# Claude Fable 5.1 vs GPT-4

> Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 28.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-fable-5-1-vs-gpt-4
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Claude Fable 5.1 scores higher in 8 categories and GPT-4 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5.1 leads 89.5 to 10.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 100% for Claude Fable 5.1 and 1.1% for GPT-4.
- Claude Fable 5.1 is cheaper at $10 / $50 per million input/output tokens, against $30 / $60 for GPT-4.
- Claude Fable 5.1 accepts more context: 1M tokens versus 8K.

## Snapshot

| | Claude Fable 5.1 | GPT-4 |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 68.5 | 28.9 |
| Rank | 2 | 308 |
| Context | 1M | 8K |
| Input $/M | $10 | $30 |
| Output $/M | $50 | $60 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Fable 5.1: 70.5 (#2)
- GPT-4: 31.2 (#277)

| Benchmark | Claude Fable 5.1 | GPT-4 |
|---|---|---|
| WeirdML | 92.9% | 12.4% |
| LMArena Coding | 1523 | 1254 |
| FrontierCode | 50.9% | — |
| CursorBench | 51.8% | — |
| LMArena WebDev | 1753 | — |
| FrontierSWE | 56.3% | — |
| SciCode | 63.1% | — |
| BigCodeBench Instruct | — | 46% |
| MirrorCode | 73.3% | — |
| BigCodeBench Complete | — | 57.2% |
| ALE-Bench | 2,143 | — |
| HumanEval+ | — | 79.3% |

## Agentic & Tool Use

- Claude Fable 5.1: 50.8 (#5)
- GPT-4: —

| Benchmark | Claude Fable 5.1 | GPT-4 |
|---|---|---|
| APEX-Agents | 68.6% | — |
| Remote Labor Index | 17.9% | — |
| GDP.pdf | 29.6% | — |
| METR Time Horizons | — | 36.1% |
| Vending-Bench 2 | 5,422 | — |

## Reasoning

- Claude Fable 5.1: 76.7 (#5)
- GPT-4: 17.3 (#285)

| Benchmark | Claude Fable 5.1 | GPT-4 |
|---|---|---|
| Chess Puzzles | 47% | 4% |
| LMArena Hard Prompts | 1526 | 1241 |
| Mystery Game Puzzles | 58% | 12% |
| DTBench | 97.6% | 62.7% |
| LMCA | 65.5% | 17.1% |
| Epoch Capabilities Index | 165 | 125.88 |
| ARC-AGI-2 | 90% | — |
| NYT Connections (extended) | 90% | — |
| ARC-AGI-1 | 97.5% | — |
| CritPt | 31.1% | — |
| EBR-Bench | 57.1% | — |
| BIG-Bench Hard | — | 75.1% |
| ForecastBench | — | 57.8 |
| HellaSwag | — | 95.3% |
| WinoGrande | — | 87.5% |

## Math

- Claude Fable 5.1: 89.5 (#3)
- GPT-4: 10.1 (#304)

| Benchmark | Claude Fable 5.1 | GPT-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 1.1% |
| LMArena Math | 1519 | 1269 |
| FrontierMath (Tiers 1-3) | 90.2% | — |
| FrontierMath Tier 4 | 87.8% | — |
| ProofBench | 100% | — |
| MATH Level 5 | — | 23% |
| FrontierMath Erdős | 0% | — |
| GSM8K | — | 92% |

## Knowledge

- Claude Fable 5.1: 69.3 (#5)
- GPT-4: 18.4 (#277)

| Benchmark | Claude Fable 5.1 | GPT-4 |
|---|---|---|
| LMArena Expert | 1528 | 1211 |
| GPQA Diamond | — | 35.7% |
| Humanity's Last Exam | 46.5% | — |
| SimpleQA Verified | 70.8% | — |
| MMLU | — | 86.4% |
| TriviaQA | — | 84.8% |

## Multimodal

- Claude Fable 5.1: 54.1 (#4)
- GPT-4: —

| Benchmark | Claude Fable 5.1 | GPT-4 |
|---|---|---|
| LMArena Vision | 1319 | — |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |

## Multilingual

- Claude Fable 5.1: 59.5 (#2)
- GPT-4: 40.8 (#210)

| Benchmark | Claude Fable 5.1 | GPT-4 |
|---|---|---|
| LMArena Non-English | 1509 | 1246 |
| LMArena Chinese | 1589 | 1242 |
| LMArena French | 1532 | 1282 |
| LMArena German | 1495 | 1251 |
| LMArena Japanese | 1565 | 1209 |
| LMArena Russian | 1525 | 1251 |
| LMArena Spanish | 1503 | 1261 |
| LMArena Korean | — | 1184 |

## Instruction Following

- Claude Fable 5.1: 79.3 (#6)
- GPT-4: 65.5 (#217)

| Benchmark | Claude Fable 5.1 | GPT-4 |
|---|---|---|
| LMArena Instruction Following | 1515 | 1241 |

## Long Context

- Claude Fable 5.1: 46.8 (#19)
- GPT-4: 37.7 (#207)

| Benchmark | Claude Fable 5.1 | GPT-4 |
|---|---|---|
| LMArena Longer Query | 1524 | 1244 |

## Writing & Preference

- Claude Fable 5.1: 79.3 (#1)
- GPT-4: 35.0 (#263)

| Benchmark | Claude Fable 5.1 | GPT-4 |
|---|---|---|
| LMArena Text | 1511 | 1263 |
| LMArena Creative Writing | 1507 | 1244 |
| EQ-Bench Creative Writing | 2162 | 752 |
| LMArena Multi-Turn | 1492 | 1257 |

## FAQ

### Is Claude Fable 5.1 better than GPT-4?

Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 28.9 on the Noometry Index.

### Which is cheaper, Claude Fable 5.1 or GPT-4?

Claude Fable 5.1 is cheaper. It lists at $10 per million input tokens and $50 per million output tokens; GPT-4 lists at $30 and $60.

### Is Claude Fable 5.1 or GPT-4 better for coding?

Claude Fable 5.1 scores higher on coding benchmarks: 70.5 versus 31.2 in the Noometry coding category.

### Which has the bigger context window?

Claude Fable 5.1 does, with 1M tokens against 8K.

### How many benchmarks do Claude Fable 5.1 and GPT-4 share?

24 benchmarks have published results for both models. Claude Fable 5.1 has 50 scored results on Noometry and GPT-4 has 38.