# Claude Fable 5.1 vs Step 3

> Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 39.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-fable-5-1-vs-step-3
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Claude Fable 5.1 scores higher in 9 categories and Step 3 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5.1 leads 89.5 to 34.9.
- Step 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Fable 5.1 | Step 3 |
|---|---|---|
| Provider | Anthropic | StepFun |
| Noometry Index | 68.5 | 39.9 |
| Rank | 2 | 145 |
| Context | 1M | — |
| Input $/M | $10 | — |
| Output $/M | $50 | — |
| Weights | Proprietary | Open |

## Coding

- Claude Fable 5.1: 70.5 (#2)
- Step 3: 39.5 (#144)

| Benchmark | Claude Fable 5.1 | Step 3 |
|---|---|---|
| LMArena Coding | 1523 | 1367 |
| FrontierCode | 50.9% | — |
| CursorBench | 51.8% | — |
| LMArena WebDev | 1753 | — |
| FrontierSWE | 56.3% | — |
| SciCode | 63.1% | — |
| WeirdML | 92.9% | — |
| MirrorCode | 73.3% | — |
| ALE-Bench | 2,143 | — |

## Agentic & Tool Use

- Claude Fable 5.1: 50.8 (#5)
- Step 3: —

| Benchmark | Claude Fable 5.1 | Step 3 |
|---|---|---|
| APEX-Agents | 68.6% | — |
| Remote Labor Index | 17.9% | — |
| GDP.pdf | 29.6% | — |
| Vending-Bench 2 | 5,422 | — |

## Reasoning

- Claude Fable 5.1: 76.7 (#5)
- Step 3: 27.6 (#102)

| Benchmark | Claude Fable 5.1 | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1526 | 1355 |
| ARC-AGI-2 | 90% | — |
| Kagi LLM Benchmark | — | 62.3% |
| NYT Connections (extended) | 90% | — |
| ARC-AGI-1 | 97.5% | — |
| CritPt | 31.1% | — |
| Chess Puzzles | 47% | — |
| EBR-Bench | 57.1% | — |
| Mystery Game Puzzles | 58% | — |
| DTBench | 97.6% | — |
| LMCA | 65.5% | — |
| Epoch Capabilities Index | 165 | — |

## Math

- Claude Fable 5.1: 89.5 (#3)
- Step 3: 34.9 (#148)

| Benchmark | Claude Fable 5.1 | Step 3 |
|---|---|---|
| LMArena Math | 1519 | 1366 |
| FrontierMath (Tiers 1-3) | 90.2% | — |
| FrontierMath Tier 4 | 87.8% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 100% | — |
| FrontierMath Erdős | 0% | — |

## Knowledge

- Claude Fable 5.1: 69.3 (#5)
- Step 3: 36.2 (#161)

| Benchmark | Claude Fable 5.1 | Step 3 |
|---|---|---|
| LMArena Expert | 1528 | 1333 |
| Humanity's Last Exam | 46.5% | — |
| SimpleQA Verified | 70.8% | — |

## Multimodal

- Claude Fable 5.1: 54.1 (#4)
- Step 3: 34.9 (#81)

| Benchmark | Claude Fable 5.1 | Step 3 |
|---|---|---|
| LMArena Vision | 1319 | 1176 |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |

## Multilingual

- Claude Fable 5.1: 59.5 (#2)
- Step 3: 46.5 (#154)

| Benchmark | Claude Fable 5.1 | Step 3 |
|---|---|---|
| LMArena Non-English | 1509 | 1327 |
| LMArena Chinese | 1589 | 1396 |
| LMArena German | 1495 | 1371 |
| LMArena Russian | 1525 | 1331 |
| LMArena Spanish | 1503 | 1372 |
| LMArena French | 1532 | — |
| LMArena Japanese | 1565 | — |
| LMArena Korean | — | 1271 |

## Instruction Following

- Claude Fable 5.1: 79.3 (#6)
- Step 3: 70.6 (#159)

| Benchmark | Claude Fable 5.1 | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1515 | 1332 |

## Long Context

- Claude Fable 5.1: 46.8 (#19)
- Step 3: 40.3 (#152)

| Benchmark | Claude Fable 5.1 | Step 3 |
|---|---|---|
| LMArena Longer Query | 1524 | 1326 |

## Writing & Preference

- Claude Fable 5.1: 79.3 (#1)
- Step 3: 54.5 (#146)

| Benchmark | Claude Fable 5.1 | Step 3 |
|---|---|---|
| LMArena Text | 1511 | 1351 |
| LMArena Creative Writing | 1507 | 1322 |
| LMArena Multi-Turn | 1492 | 1340 |
| EQ-Bench Creative Writing | 2162 | — |

## FAQ

### Is Claude Fable 5.1 better than Step 3?

Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 39.9 on the Noometry Index.

### Is Claude Fable 5.1 or Step 3 better for coding?

Claude Fable 5.1 scores higher on coding benchmarks: 70.5 versus 39.5 in the Noometry coding category.

### How many benchmarks do Claude Fable 5.1 and Step 3 share?

15 benchmarks have published results for both models. Claude Fable 5.1 has 50 scored results on Noometry and Step 3 has 17.