Claude Fable 5 vs Claude Opus 4.5
Claude Fable 5 (Anthropic) and Claude Opus 4.5 (Anthropic) compared on benchmarks, pricing, context window, and use-case rankings.
- Claude Fable 5 leads on overall intelligence (ECI 161 vs 150).
- Claude Opus 4.5 is cheaper on input tokens — $5.00 vs $10.00 per 1M.
- Claude Fable 5 has a larger context window (1M vs 200K tokens).
- Claude Fable 5 ranks higher for coding (99th vs 71th percentile).
| Attribute | Claude Fable 5 | Claude Opus 4.5 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 161 | 150 |
| Coding | 99 | 71 |
| Math | 95 | 31 |
| Reasoning & Knowledge | 96 | 63 |
| Agentic & Tools | 98 | 62 |
| Specifications | ||
| Developer | Anthropic | Anthropic |
| Family | Claude | Claude |
| Released | Jun 9, 2026 | Nov 24, 2025 |
| Parameters | — | — |
| Availability | API access | API access |
| Context window | 1M | 200K |
| Price — $/M input | $10.00 | $5.00 |
| Price — $/M output | $50.00 | $25.00 |
| Inputs | text, image, file | file, image, text |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 100% | 86% |
| APEX | 45% | 21% |
| GPQA Diamond | 93% | 86% |
| Humanity's Last Exam | 53% | 25% |
| SciCode | 60% | 50% |
| SimpleBench | 82% | 62% |
| SimpleQA Verified | 68% | 42% |
| WebDev Arena | 1654 | 1512 |
| WeirdML | 92% | 64% |
| τ²-bench | 99% | 89% |
| ARC-AGI | — | 80% |
| ARC-AGI-2 | — | 38% |
| FrontierMath | — | 21% |
| FrontierMath Tier 4 | — | 4% |
| GDPval (win/tie rate) | — | 60% |
| GSO (code optimization) | — | 27% |
| LiveCodeBench | — | 87% |
| METR task horizon | — | 4.9 h |
| MMLU-Pro | — | 90% |
| SWE-bench Verified | — | 77% |
| Terminal-Bench | — | 63% |
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 Opus 4.5?
On Epoch AI's Capabilities Index, Claude Fable 5 scores higher (161) than Claude Opus 4.5 (150). 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 Opus 4.5?
Claude Opus 4.5 is cheaper on input tokens at $5.00 per million, versus $10.00 (representative OpenRouter pricing).
Which has a larger context window, Claude Fable 5 or Claude Opus 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 Opus 4.5?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Claude Fable 5 ranks higher — 99th vs 71th 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.