# Claude Fable 5.2 vs Claude Sonnet 5.5

> Side-by-side benchmark comparison for Claude Fable 5.2 and Claude Sonnet 5.5 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/claude-fable-5-2-vs-claude-sonnet-5-5
- Last updated: November 9, 2026

- Shared sourced benchmarks: 20
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Claude Fable 5.2 leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Claude Fable 5.2 has the higher overall point estimate 91.19 to 81.29. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in agentic, where the averages are 90.7 for Claude Fable 5.2 and 68.3 for Claude Sonnet 5.5.
- The biggest single benchmark swing is SWE Multimodal in Coding, with scores of 74.1% and 54.3%.
- Claude Sonnet 5.5 is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.

## Model Snapshot

| Property | Claude Fable 5.2 | Claude Sonnet 5.5 |
|----------|----------|----------|
| Creator | Anthropic | Anthropic |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 1M |
| Overall Score | 91.19 | 81.29 |
| Benchmarks Covered | 30 | 62 |
| Pricing (input/output) | $8.00 / $40.00 | $2.00 / $10.00 |

## Category Breakdown

### Agentic

- Winner: Directional only
- Claude Fable 5.2 public-lane score: 90.7 (Estimated · #1/132)
- Claude Sonnet 5.5 public-lane score: 68.3 (Supported · #12/132)

| Benchmark | Claude Fable 5.2 | Claude Sonnet 5.5 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 4.0 | 67.60% | 70.60% | Claude Sonnet 5.5 |
| Terminal-Bench-Science 0.1 | 74.6% | 59.9% | Claude Fable 5.2 |
| AutomationBench | 51.4% | Coming soon | Coming soon |
| OSWorld 2.1 Offline | 89.3% | 83.9% | Claude Fable 5.2 |
| WANDR | 82.1% | Coming soon | Coming soon |
| Remote Labor Index | 41.3% | Coming soon | Coming soon |
| RoboDojo Sim | 64.9% | Coming soon | Coming soon |
| DRACO | 87.7% | 87.0% | Claude Fable 5.2 |
| Terminal-Bench 4.1 | Coming soon | 63.90% | Coming soon |
| HLE w/ tools | Coming soon | 64.5% | Coming soon |
| LAB all-pass (Harvey held-out) | Coming soon | 10.0% | Coming soon |
| LAB criterion-pass (Harvey held-out) | Coming soon | 93.1% | Coming soon |
| Toolathlon Verified Pass@3 | Coming soon | 85.2% | Coming soon |
| Toolathlon Verified Pass³ | Coming soon | 68.5% | Coming soon |
| Toolathlon Verified avg. turns | Coming soon | 31.6 turns | Coming soon |
| AutomationBench (Zapier 1.0.6) | Coming soon | 44.70% | Coming soon |
| Toolathlon-Verified | Coming soon | 77.8% | Coming soon |
| Hermes Index | Coming soon | 53.1% | Coming soon |
| Hermes Bench | Coming soon | 73.5% | Coming soon |
| MazeBench | Coming soon | 8% | Coming soon |
| OSWorld 2.1 | Coming soon | 80.1% | Coming soon |
| Binary Exploitation Benchmark | Coming soon | 48 | Coming soon |

### Coding

- Winner: Directional only
- Claude Fable 5.2 public-lane score: 86.9 (Estimated · #1/158)
- Claude Sonnet 5.5 public-lane score: 81.4 (Supported · #3/158)

| Benchmark | Claude Fable 5.2 | Claude Sonnet 5.5 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Pro | 93% | 81.3% | Claude Fable 5.2 |
| SWE Multilingual | 96.6% | 90.3% | Claude Fable 5.2 |
| SWE Multimodal | 74.1% | 54.3% | Claude Fable 5.2 |
| DeepSWE | 74.3% | 71.0% | Claude Fable 5.2 |
| FrontierSWE v2 | 69.9% | 61.9% | Claude Fable 5.2 |
| ProgramBench | 85.6% | 79.7% | Claude Fable 5.2 |
| FrontierCode 2.0 | 49.1% | 41.0% | Claude Fable 5.2 |
| CursorBench 4.0 | 60.0% | 55.5% | Claude Fable 5.2 |
| FrontierCode 1.1 Main | Coming soon | 46.2% | Coming soon |
| FrontierCode 1.1 Extended | Coming soon | 59.1% | Coming soon |
| Bug Hunt Bench | Coming soon | 51.3 fixes | Coming soon |

### Reasoning

- Winner: Claude Fable 5.2
- Claude Fable 5.2 public-lane score: 90.7 (Supported · #1/157)
- Claude Sonnet 5.5 public-lane score: 76.2 (Supported · #7/157)

| Benchmark | Claude Fable 5.2 | Claude Sonnet 5.5 | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-3 | 65.7% | Coming soon | Coming soon |
| ARC-AGI-3 Provider Adapter | 94.90% | Coming soon | Coming soon |
| STEM Professor Bench | 61.8% | Coming soon | Coming soon |

