# Claude Fable 5.1 vs Claude Fable 5.2

> Side-by-side benchmark comparison for Claude Fable 5.1 and Claude Fable 5.2 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/claude-fable-5-1-vs-claude-fable-5-2
- Last updated: November 9, 2026

- Shared sourced benchmarks: 28
- 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 80.9. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in reasoning, where the averages are 76.8 for Claude Fable 5.1 and 90.7 for Claude Fable 5.2.
- The biggest single benchmark swing is BenchCAD 2.1 in Multimodal & Grounded, with scores of 36.3% and 75.4%.
- Claude Fable 5.2 is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.

## Model Snapshot

| Property | Claude Fable 5.1 | Claude Fable 5.2 |
|----------|----------|----------|
| Creator | Anthropic | Anthropic |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 1M |
| Overall Score | 80.9 | 91.19 |
| Benchmarks Covered | 56 | 30 |
| Pricing (input/output) | $10.00 / $50.00 | $8.00 / $40.00 |

## Category Breakdown

### Agentic

- Winner: Directional only
- Claude Fable 5.1 public-lane score: 80.4 (Supported · #3/132)
- Claude Fable 5.2 public-lane score: 90.7 (Estimated · #1/132)

| Benchmark | Claude Fable 5.1 | Claude Fable 5.2 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 4.1 | 57.60% | Coming soon | Coming soon |
| Terminal-Bench 4.0 | 55.80% | 67.60% | Claude Fable 5.2 |
| Terminal-Bench-Science 0.1 | 52.6% | 74.6% | Claude Fable 5.2 |
| OSWorld 2.0 | 41.7% | Coming soon | Coming soon |
| AutomationBench | 31.4% | 51.4% | Claude Fable 5.2 |
| Toolathlon-Verified | 77.8% | Coming soon | Coming soon |
| Toolathlon Verified Pass@3 | 81.5% | Coming soon | Coming soon |
| Toolathlon Verified Pass³ | 73.1% | Coming soon | Coming soon |
| Toolathlon Verified avg. turns | 23.7 turns | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 85.0% | Coming soon | Coming soon |
| ApprenticeBench | 72% | Coming soon | Coming soon |
| CWE-bench v1 | 58.0% | Coming soon | Coming soon |
| MazeBench | 10% | Coming soon | Coming soon |
| OSWorld 2.1 | 80.7% | Coming soon | Coming soon |
| WANDR | 68.7% | 82.1% | Claude Fable 5.2 |
| RoboDojo Sim | 27.6% | 64.9% | Claude Fable 5.2 |
| Remote Labor Index | 17.9% | 41.3% | Claude Fable 5.2 |
| OSWorld 2.1 Offline | 83.5% | 89.3% | Claude Fable 5.2 |
| DRACO | 87.7% | 87.7% | Tie |

### Coding

- Winner: Directional only
- Claude Fable 5.1 public-lane score: 76.4 (Supported · #5/158)
- Claude Fable 5.2 public-lane score: 86.9 (Estimated · #1/158)

| Benchmark | Claude Fable 5.1 | Claude Fable 5.2 | Winner |
|-----------|-----------|-----------|--------|
| Bug Hunt Bench | 43.0 fixes | Coming soon | Coming soon |
| SWE-bench Pro | 81.2% | 93% | Claude Fable 5.2 |
| SWE Multilingual | 89.1% | 96.6% | Claude Fable 5.2 |
| SWE Multimodal | 54.7% | 74.1% | Claude Fable 5.2 |
| DeepSWE | 67.4% | 74.3% | Claude Fable 5.2 |
| FrontierSWE v2 | 56.3% | 69.9% | Claude Fable 5.2 |
| ProgramBench | 87.6% | 85.6% | Claude Fable 5.1 |
| CursorBench 3.2 | 73.4% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 90.5% | Coming soon | Coming soon |
| CursorBench 4.0 | 51.8% | 60.0% | Claude Fable 5.2 |
| PostTrainBench v1.1 | 40.2% | Coming soon | Coming soon |
| FrontierCode 2.0 | 32.4% | 49.1% | Claude Fable 5.2 |

### Reasoning

- Winner: Claude Fable 5.2
- Claude Fable 5.1 public-lane score: 76.8 (Supported · #6/157)
- Claude Fable 5.2 public-lane score: 90.7 (Supported · #1/157)

| Benchmark | Claude Fable 5.1 | Claude Fable 5.2 | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-1 | 97.50% | Coming soon | Coming soon |
| ARC-AGI-2 | 90% | Coming soon | Coming soon |
| GraphWalks BFS 256K–1M | 65.0% | Coming soon | Coming soon |
| STEM Professor Bench | 29.9% | 61.8% | Claude Fable 5.2 |
| ARC-AGI-3 | Coming soon | 65.7% | Coming soon |
| ARC-AGI-3 Provider Adapter | Coming soon | 94.90% | Coming soon |

