# Claude Fable 5.1 vs Inkling

> Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 44.1 on the Noometry Index. Inkling costs 7.8× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-fable-5-1-vs-inkling
- Last updated: 2026-10-10
- Shared benchmarks: 36

## Summary

- They share 36 benchmarks with published results for both. Claude Fable 5.1 scores higher in 9 categories and Inkling 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 31.2.
- The biggest single-benchmark swing is ProofBench: 100% for Claude Fable 5.1 and 0% for Inkling.
- Inkling is cheaper at $1.87 / $4.68 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
- Claude Fable 5.1 accepts more context: 1M tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Fable 5.1 | Inkling |
|---|---|---|
| Provider | Anthropic | Thinking Machines Lab |
| Noometry Index | 68.5 | 44.1 |
| Rank | 2 | 75 |
| Context | 1M | 66K |
| Input $/M | $10 | $1.87 |
| Output $/M | $50 | $4.68 |
| Weights | Proprietary | Open |

## Coding

- Claude Fable 5.1: 70.5 (#2)
- Inkling: 34.1 (#229)

| Benchmark | Claude Fable 5.1 | Inkling |
|---|---|---|
| FrontierCode | 50.9% | 14% |
| LMArena WebDev | 1753 | 1412 |
| FrontierSWE | 56.3% | 4.1% |
| SciCode | 63.1% | 47% |
| WeirdML | 92.9% | 32.3% |
| LMArena Coding | 1523 | 1463 |
| ALE-Bench | 2,143 | 946 |
| CursorBench | 51.8% | — |
| MirrorCode | 73.3% | — |

## Agentic & Tool Use

- Claude Fable 5.1: 50.8 (#5)
- Inkling: 29.5 (#76)

| Benchmark | Claude Fable 5.1 | Inkling |
|---|---|---|
| APEX-Agents | 68.6% | 33.8% |
| Remote Labor Index | 17.9% | — |
| τ²-bench Banking | — | 25% |
| GDP.pdf | 29.6% | — |
| Vending-Bench 2 | 5,422 | — |

## Reasoning

- Claude Fable 5.1: 76.7 (#5)
- Inkling: 40.6 (#48)

| Benchmark | Claude Fable 5.1 | Inkling |
|---|---|---|
| ARC-AGI-2 | 90% | 36.5% |
| ARC-AGI-1 | 97.5% | 79.5% |
| CritPt | 31.1% | 5.4% |
| Chess Puzzles | 47% | 21% |
| LMArena Hard Prompts | 1526 | 1452 |
| DTBench | 97.6% | 87.5% |
| LMCA | 65.5% | 37.6% |
| Epoch Capabilities Index | 165 | 148.6 |
| SimpleBench | — | 50% |
| NYT Connections (extended) | 90% | — |
| EBR-Bench | 57.1% | — |
| Mystery Game Puzzles | 58% | — |

## Math

- Claude Fable 5.1: 89.5 (#3)
- Inkling: 31.2 (#198)

| Benchmark | Claude Fable 5.1 | Inkling |
|---|---|---|
| FrontierMath (Tiers 1-3) | 90.2% | 33.3% |
| FrontierMath Tier 4 | 87.8% | 4.9% |
| OTIS Mock AIME 2024-2025 | 100% | 88.9% |
| ProofBench | 100% | 0% |
| LMArena Math | 1519 | 1482 |
| FrontierMath Erdős | 0% | — |

## Knowledge

- Claude Fable 5.1: 69.3 (#5)
- Inkling: 55.2 (#44)

| Benchmark | Claude Fable 5.1 | Inkling |
|---|---|---|
| SimpleQA Verified | 70.8% | 40.3% |
| LMArena Expert | 1528 | 1468 |
| GPQA Diamond | — | 88.3% |
| Humanity's Last Exam | 46.5% | — |

## Multimodal

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

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

## Multilingual

- Claude Fable 5.1: 59.5 (#2)
- Inkling: 54.2 (#49)

| Benchmark | Claude Fable 5.1 | Inkling |
|---|---|---|
| LMArena Non-English | 1509 | 1434 |
| LMArena Chinese | 1589 | 1495 |
| LMArena French | 1532 | 1453 |
| LMArena German | 1495 | 1456 |
| LMArena Japanese | 1565 | 1428 |
| LMArena Russian | 1525 | 1430 |
| LMArena Spanish | 1503 | 1442 |
| LMArena Korean | — | 1401 |

## Instruction Following

- Claude Fable 5.1: 79.3 (#6)
- Inkling: 75.3 (#65)

| Benchmark | Claude Fable 5.1 | Inkling |
|---|---|---|
| LMArena Instruction Following | 1515 | 1427 |

## Long Context

- Claude Fable 5.1: 46.8 (#19)
- Inkling: 43.9 (#79)

| Benchmark | Claude Fable 5.1 | Inkling |
|---|---|---|
| LMArena Longer Query | 1524 | 1436 |

## Writing & Preference

- Claude Fable 5.1: 79.3 (#1)
- Inkling: 65.5 (#48)

| Benchmark | Claude Fable 5.1 | Inkling |
|---|---|---|
| LMArena Text | 1511 | 1443 |
| LMArena Creative Writing | 1507 | 1390 |
| EQ-Bench Creative Writing | 2162 | 1611 |
| LMArena Multi-Turn | 1492 | 1436 |
| EQ-Bench 4 | — | 1226 |

## FAQ

### Is Claude Fable 5.1 better than Inkling?

Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 44.1 on the Noometry Index. Inkling costs 7.8× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.

### Which is cheaper, Claude Fable 5.1 or Inkling?

Inkling is cheaper. It lists at $1.87 per million input tokens and $4.68 per million output tokens; Claude Fable 5.1 lists at $10 and $50.

### Is Claude Fable 5.1 or Inkling better for coding?

Claude Fable 5.1 scores higher on coding benchmarks: 70.5 versus 34.1 in the Noometry coding category.

### Which has the bigger context window?

Claude Fable 5.1 does, with 1M tokens against 66K.

### How many benchmarks do Claude Fable 5.1 and Inkling share?

36 benchmarks have published results for both models. Claude Fable 5.1 has 50 scored results on Noometry and Inkling has 41.