### Multimodal & Grounded

- Winner: Directional only
- Claude Fable 5.2 public-lane score: 89.8 (Estimated · #1/67)
- Claude Sonnet 5.5 public-lane score: 77.6 (Estimated · #7/67)

| Benchmark | Claude Fable 5.2 | Claude Sonnet 5.5 | Winner |
|-----------|-----------|-----------|--------|
| Chartography (no tools) | 73.4% | 61.6% | Claude Fable 5.2 |
| Chartography (tools) | 91.6% | 90.2% | Claude Fable 5.2 |
| OfficeQA | 83.4% | 76.9% | Claude Fable 5.2 |
| OfficeQA Pro | 72.9% | 65.6% | Claude Fable 5.2 |
| BenchCAD 2.1 | 75.4% | Coming soon | Coming soon |
| BenchCAD 2.1 (tools) | 83.5% | Coming soon | Coming soon |
| ExtractBench Pro | Coming soon | 32% | Coming soon |
| ExtractBench (LlamaIndex) | Coming soon | 94.68% | Coming soon |
| ParseBench | Coming soon | 69.21% | Coming soon |
| BenchCAD Vision2Code (no tools) | Coming soon | 0.747 | Coming soon |
| BenchCAD Vision2Code (tools) | Coming soon | 0.963 | Coming soon |
| Biomedical image analysis | Coming soon | 72.2% | Coming soon |

### Knowledge

- Winner: Claude Fable 5.2
- Claude Fable 5.2 public-lane score: 97.6 (Supported · #1/179)
- Claude Sonnet 5.5 public-lane score: 79.9 (Supported · #8/179)

| Benchmark | Claude Fable 5.2 | Claude Sonnet 5.5 | Winner |
|-----------|-----------|-----------|--------|
| HLE | 74.2% | Coming soon | Coming soon |
| HLE w/o tools | 73.2% | 56.9% | Claude Fable 5.2 |
| PhysicianBench | 64.4% | 63.2% | Claude Fable 5.2 |
| HealthBench (raw) | Coming soon | 69.4% | Coming soon |
| HealthBench (length-adjusted) | Coming soon | 65.4% | Coming soon |
| HealthBench Professional (raw) | Coming soon | 77.1% | Coming soon |
| HealthBench Professional | Coming soon | 69.2% | Coming soon |
| BioMysteryBench (human-solvable) | Coming soon | 89.2% | Coming soon |
| BioMysteryBench (human-difficult) | Coming soon | 44.7% | Coming soon |
| SpatialBench Verified | Coming soon | 72.5% | Coming soon |
| SingleCellBench | Coming soon | 59.1% | Coming soon |
| Protein Design | Coming soon | 51.0% | Coming soon |
| Morphology-to-molecule matching | Coming soon | 25.0% | Coming soon |
| Medicinal chemistry | Coming soon | 65.3% | Coming soon |
| Protein Design library ranking | Coming soon | 54.8% | Coming soon |
| De novo protein-binder design | Coming soon | 82.3% | Coming soon |
| Protocols (troubleshooting) | Coming soon | 67.3% | Coming soon |
| Protocols (understanding) | Coming soon | 66.6% | Coming soon |

### Multilingual

- Winner: Not comparable
- Claude Fable 5.2 public-lane score: Coming soon
- Claude Sonnet 5.5 public-lane score: Coming soon

| Benchmark | Claude Fable 5.2 | Claude Sonnet 5.5 | Winner |
|-----------|-----------|-----------|--------|
| GMMLU | 96.0% | 92.1% | Claude Fable 5.2 |
| MILU | 94.1% | 91.6% | Claude Fable 5.2 |

### Mathematics

- Winner: Not comparable
- Claude Fable 5.2 public-lane score: Coming soon
- Claude Sonnet 5.5 public-lane score: 91.7 (Unranked · 4 rankable rows)

| Benchmark | Claude Fable 5.2 | Claude Sonnet 5.5 | Winner |
|-----------|-----------|-----------|--------|
| ArXivMath Aug. 2026 (no tools) | Coming soon | 86.8% | Coming soon |
| ArXivMath Aug. 2026 (tools) | Coming soon | 95.2% | Coming soon |
| FrontierMath v2 (Tiers 1-3) | Coming soon | 88.772% | Coming soon |
| FrontierMath v2 (Tier 4) | Coming soon | 80.488% | Coming soon |

## FAQ

### Which is better overall, Claude Fable 5.2 or Claude Sonnet 5.5?

Claude Fable 5.2 has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between Claude Fable 5.2 and Claude Sonnet 5.5?

The widest category gap is in agentic, where the averages are 90.7 for Claude Fable 5.2 and 68.3 for Claude Sonnet 5.5.

### How many benchmarks does Claude Fable 5.2 cover on BenchLM?

Claude Fable 5.2 currently has 30 sourced benchmark scores on BenchLM.

### How many benchmarks does Claude Sonnet 5.5 cover on BenchLM?

Claude Sonnet 5.5 currently has 62 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Claude Fable 5.2 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-claude-fable-5-2)
- [Claude Sonnet 5.5 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-claude-sonnet-5-5)
- [Claude Fable 5.2 vs Claude Fable 5](/compare/claude-fable-vs-claude-fable-5-2)
- [Claude Sonnet 5.5 vs Claude Fable 5](/compare/claude-fable-vs-claude-sonnet-5-5)

## Explore More

- [Claude Fable 5.2 profile](/models/claude-fable-5-2)
- [Claude Sonnet 5.5 profile](/models/claude-sonnet-5-5)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)