Claude Fable 5 vs Claude Haiku 5.5
Claude Fable 5 Verdict
- Claude Fable 5 (max) leads on quality: 69.1 vs 61.3.
- Claude Fable 5 (max) is stronger in agents & tools, coding, composite, instruction following, knowledge, long context, maths, reasoning.
- Claude Haiku 5.5 (high) is 100× cheaper ($0.200 vs $20.00 per 1M blended).
- Claude Haiku 5.5 (high) streams 2.7× faster (174 vs 65 tokens per second).
| Metric | Claude Fable 5 (max) | Claude Haiku 5.5 (high) |
|---|---|---|
| BenchLeader Index | 69.1 | 61.3 |
| Agents & tools score | 65.0 | – |
| Coding score | 74.1 | 62.6 |
| Composite score | 79.8 | 72.4 |
| Instruction following score | 63.0 | – |
| Knowledge score | 81.2 | 64.3 |
| Long context score | 66.4 | 63.8 |
| Maths score | 73.0 | 66.2 |
| Reasoning score | 74.0 | 72.1 |
| Blended price $/M | $20.00 | $0.200 |
| Output speed | 65 tok/s | 174 tok/s |
| Time to first answer | 117.7 s | 22.6 s |
| Context window | 1M | 1M |
| GPQA Diamond | 85.9% | – |
| FrontierMath Tiers 1–3 | 87.0% | – |
| FrontierMath Tier 4 | 90.2% | – |
| OTIS Mock AIME | 99.7% | 97.2% |
| Terminal-Bench | 44.5% | – |
| SimpleBench | 81.9% | – |
| SciCode | 61.0% | – |
| WeirdML | 91.9% | – |
| ProofBench | 95.0% | – |
| LMArena WebDev | – | 1587 |
| LiveBench | 83.0% | – |
| LiveBench Reasoning | 89.7% | – |
| LiveBench Coding | 86.0% | – |
| LiveBench Agentic Coding | 62.2% | – |
| LiveBench Mathematics | 96.0% | – |
| LiveBench Data Analysis | 80.5% | – |
| LiveBench Language | 90.7% | – |
| LiveBench Instruction Following | 75.8% | – |
| AA Intelligence Index v4.3.2 | 49.6 | 37.8 |
| IFBench | 63.5% | – |
| AA-LCR | 82.3% | 77.3% |
| AA-Omniscience | 43.3 | 5.8 |
| Terminal-Bench Hard | 62.9% | – |
| GPQA Diamond (AA) | 92.6% | – |
| Humanity's Last Exam (AA) | 55.5% | 37.3% |
| SciCode (AA) | 61.0% | 48.7% |
| τ²-Bench Telecom (AA) | 98.5% | – |
| ARC-AGI-1 | 98.5% | – |
| ARC-AGI-2 | 89.2% | – |
| CritPt | 28.6% | 18.6% |
| GDPval-AA v2.1 | 55.6% | 45.9% |
| τ³-Banking (AA) | 38.1% | – |
| Analyst Agent (AA) | 48.8% | – |
| Chess Puzzles | 41.0% | – |
| EBR-bench | 39.5% | – |
| Mystery Game Puzzles | 52.0% | – |
| PostTrainBench | 41.8% | – |
| DeepSWE v1.1 | 69.7% | – |
| LMCA | 60.3% | – |
| DTBench | 98.4% | – |
| Vending-Bench 2 | 4966.6 | – |
| GDP.pdf | 29.8% | – |
| FrontierSWE | 47.0% | – |
| Terminal-Bench 4.0 (AA) | 42.4% | 21.7% |
| Terminal-Bench 2.1 (AA) | 84.6% | – |
| AutomationBench | 54.1% | 33.7% |
| GDP.pdf | 24.0% | 17.2% |
| MLCR | 64.4% | – |
| Harvey LAB | – | 1.1% |
| EnterpriseOps-Gym | 51.1% | – |
| AA-Omniscience: accuracy | 65.3% | 34.8% |
| AA-Omniscience: non-hallucination | 36.4% | 55.5% |
| AA-Briefcase v1.1 | 1540 | 1442 |
Data as of 2026-10-11. Best configuration of each model; every score links to its source on the model pages.
Claude Fable 5 vs Claude Haiku 5.5: questions
- Is Claude Fable 5 better than Claude Haiku 5.5?
- Claude Fable 5 (max) leads on quality: 69.1 vs 61.3. The BenchLeader Index combines every independent quality benchmark; Claude Fable 5 (max) is ahead overall as of 2026-10-11, but check the category scores for your use.
- Is Claude Fable 5 better than Claude Haiku 5.5 for coding?
- Claude Fable 5 scores higher in coding (74 vs 63 on the category index, where 50 is average).
- Which is cheaper, Claude Fable 5 or Claude Haiku 5.5?
- Claude Haiku 5.5 is cheaper: $0.200 against $20.00 per million tokens, blended at three input tokens per output token.
- Which is faster, Claude Fable 5 or Claude Haiku 5.5?
- Claude Haiku 5.5 streams faster: 174 against 65 output tokens per second.
- Which has the larger context window?
- Both accept 1M tokens of context.