# Claude Fable 5.1 vs GPT-5.4 mini

> Side-by-side benchmark comparison for Claude Fable 5.1 and GPT-5.4 mini across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/claude-fable-5-1-vs-gpt-5-4-mini
- Last updated: October 17, 2026

- Shared sourced benchmarks: 10
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Pick Claude Fable 5.1 if you want the stronger benchmark profile. GPT-5.4 mini 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 53.41.
- The clearest category separation is in agentic, where the averages are 80.9 for Claude Fable 5.1 and 35.9 for GPT-5.4 mini.
- The biggest single benchmark swing is FrontierMath v2 (Tier 4) in Mathematics, with scores of 87.805% and 9.756%.
- GPT-5.4 mini is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Claude Fable 5.1 also has the larger context window at 1M.

## Model Snapshot

| Property | Claude Fable 5.1 | GPT-5.4 mini |
|----------|----------|----------|
| Creator | Anthropic | OpenAI |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 400K |
| Overall Score | 83.18 | 53.41 |
| Benchmarks Covered | 33 | 22 |
| Pricing (input/output) | $10.00 / $50.00 | $0.75 / $4.50 |

## Category Breakdown

### Agentic

- Winner: Claude Fable 5.1
- Claude Fable 5.1 public-lane score: 80.9 (Supported · #2/128)
- GPT-5.4 mini public-lane score: 35.9 (Supported · #78/128)

| Benchmark | Claude Fable 5.1 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 4.0 | 55.80% | Coming soon | Coming soon |
| Terminal-Bench-Science 0.1 | 52.6% | Coming soon | Coming soon |
| OSWorld 2.0 | 41.7% | Coming soon | Coming soon |
| AutomationBench | 31.4% | Coming soon | Coming soon |
| 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% | 54.7% | Claude Fable 5.1 |
| ApprenticeBench | 72% | Coming soon | Coming soon |
| CWE-bench v1 | 58.0% | Coming soon | Coming soon |
| MazeBench | 10% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 60% | Coming soon |
| OSWorld-Verified | Coming soon | 72.1% | Coming soon |
| MCP Atlas | Coming soon | 57.7% | Coming soon |
| Toolathlon | Coming soon | 42.9% | Coming soon |
| τ²-bench results | Coming soon | 93.4% | Coming soon |

### Coding

- Winner: Claude Fable 5.1
- Claude Fable 5.1 public-lane score: 76.8 (Supported · #3/150)
- GPT-5.4 mini public-lane score: 35.1 (Supported · #77/150)

| Benchmark | Claude Fable 5.1 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| Bug Hunt Bench | 43.0 fixes | Coming soon | Coming soon |
| SWE-bench Pro | 81.2% | Coming soon | Coming soon |
| SWE Multilingual | 89.1% | Coming soon | Coming soon |
| SWE Multimodal | 54.7% | Coming soon | Coming soon |
| DeepSWE | 67.4% | Coming soon | Coming soon |
| FrontierSWE v2 | 56.3% | Coming soon | Coming soon |
| ProgramBench | 87.6% | Coming soon | Coming soon |
| CursorBench 3.2 | 73.4% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 90.5% | 81.5% | Claude Fable 5.1 |
| CursorBench 4.0 | 51.8% | Coming soon | Coming soon |
| PostTrainBench v1.1 | 40.2% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 60.0% | Coming soon |
| Vibe Code Bench | Coming soon | 47.97% | Coming soon |
| FrontierCode 1.1 Main | Coming soon | 27.0% | Coming soon |
| SWE-bench (Vals) | Coming soon | 73.0% | Coming soon |

### Reasoning

- Winner: Not comparable
- Claude Fable 5.1 public-lane score: 85.2 (#4/28)
- GPT-5.4 mini public-lane score: 43.7 (Unranked · 4 rankable rows)

| Benchmark | Claude Fable 5.1 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-1 | 97.50% | 63.70% | Claude Fable 5.1 |
| ARC-AGI-2 | 90% | 18.9% | Claude Fable 5.1 |
| GraphWalks BFS 256K–1M | 65.0% | Coming soon | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- Claude Fable 5.1 public-lane score: Coming soon
- GPT-5.4 mini public-lane score: 73.8 (#28/54)

| Benchmark | Claude Fable 5.1 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | Coming soon | 76.6% | Coming soon |
| MMMU-Pro w/ Python | Coming soon | 78% | Coming soon |

### Knowledge

- Winner: Claude Fable 5.1
- Claude Fable 5.1 public-lane score: 86.9 (Supported · #2/184)
- GPT-5.4 mini public-lane score: 51.5 (Supported · #74/184)

| Benchmark | Claude Fable 5.1 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| HLE | 65% | 41.5% | Claude Fable 5.1 |
| HLE w/o tools | 60.9% | 28.2% | Claude Fable 5.1 |
| GPQA Diamond (Vals) | 93.4% | 83.1% | Claude Fable 5.1 |
| MMLU-Pro (Vals) | 92.4% | 84.6% | Claude Fable 5.1 |
| GPQA | Coming soon | 88% | Coming soon |

### Instruction Following

- Winner: Not comparable
- Claude Fable 5.1 public-lane score: Coming soon
- GPT-5.4 mini public-lane score: 89.9 (#27/148)

| Benchmark | Claude Fable 5.1 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| Gray Swan IPI (15 attempts) | 1.0% | Coming soon | Coming soon |

### Mathematics

- Winner: Not comparable
- Claude Fable 5.1 public-lane score: 96.8 (Unranked · 2 rankable rows)
- GPT-5.4 mini public-lane score: 55.9 (Unranked · 2 rankable rows)

| Benchmark | Claude Fable 5.1 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | 90.175% | 51.228% | Claude Fable 5.1 |
| FrontierMath v2 (Tier 4) | 87.805% | 9.756% | Claude Fable 5.1 |

## FAQ

### Which is better overall, Claude Fable 5.1 or GPT-5.4 mini?

Claude Fable 5.1 is ahead overall on BenchLM right now.

### Where is the biggest gap between Claude Fable 5.1 and GPT-5.4 mini?

The widest category gap is in agentic, where the averages are 80.9 for Claude Fable 5.1 and 35.9 for GPT-5.4 mini.

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

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

### How many benchmarks does GPT-5.4 mini cover on BenchLM?

GPT-5.4 mini currently has 22 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Claude Fable 5.1 vs Claude Fable 5](/compare/claude-fable-vs-claude-fable-5-1)
- [GPT-5.4 mini vs Claude Fable 5](/compare/claude-fable-vs-gpt-5-4-mini)
- [Claude Fable 5.1 vs GPT-5.4 Pro](/compare/claude-fable-5-1-vs-gpt-5-4-pro)
- [GPT-5.4 mini vs GPT-5.4 Pro](/compare/gpt-5-4-mini-vs-gpt-5-4-pro)

## Explore More

- [Claude Fable 5.1 profile](/models/claude-fable-5-1)
- [GPT-5.4 mini profile](/models/gpt-5-4-mini)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)