# Claude 3.7 Sonnet vs Claude Fable 5

> Claude Fable 5 is the stronger model overall, scoring 66.8 to 39.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-7-sonnet-vs-claude-fable-5
- Last updated: 2026-10-12
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 1 category and Claude Fable 5 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Fable 5 leads 76.8 to 18.6.
- The biggest single-benchmark swing is ARC-AGI-2: 0.9% for Claude 3.7 Sonnet and 89.2% for Claude Fable 5.

## Snapshot

| | Claude 3.7 Sonnet | Claude Fable 5 |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 39.5 | 66.8 |
| Rank | 164 | 5 |
| Context | — | 1M |
| Input $/M | — | $10 |
| Output $/M | — | $50 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3.7 Sonnet: 40.6 (#136)
- Claude Fable 5: 70.6 (#4)

| Benchmark | Claude 3.7 Sonnet | Claude Fable 5 |
|---|---|---|
| GSO | 3.8% | 78.4% |
| LMArena Coding | 1361 | 1519 |
| SWE-bench Verified | 61% | — |
| DeepSWE | — | 69.9% |
| FrontierCode | — | 53.5% |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| LMArena WebDev | — | 1625 |
| FrontierSWE | — | 47% |
| SciCode | — | 61% |
| WeirdML | — | 91.9% |
| LiveBench Coding | 74.5% | — |
| MirrorCode | — | 63.9% |
| CadEval | 54% | — |
| ALE-Bench | — | 2,041 |

## Agentic & Tool Use

- Claude 3.7 Sonnet: 34.1 (#50)
- Claude Fable 5: 54.0 (#2)

| Benchmark | Claude 3.7 Sonnet | Claude Fable 5 |
|---|---|---|
| APEX-Agents | — | 63.6% |
| Remote Labor Index | — | 16.1% |
| TheAgentCompany | 30.9% | — |
| τ²-bench Banking | — | 39.7% |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| PostTrainBench | — | 41.8% |
| GBAEval | — | 74.5% |
| GDP.pdf | — | 30% |
| LMArena Search | — | 1230 |
| METR Time Horizons | 60% | — |
| Vending-Bench 2 | — | 5,680 |

## Reasoning

- Claude 3.7 Sonnet: 18.6 (#277)
- Claude Fable 5: 76.8 (#6)

| Benchmark | Claude 3.7 Sonnet | Claude Fable 5 |
|---|---|---|
| ARC-AGI-2 | 0.9% | 89.2% |
| SimpleBench | 46.4% | 81.9% |
| ARC-AGI-1 | 28.6% | 98.5% |
| EnigmaEval | 4.2% | 39.3% |
| LMArena Hard Prompts | 1333 | 1508 |
| Epoch Capabilities Index | 141.16 | 162.06 |
| Kagi LLM Benchmark | — | 91.4% |
| NYT Connections (extended) | — | 92.7% |
| CritPt | — | 28.6% |
| Chess Puzzles | — | 41% |
| EBR-Bench | — | 39.5% |
| LiveBench Reasoning | 87.8% | — |
| Mystery Game Puzzles | — | 52% |
| DTBench | — | 98.4% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 61.1% |
| Surface Evolver Bench | — | 95% |
| Bench to the Future 3 | — | 0.13 |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |

## Math

- Claude 3.7 Sonnet: 37.5 (#153)
- Claude Fable 5: 88.5 (#5)

| Benchmark | Claude 3.7 Sonnet | Claude Fable 5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 100% |
| LMArena Math | 1337 | 1519 |
| FrontierMath (Tiers 1-3) | — | 87% |
| FrontierMath Tier 4 | — | 90.2% |
| ProofBench | — | 95% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Erdős | — | 0% |

## Knowledge

- Claude 3.7 Sonnet: 39.8 (#130)
- Claude Fable 5: 62.2 (#25)

| Benchmark | Claude 3.7 Sonnet | Claude Fable 5 |
|---|---|---|
| GPQA Diamond | 79.7% | 85.9% |
| LMArena Expert | 1321 | 1534 |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | — | 70.7% |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| GPQA (HELM) | 60.8% | — |

## Multimodal

- Claude 3.7 Sonnet: 33.7 (#95)
- Claude Fable 5: 45.3 (#17)

| Benchmark | Claude 3.7 Sonnet | Claude Fable 5 |
|---|---|---|
| LMArena Vision | 1169 | 1324 |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| Blueprint-Bench 2 | — | 38.6% |
| Furniture Assembly | — | 35.8% |
| LMArena Document | — | 1496 |
| SpatialViz-Bench | 33.9% | — |

## Multilingual

- Claude 3.7 Sonnet: 44.1 (#179)
- Claude Fable 5: 57.3 (#9)

| Benchmark | Claude 3.7 Sonnet | Claude Fable 5 |
|---|---|---|
| LMArena Non-English | 1296 | 1481 |
| LMArena Chinese | 1299 | 1543 |
| LMArena French | 1303 | 1505 |
| LMArena German | 1301 | 1486 |
| LMArena Japanese | 1267 | 1506 |
| LMArena Korean | 1249 | 1488 |
| LMArena Russian | 1311 | 1504 |
| LMArena Spanish | 1298 | 1498 |

## Instruction Following

- Claude 3.7 Sonnet: 72.9 (#125)
- Claude Fable 5: 78.6 (#8)

| Benchmark | Claude 3.7 Sonnet | Claude Fable 5 |
|---|---|---|
| LMArena Instruction Following | 1352 | 1502 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |

## Long Context

- Claude 3.7 Sonnet: 50.3 (#10)
- Claude Fable 5: 46.3 (#23)

| Benchmark | Claude 3.7 Sonnet | Claude Fable 5 |
|---|---|---|
| LMArena Longer Query | 1373 | 1509 |
| Fiction.LiveBench | 83.3% | — |

## Writing & Preference

- Claude 3.7 Sonnet: 54.4 (#150)
- Claude Fable 5: 75.9 (#5)

| Benchmark | Claude 3.7 Sonnet | Claude Fable 5 |
|---|---|---|
| LMArena Text | 1314 | 1491 |
| LMArena Creative Writing | 1332 | 1494 |
| EQ-Bench Creative Writing | 1412 | 1943 |
| LMArena Multi-Turn | 1339 | 1504 |
| Short-Story Creative Writing | 81.1% | — |
| WildBench | 81.4% | — |
| EQ-Bench 4 | — | 1340 |
| LiveBench Language | 59.9% | — |

## FAQ

### Is Claude 3.7 Sonnet better than Claude Fable 5?

Claude Fable 5 is the stronger model overall, scoring 66.8 to 39.5 on the Noometry Index.

### Is Claude 3.7 Sonnet or Claude Fable 5 better for coding?

Claude Fable 5 scores higher on coding benchmarks: 70.6 versus 40.6 in the Noometry coding category.

### How many benchmarks do Claude 3.7 Sonnet and Claude Fable 5 share?

27 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Claude Fable 5 has 62.