### Multimodal & Grounded

- Winner: Directional only
- Claude Fable 5.1 public-lane score: 81.1 (Estimated · #3/67)
- Claude Fable 5.2 public-lane score: 89.8 (Estimated · #1/67)

| Benchmark | Claude Fable 5.1 | Claude Fable 5.2 | Winner |
|-----------|-----------|-----------|--------|
| ParseBench | 77.81% | Coming soon | Coming soon |
| Chartography (no tools) | 42.6% | 73.4% | Claude Fable 5.2 |
| Chartography (tools) | 86.2% | 91.6% | Claude Fable 5.2 |
| BenchCAD Vision2Code (no tools) | 0.437 | Coming soon | Coming soon |
| BenchCAD Vision2Code (tools) | 0.843 | Coming soon | Coming soon |
| GDP.pdf (no tools) | 85.4% | Coming soon | Coming soon |
| GDP.pdf (tools) | 85.1% | Coming soon | Coming soon |
| OfficeQA | 80.2% | 83.4% | Claude Fable 5.2 |
| OfficeQA Pro | 69% | 72.9% | Claude Fable 5.2 |
| BenchCAD 2.1 | 36.3% | 75.4% | Claude Fable 5.2 |
| BenchCAD 2.1 (tools) | 44.4% | 83.5% | Claude Fable 5.2 |

### Knowledge

- Winner: Claude Fable 5.2
- Claude Fable 5.1 public-lane score: 84.6 (Supported · #3/179)
- Claude Fable 5.2 public-lane score: 97.6 (Supported · #1/179)

| Benchmark | Claude Fable 5.1 | Claude Fable 5.2 | Winner |
|-----------|-----------|-----------|--------|
| HLE | 65% | 74.2% | Claude Fable 5.2 |
| HLE w/o tools | 60.9% | 73.2% | Claude Fable 5.2 |
| GPQA Diamond (Vals) | 93.4% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 92.4% | Coming soon | Coming soon |
| PhysicianBench | 61.0% | 64.4% | Claude Fable 5.2 |

### Multilingual

- Winner: Not comparable
- Claude Fable 5.1 public-lane score: Coming soon
- Claude Fable 5.2 public-lane score: Coming soon

| Benchmark | Claude Fable 5.1 | Claude Fable 5.2 | Winner |
|-----------|-----------|-----------|--------|
| GMMLU | 94.0% | 96.0% | Claude Fable 5.2 |
| MILU | 93.0% | 94.1% | Claude Fable 5.2 |

### Instruction Following

- Winner: Not comparable
- Claude Fable 5.1 public-lane score: Coming soon
- Claude Fable 5.2 public-lane score: Coming soon

| Benchmark | Claude Fable 5.1 | Claude Fable 5.2 | Winner |
|-----------|-----------|-----------|--------|
| Gray Swan IPI (15 attempts) | 1.0% | Coming soon | Coming soon |

### Mathematics

- Winner: Not comparable
- Claude Fable 5.1 public-lane score: 93.3 (Unranked · 2 rankable rows)
- Claude Fable 5.2 public-lane score: Coming soon

| Benchmark | Claude Fable 5.1 | Claude Fable 5.2 | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | 90.175% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 87.805% | Coming soon | Coming soon |

## FAQ

### Which is better overall, Claude Fable 5.1 or Claude Fable 5.2?

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 5.1 and Claude Fable 5.2?

The widest category gap is in reasoning, where the averages are 76.8 for Claude Fable 5.1 and 90.7 for Claude Fable 5.2.

### How many benchmarks does Claude Fable 5.1 cover on BenchLM?

Claude Fable 5.1 currently has 56 sourced benchmark scores on BenchLM.

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

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

## Related Comparisons

- [Claude Fable 5.1 vs Claude Fable 5](/compare/claude-fable-vs-claude-fable-5-1)
- [Claude Fable 5.2 vs Claude Fable 5](/compare/claude-fable-vs-claude-fable-5-2)
- [Claude Fable 5.1 vs Gemini 4 Carbon](/compare/claude-fable-5-1-vs-gemini-4-carbon)
- [Claude Fable 5.2 vs Gemini 4 Carbon](/compare/claude-fable-5-2-vs-gemini-4-carbon)

## Explore More

- [Claude Fable 5.1 profile](/models/claude-fable-5-1)
- [Claude Fable 5.2 profile](/models/claude-fable-5-2)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)