# Claude Fable 5.1 vs Claude Fable 5.2

As of Nov 22, 2026, Claude Fable 5.1 leads Claude Fable 5.2 in 3 of 10 shared categories: Reasoning, Factuality, and Legal.

## Which is better for coding?

As of Nov 22, 2026, Claude Fable 5.2 leads Claude Fable 5.1 in Coding at #2 against #5.

## Pricing

Claude Fable 5.1: $20 per 1M blended tokens.

Claude Fable 5.2: $16 per 1M blended tokens.

Claude Fable 5.1: closed weights.

Claude Fable 5.2: closed weights.

## Benchmarks side by side

| Benchmark | Claude Fable 5.1 | Claude Fable 5.2 |
| --- | ---: | ---: |
| ARC-AGI | 97.5% | 98.5% |
| Excel Modeling Benchmark (EMB) | 76.7 | 77.4 |
| GDP.pdf | 29.6% | 51.8% |
| Legal Research Bench | 55.3 | 46.2 |
| LMArena Text (style-controlled, coding) | 1533 | 1526 |
| LMArena Text (style-controlled, hard prompts) | 1522 | 1517 |
| LMArena Text (style-controlled, longer query) | 1511 | 1518 |
| LMArena Text (style-controlled, overall) | 1503 | 1503 |
| LMArena Text factuality | 1499 | 1483 |
| LMArena Vision (style-controlled) | 1290 | 1305 |
| LMArena WebDev | 1742 | 1824 |
| MysteryMechanism | 47.7 | 51.8 |
| ProofBench | 100 | 100 |
| SimpleQA Verified | 70.8% | 94.0% |
| Tax Agent Bench | 50.7 | 32.1 |
| Vibe Code Bench | 90.3 | 93.8 |

## Verdict

As of Nov 22, 2026, Claude Fable 5.1 leads Claude Fable 5.2 in 3 of 10 shared categories: Reasoning, Factuality, and Legal.

- Which to pick, General LLM: As of Nov 22, 2026, Claude Fable 5.2 leads Claude Fable 5.1 in General LLM at #5 against #7.
- Which to pick, Reasoning: As of Nov 22, 2026, Claude Fable 5.1 leads Claude Fable 5.2 in Reasoning at #7 against #10.
- Which to pick, Science: As of Nov 22, 2026, Claude Fable 5.2 leads Claude Fable 5.1 in Science at #2 against #5.
- Which to pick, Coding: As of Nov 22, 2026, Claude Fable 5.2 leads Claude Fable 5.1 in Coding at #2 against #5.
- Which to pick, Coding › Web dev: As of Nov 22, 2026, Claude Fable 5.2 leads Claude Fable 5.1 in Coding › Web dev at #1 against #10.
- Which to pick, Long context: As of Nov 22, 2026, Claude Fable 5.2 leads Claude Fable 5.1 in Long context at #5 against #7.
- Which to pick, Factuality: As of Nov 22, 2026, Claude Fable 5.1 leads Claude Fable 5.2 in Factuality at #3 against #13.
- Which to pick, Abstraction (ARC): As of Nov 22, 2026, Claude Fable 5.2 leads Claude Fable 5.1 in Abstraction (ARC) at #1 against #3.
- Which to pick, Finance: As of Nov 22, 2026, Claude Fable 5.2 leads Claude Fable 5.1 in Finance at #1 against #7.
- Which to pick, Legal: As of Nov 22, 2026, Claude Fable 5.1 leads Claude Fable 5.2 in Legal at #2 against #13.

As of Nov 22, 2026, Claude Fable 5.1 is near state of the art, rank #2 in Math (since Nov 22, 2026; sources Humanity's Last Exam; methodology v1.0).

As of Nov 22, 2026, Claude Fable 5.2 is tied for state of the art in Coding › Web dev (since Nov 11, 2026; sources LMArena WebDev; methodology v1.0).

## Related comparisons

- [Claude Fable 5.2 vs Claude Opus 5.5](https://isitsota.com/compare/claude-fable-5-2-vs-claude-opus-5-5)
- [Claude Fable 5.2 vs Gemini 4 Carbon](https://isitsota.com/compare/claude-fable-5-2-vs-gemini-4-carbon)
- [Claude Fable 5.2 vs Gemini 4 Argon](https://isitsota.com/compare/claude-fable-5-2-vs-gemini-4-argon)
- [Claude Fable 5.2 vs Gemini 4 Neon](https://isitsota.com/compare/claude-fable-5-2-vs-gemini-4-neon)
- [Claude Fable 5.1 vs Claude Opus 5.5](https://isitsota.com/compare/claude-fable-5-1-vs-claude-opus-5-5)
- [Claude Fable 5.2 vs Claude Sonnet 5.5](https://isitsota.com/compare/claude-fable-5-2-vs-claude-sonnet-5-5)
- [Claude Fable 5.1 vs Gemini 4 Carbon](https://isitsota.com/compare/claude-fable-5-1-vs-gemini-4-carbon)
- [Claude Fable 5.2 vs GPT-6 Astra](https://isitsota.com/compare/claude-fable-5-2-vs-gpt-6-astra)
