Claude Fable 5 vs Claude Haiku 4.5
Claude Fable 5 (Anthropic) and Claude Haiku 4.5 (Anthropic) compared on benchmarks, pricing, context window, and use-case rankings.
- Claude Fable 5 leads on overall intelligence (ECI 163 vs 142).
- Claude Haiku 4.5 is cheaper on input tokens — $1.00 vs $10.00 per 1M.
- Claude Fable 5 has a larger context window (1M vs 200K tokens).
- Claude Fable 5 ranks higher for coding (96th vs 17th percentile).
| Attribute | Claude Fable 5 | Claude Haiku 4.5 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 163 | 142 |
| Coding | 96 | 17 |
| Math | 96 | 7 |
| Reasoning & Knowledge | 89 | 8 |
| Agentic & Tools | 96 | 16 |
| Specifications | ||
| Developer | Anthropic | Anthropic |
| Family | Claude | Claude |
| Released | Jun 9, 2026 | Oct 15, 2025 |
| Parameters | — | — |
| Availability | API access | API access |
| Context window | 1M | 200K |
| Price — $/M input | $10.00 | $1.00 |
| Price — $/M output | $50.00 | $5.00 |
| Inputs | text, image, file | text, image, file |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 100% | 67% |
| APEX | 45% | 9% |
| ARC-AGI | 99% | 48% |
| ARC-AGI-2 | 89% | 4% |
| GPQA Diamond | 86% | 71% |
| Humanity's Last Exam | 56% | — |
| SciCode | 61% | — |
| SimpleBench | 82% | — |
| SimpleQA Verified | 71% | 13% |
| WebDev Arena | 1626 | 1327 |
| WeirdML | 92% | 45% |
| τ²-bench | 99% | — |
| FrontierMath | — | 6% |
| FrontierMath Tier 4 | — | 2% |
| MATH Level 5 | — | 96% |
| Terminal-Bench | — | 36% |
Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.
Frequently asked questions
Is Claude Fable 5 better than Claude Haiku 4.5?
On Epoch AI's Capabilities Index, Claude Fable 5 scores higher (163) than Claude Haiku 4.5 (142). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.
Which is cheaper, Claude Fable 5 or Claude Haiku 4.5?
Claude Haiku 4.5 is cheaper on input tokens at $1.00 per million, versus $10.00 (representative OpenRouter pricing).
Which has a larger context window, Claude Fable 5 or Claude Haiku 4.5?
Claude Fable 5 supports up to 1M tokens, compared with 200K for the other.
Which is better for coding, Claude Fable 5 or Claude Haiku 4.5?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Claude Fable 5 ranks higher — 96th vs 17th percentile among the models tracked on Model Beat.
Want a different match-up? Open the compare tool to add or swap models.
More comparisons
Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.