9 vs 65.0.
- Claude Fable 5 (thinking) is stronger in agents & tools, composite, instruction following, knowledge, reasoning.
- Step 5 Preview is stronger in long context, multimodal.
- Step 5 Preview is 14× cheaper ($1.43 vs $20.00 per 1M blended).
| Metric | Claude Fable 5 (thinking) | Step 5 Preview |
|---|---|---|
| BenchLeader Index | 70.9 | 65.0 |
| Agents & tools score | 74.1 | – |
| Composite score | 92.1 | 84.4 |
| Instruction following score | 63.0 | – |
| Knowledge score | 84.9 | 72.0 |
| Long context score | 67.7 | 70.8 |
| Reasoning score | 90.8 | 82.1 |
| Multimodal score | – | 60.8 |
| Blended price $/M | $20.00 | $1.43 |
| Output speed | 57 tok/s | – |
| Time to first answer | 108.4 s | – |
| Context window | 1M | 1M |
| AA Intelligence Index | 49.7 | 43.6 |
| IFBench | 63.5% | – |
| AA-LCR | 82.3% | 88.3% |
| MMMU-Pro | – | 76.4% |
| AA-Omniscience | 43.3 | 16.4 |
| Terminal-Bench Hard | 62.9% | – |
| GPQA Diamond (AA) | 92.6% | – |
| Humanity's Last Exam (AA) | 55.5% | 46.5% |
| SciCode (AA) | 61.0% | 58.9% |
| τ²-Bench Telecom (AA) | 98.5% | – |
| Kagi LLM Benchmark | 91.4% | – |
| CritPt | 28.6% | 20.9% |
| GDPval (AA) | 56.6% | 53.6% |
| τ²-Bench Banking (AA) | 38.1% | – |
| Analyst Agent (AA) | 48.8% | – |
Data as of 2026-09-19. Best configuration of each model; every score links to its source on the model pages.
Claude Fable 5 vs Step 5 Preview: questions
- Is Claude Fable 5 better than Step 5 Preview?
- Claude Fable 5 (thinking) leads on quality: 70.9 vs 65.0. The BenchLeader Index combines every independent quality benchmark; Claude Fable 5 (thinking) is ahead overall as of 2026-09-19, but check the category scores for your use.
- Which is cheaper, Claude Fable 5 or Step 5 Preview?
- Step 5 Preview is cheaper: $1.43 against $20.00 per million tokens, blended at three input tokens per output token.
- Which has the larger context window?
- Both accept 1M tokens of context.