# Claude Fable 5.2 vs Claude Opus 5.5

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

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

- Shared sourced benchmarks: 27
- 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 85.82. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in reasoning, where the averages are 90.7 for Claude Fable 5.2 and 80 for Claude Opus 5.5.
- The biggest single benchmark swing is BenchCAD 2.1 in Multimodal & Grounded, with scores of 75.4% and 49.0%.
- Claude Opus 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 Opus 5.5 |
|----------|----------|----------|
| Creator | Anthropic | Anthropic |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 1M |
| Overall Score | 91.19 | 85.82 |
| Benchmarks Covered | 30 | 82 |
| Pricing (input/output) | $8.00 / $40.00 | $4.00 / $20.00 |

## Category Breakdown

### Agentic

- Winner: Directional only
- Claude Fable 5.2 public-lane score: 90.7 (Estimated · #1/132)
- Claude Opus 5.5 public-lane score: 89.3 (Supported · #2/132)

| Benchmark | Claude Fable 5.2 | Claude Opus 5.5 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 4.0 | 67.60% | 66.40% | Claude Fable 5.2 |
| Terminal-Bench-Science 0.1 | 74.6% | 58.7% | Claude Fable 5.2 |
| AutomationBench | 51.4% | 40.0% | Claude Fable 5.2 |
| OSWorld 2.1 Offline | 89.3% | 87.2% | Claude Fable 5.2 |
| WANDR | 82.1% | 72.3% | Claude Fable 5.2 |
| Remote Labor Index | 41.3% | 21.3% | Claude Fable 5.2 |
| RoboDojo Sim | 64.9% | 39.4% | Claude Fable 5.2 |
| DRACO | 87.7% | 87.4% | Claude Fable 5.2 |
| Terminal-Bench 4.1 | Coming soon | 65.80% | Coming soon |
| HLE w/ tools | Coming soon | 67.7% | Coming soon |
| OSWorld 2.0 | Coming soon | 48.7% | Coming soon |
| LAB all-pass (Harvey held-out) | Coming soon | 8.3% | Coming soon |
| LAB criterion-pass (Harvey held-out) | Coming soon | 91.2% | Coming soon |
| Toolathlon-Verified | Coming soon | 77.8% | Coming soon |
| Toolathlon Verified Pass@3 | Coming soon | 82.4% | Coming soon |
| Toolathlon Verified Pass³ | Coming soon | 72.2% | Coming soon |
| Toolathlon Verified avg. turns | Coming soon | 26.9 turns | Coming soon |
| CWE-bench v1 | Coming soon | 67.0% | Coming soon |
| Hermes Index | Coming soon | 63.3% | Coming soon |
| Hermes Bench | Coming soon | 76.7% | Coming soon |
| MazeBench | Coming soon | 13% | Coming soon |
| OSWorld 2.1 | Coming soon | 81.8% | Coming soon |
| CVE Rediscovery | Coming soon | 81.3% | Coming soon |
| ExploitGym | Coming soon | 33.3% | Coming soon |
| Binary Exploitation Benchmark | Coming soon | 112 | Coming soon |
| CWE-bench | Coming soon | 67.1% | Coming soon |

### Coding

- Winner: Directional only
- Claude Fable 5.2 public-lane score: 86.9 (Estimated · #1/158)
- Claude Opus 5.5 public-lane score: 82.4 (Supported · #2/158)

| Benchmark | Claude Fable 5.2 | Claude Opus 5.5 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Pro | 93% | 89.9% | Claude Fable 5.2 |
| SWE Multilingual | 96.6% | 93.9% | Claude Fable 5.2 |
| SWE Multimodal | 74.1% | 61.4% | Claude Fable 5.2 |
| DeepSWE | 74.3% | 74.2% | Claude Fable 5.2 |
| FrontierSWE v2 | 69.9% | 62.3% | Claude Fable 5.2 |
| ProgramBench | 85.6% | 91.2% | Claude Opus 5.5 |
| FrontierCode 2.0 | 49.1% | 45.5% | Claude Fable 5.2 |
| CursorBench 4.0 | 60.0% | 57.8% | Claude Fable 5.2 |
| ScarfBench | Coming soon | 70.5% | Coming soon |
| FrontierCode 1.1 Main | Coming soon | 54.4% | Coming soon |
| FrontierCode 1.1 Extended | Coming soon | 63.6% | Coming soon |
| PostTrainBench v1.1 | Coming soon | 49.3% | Coming soon |
| Bug Hunt Bench | Coming soon | 41.7 fixes | Coming soon |

### Reasoning

- Winner: Claude Fable 5.2
- Claude Fable 5.2 public-lane score: 90.7 (Supported · #1/157)
- Claude Opus 5.5 public-lane score: 80 (Supported · #4/157)

| Benchmark | Claude Fable 5.2 | Claude Opus 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% | 53.7% | Claude Fable 5.2 |
| STEMBench | Coming soon | 2.62 | Coming soon |
| ARC-AGI-1 | Coming soon | 97.50% | Coming soon |
| ARC-AGI-2 | Coming soon | 91.7% | Coming soon |
| GraphWalks BFS 256K–1M | Coming soon | 66.8% | Coming soon |

