# Claude Fable 5 vs Claude Fable 5.1

> Side-by-side benchmark comparison for Claude Fable 5 and Claude Fable 5.1 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/claude-fable-vs-claude-fable-5-1
- Last updated: October 17, 2026

- Shared sourced benchmarks: 13
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Pick Claude Fable 5.1 if you want the stronger benchmark profile. Claude Fable 5 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Claude Fable 5.1 leads overall 83.18 to 81.27.
- The clearest category separation is in coding, where the averages are 71.3 for Claude Fable 5 and 76.8 for Claude Fable 5.1.
- The biggest single benchmark swing is ApprenticeBench in Agentic, with scores of 34% and 72%.

## Model Snapshot

| Property | Claude Fable 5 | Claude Fable 5.1 |
|----------|----------|----------|
| Creator | Anthropic | Anthropic |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 1M+ | 1M |
| Overall Score | 81.27 | 83.18 |
| Benchmarks Covered | 24 | 33 |
| Pricing (input/output) | $10.00 / $50.00 | $10.00 / $50.00 |

## Category Breakdown

### Agentic

- Winner: Claude Fable 5.1
- Claude Fable 5 public-lane score: 75.9 (Supported · #6/128)
- Claude Fable 5.1 public-lane score: 80.9 (Supported · #2/128)

| Benchmark | Claude Fable 5 | Claude Fable 5.1 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 3.0 | 34.0% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 84.3% | Coming soon | Coming soon |
| OSWorld-Verified | 85% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 80.5% | 85.0% | Claude Fable 5.1 |
| ApprenticeBench | 34% | 72% | Claude Fable 5.1 |
| MazeBench | 11% | 10% | Claude Fable 5 |
| Terminal-Bench 4.0 | Coming soon | 55.80% | Coming soon |
| Terminal-Bench-Science 0.1 | Coming soon | 52.6% | Coming soon |
| OSWorld 2.0 | Coming soon | 41.7% | Coming soon |
| AutomationBench | Coming soon | 31.4% | Coming soon |
| Toolathlon-Verified | Coming soon | 77.8% | Coming soon |
| Toolathlon Verified Pass@3 | Coming soon | 81.5% | Coming soon |
| Toolathlon Verified Pass³ | Coming soon | 73.1% | Coming soon |
| Toolathlon Verified avg. turns | Coming soon | 23.7 turns | Coming soon |
| CWE-bench v1 | Coming soon | 58.0% | Coming soon |

### Coding

- Winner: Claude Fable 5.1
- Claude Fable 5 public-lane score: 71.3 (Supported · #7/150)
- Claude Fable 5.1 public-lane score: 76.8 (Supported · #3/150)

| Benchmark | Claude Fable 5 | Claude Fable 5.1 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 95% | Coming soon | Coming soon |
| SWE-bench Pro | 80% | 81.2% | Claude Fable 5.1 |
| FrontierSWE v2 | 47.0% | 56.3% | Claude Fable 5.1 |
| FrontierCode 1.1 Main | 53.5% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 84.3% | Coming soon | Coming soon |
| cursorBench31 | 70.6% | Coming soon | Coming soon |
| CursorBench 3.2 | 70.5% | 73.4% | Claude Fable 5.1 |
| VulcanBench v3 | 89.5% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 89.8% | 90.5% | Claude Fable 5.1 |
| SWE-bench (Vals) | 95.0% | Coming soon | Coming soon |
| Bug Hunt Bench | Coming soon | 43.0 fixes | Coming soon |
| SWE Multilingual | Coming soon | 89.1% | Coming soon |
| SWE Multimodal | Coming soon | 54.7% | Coming soon |
| DeepSWE | Coming soon | 67.4% | Coming soon |
| ProgramBench | Coming soon | 87.6% | Coming soon |
| CursorBench 4.0 | Coming soon | 51.8% | Coming soon |
| PostTrainBench v1.1 | Coming soon | 40.2% | Coming soon |

### Reasoning

- Winner: Not comparable
- Claude Fable 5 public-lane score: 84.3 (Unranked · 4 rankable rows)
- Claude Fable 5.1 public-lane score: 85.2 (#4/28)

| Benchmark | Claude Fable 5 | Claude Fable 5.1 | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-1 | 98.50% | 97.50% | Claude Fable 5 |
| ARC-AGI-2 | 89.2% | 90% | Claude Fable 5.1 |
| GraphWalks BFS 256K–1M | Coming soon | 65.0% | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- Claude Fable 5 public-lane score: 66 (Unranked · 2 rankable rows)
- Claude Fable 5.1 public-lane score: Coming soon

| Benchmark | Claude Fable 5 | Claude Fable 5.1 | Winner |
|-----------|-----------|-----------|--------|
| Blueprint-Bench 2 | 38.6% | Coming soon | Coming soon |
| OfficeQA Pro | 57.9% | Coming soon | Coming soon |

### Knowledge

- Winner: Claude Fable 5.1
- Claude Fable 5 public-lane score: 82.5 (Supported · #6/184)
- Claude Fable 5.1 public-lane score: 86.9 (Supported · #2/184)

| Benchmark | Claude Fable 5 | Claude Fable 5.1 | Winner |
|-----------|-----------|-----------|--------|
| GPQA Diamond (Vals) | 93.2% | 93.4% | Claude Fable 5.1 |
| MMLU-Pro (Vals) | 91.5% | 92.4% | Claude Fable 5.1 |
| HLE | Coming soon | 65% | Coming soon |
| HLE w/o tools | Coming soon | 60.9% | Coming soon |

### Instruction Following

- Winner: Not comparable
- Claude Fable 5 public-lane score: 77.1 (#62/148)
- Claude Fable 5.1 public-lane score: Coming soon

| Benchmark | Claude Fable 5 | Claude Fable 5.1 | Winner |
|-----------|-----------|-----------|--------|
| Gray Swan IPI (15 attempts) | Coming soon | 1.0% | Coming soon |

### Mathematics

- Winner: Not comparable
- Claude Fable 5 public-lane score: 96 (Unranked · 2 rankable rows)
- Claude Fable 5.1 public-lane score: 96.8 (Unranked · 2 rankable rows)

| Benchmark | Claude Fable 5 | Claude Fable 5.1 | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | 87.018% | 90.175% | Claude Fable 5.1 |
| FrontierMath v2 (Tier 4) | 90.200% | 87.805% | Claude Fable 5 |

## FAQ

### Which is better overall, Claude Fable 5 or Claude Fable 5.1?

Claude Fable 5.1 is ahead overall on BenchLM right now.

### Where is the biggest gap between Claude Fable 5 and Claude Fable 5.1?

The widest category gap is in coding, where the averages are 71.3 for Claude Fable 5 and 76.8 for Claude Fable 5.1.

### How many benchmarks does Claude Fable 5 cover on BenchLM?

Claude Fable 5 currently has 24 sourced benchmark scores on BenchLM.

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

Claude Fable 5.1 currently has 33 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Claude Fable 5 vs Claude Opus 5.5](/compare/claude-fable-vs-claude-opus-5-5)
- [Claude Fable 5.1 vs Claude Opus 5.5](/compare/claude-fable-5-1-vs-claude-opus-5-5)
- [Claude Fable 5 vs GPT-6.1 Sol](/compare/claude-fable-vs-gpt-6-1-sol)
- [Claude Fable 5.1 vs GPT-6.1 Sol](/compare/claude-fable-5-1-vs-gpt-6-1-sol)

## Explore More

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