### Multimodal & Grounded

- Winner: Directional only
- Claude Fable 5.2 public-lane score: 89.8 (Estimated · #1/67)
- Claude Opus 5.5 public-lane score: 84.4 (Supported · #2/67)

| Benchmark | Claude Fable 5.2 | Claude Opus 5.5 | Winner |
|-----------|-----------|-----------|--------|
| Chartography (no tools) | 73.4% | 64.4% | Claude Fable 5.2 |
| Chartography (tools) | 91.6% | 89.0% | Claude Fable 5.2 |
| OfficeQA | 83.4% | 78.9% | Claude Fable 5.2 |
| OfficeQA Pro | 72.9% | 67.7% | Claude Fable 5.2 |
| BenchCAD 2.1 | 75.4% | 49.0% | Claude Fable 5.2 |
| BenchCAD 2.1 (tools) | 83.5% | 65.3% | Claude Fable 5.2 |
| ExtractBench Pro | Coming soon | 51% | Coming soon |
| ExtractBench (LlamaIndex) | Coming soon | 86.06% | Coming soon |
| ParseBench | Coming soon | 78.80% | Coming soon |
| BenchCAD Vision2Code (no tools) | Coming soon | 0.730 | Coming soon |
| BenchCAD Vision2Code (tools) | Coming soon | 0.962 | Coming soon |
| Biomedical image analysis | Coming soon | 71.4% | Coming soon |

### Knowledge

- Winner: Claude Fable 5.2
- Claude Fable 5.2 public-lane score: 97.6 (Supported · #1/179)
- Claude Opus 5.5 public-lane score: 88.1 (Supported · #2/179)

| Benchmark | Claude Fable 5.2 | Claude Opus 5.5 | Winner |
|-----------|-----------|-----------|--------|
| HLE | 74.2% | Coming soon | Coming soon |
| HLE w/o tools | 73.2% | 64.4% | Claude Fable 5.2 |
| PhysicianBench | 64.4% | 68.4% | Claude Opus 5.5 |
| HealthBench (raw) | Coming soon | 68.1% | Coming soon |
| HealthBench (length-adjusted) | Coming soon | 60.6% | Coming soon |
| HealthBench Professional | Coming soon | 65.6% | Coming soon |
| HealthBench Professional (raw) | Coming soon | 77.1% | Coming soon |
| BioMysteryBench (human-solvable) | Coming soon | 89.3% | Coming soon |
| BioMysteryBench (human-difficult) | Coming soon | 50.0% | Coming soon |
| SpatialBench Verified | Coming soon | 72.0% | Coming soon |
| SingleCellBench | Coming soon | 61.2% | Coming soon |
| Morphology-to-molecule matching | Coming soon | 34.0% | Coming soon |
| Medicinal chemistry | Coming soon | 63.5% | Coming soon |
| Protein Design | Coming soon | 60.2% | Coming soon |
| Protein Design library ranking | Coming soon | 56.0% | Coming soon |
| De novo protein-binder design | Coming soon | 82.6% | Coming soon |
| Protocols (troubleshooting) | Coming soon | 73.7% | Coming soon |
| Protocols (understanding) | Coming soon | 69.0% | Coming soon |
| Protein Domain ID | Coming soon | 73.6% | Coming soon |
| Protein Mutation Attribution | Coming soon | 49.5% | Coming soon |

### Multilingual

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

| Benchmark | Claude Fable 5.2 | Claude Opus 5.5 | Winner |
|-----------|-----------|-----------|--------|
| GMMLU | 96.0% | 94.3% | Claude Fable 5.2 |
| MILU | 94.1% | 93.1% | Claude Fable 5.2 |

### Instruction Following

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

| Benchmark | Claude Fable 5.2 | Claude Opus 5.5 | Winner |
|-----------|-----------|-----------|--------|
| Gray Swan IPI (15 attempts) | Coming soon | 1.0% | Coming soon |

### Mathematics

- Winner: Not comparable
- Claude Fable 5.2 public-lane score: Coming soon
- Claude Opus 5.5 public-lane score: 93.8 (Unranked · 4 rankable rows)

| Benchmark | Claude Fable 5.2 | Claude Opus 5.5 | Winner |
|-----------|-----------|-----------|--------|
| ArXivMath Aug. 2026 (no tools) | Coming soon | 91.2% | Coming soon |
| ArXivMath Aug. 2026 (tools) | Coming soon | 96.9% | Coming soon |
| FrontierMath v2 (Tiers 1-3) | Coming soon | 91.228% | Coming soon |
| FrontierMath v2 (Tier 4) | Coming soon | 95.000% | Coming soon |

## FAQ

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

The widest category gap is in reasoning, where the averages are 90.7 for Claude Fable 5.2 and 80 for Claude Opus 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 Opus 5.5 cover on BenchLM?

Claude Opus 5.5 currently has 82 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 Opus 5.5 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-claude-opus-5-5)
- [Claude Fable 5.2 vs Claude Fable 5](/compare/claude-fable-vs-claude-fable-5-2)
- [Claude Opus 5.5 vs Claude Fable 5](/compare/claude-fable-vs-claude-opus-5-5)

## Explore More

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