# Claude Opus 5.5 vs Inkling

> Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 44.1 on the Noometry Index. Inkling costs 3.1× less per token, which makes it the better buy when Claude Opus 5.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-opus-5-5-vs-inkling
- Last updated: 2026-10-10
- Shared benchmarks: 33

## Summary

- They share 33 benchmarks with published results for both. Claude Opus 5.5 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 Opus 5.5 leads 91.8 to 31.3.
- The biggest single-benchmark swing is ProofBench: 100% for Claude Opus 5.5 and 0% for Inkling.
- Inkling is cheaper at $1.87 / $4.68 per million input/output tokens, against $4 / $20 for Claude Opus 5.5.
- Claude Opus 5.5 accepts more context: 1M tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Opus 5.5 | Inkling |
|---|---|---|
| Provider | Anthropic | Thinking Machines Lab |
| Noometry Index | 68.6 | 44.1 |
| Rank | 3 | 80 |
| Context | 1M | 66K |
| Input $/M | $4 | $1.87 |
| Output $/M | $20 | $4.68 |
| Weights | Proprietary | Open |

## Coding

- Claude Opus 5.5: 71.9 (#3)
- Inkling: 34.5 (#234)

| Benchmark | Claude Opus 5.5 | Inkling |
|---|---|---|
| FrontierCode | 54.6% | 14% |
| LMArena WebDev | 1813 | 1413 |
| FrontierSWE | 62.3% | 4.1% |
| SciCode | 66.9% | 47% |
| LMArena Coding | 1547 | 1464 |
| ALE-Bench | 2,147 | 946 |
| CursorBench | 57.8% | — |
| WeirdML | — | 32.3% |
| MirrorCode | 77.4% | — |

## Agentic & Tool Use

- Claude Opus 5.5: 45.3 (#15)
- Inkling: 29.6 (#85)

| Benchmark | Claude Opus 5.5 | Inkling |
|---|---|---|
| APEX-Agents | 73.5% | 33.8% |
| τ²-bench Banking | — | 25% |
| GDP.pdf | 30.6% | — |
| Vending-Bench 2 | 9,235 | — |

## Reasoning

- Claude Opus 5.5: 80.2 (#3)
- Inkling: 40.4 (#56)

| Benchmark | Claude Opus 5.5 | Inkling |
|---|---|---|
| ARC-AGI-2 | 93.3% | 36.5% |
| ARC-AGI-1 | 98.5% | 79.5% |
| CritPt | 31.7% | 5.4% |
| LMArena Hard Prompts | 1535 | 1451 |
| DTBench | 98.9% | 87.5% |
| LMCA | 68.2% | 37.6% |
| Epoch Capabilities Index | 167.33 | 148.54 |
| SimpleBench | — | 50% |
| NYT Connections (extended) | 88.5% | — |
| Chess Puzzles | — | 21% |
| EBR-Bench | 71.4% | — |
| Mystery Game Puzzles | 71% | — |

## Math

- Claude Opus 5.5: 91.8 (#3)
- Inkling: 31.3 (#225)

| Benchmark | Claude Opus 5.5 | Inkling |
|---|---|---|
| FrontierMath (Tiers 1-3) | 91.2% | 33.3% |
| FrontierMath Tier 4 | 95% | 4.9% |
| OTIS Mock AIME 2024-2025 | 100% | 88.9% |
| ProofBench | 100% | 0% |
| LMArena Math | 1506 | 1479 |
| FrontierMath Erdős | 2.9% | — |

## Knowledge

- Claude Opus 5.5: 66.4 (#10)
- Inkling: 55.1 (#49)

| Benchmark | Claude Opus 5.5 | Inkling |
|---|---|---|
| GPQA Diamond | 90.6% | 88.3% |
| SimpleQA Verified | 72.2% | 40.3% |
| LMArena Expert | 1547 | 1465 |

## Multimodal

- Claude Opus 5.5: 57.8 (#1)
- Inkling: —

| Benchmark | Claude Opus 5.5 | Inkling |
|---|---|---|
| LMArena Vision | 1321 | — |
| Blueprint-Bench 2 | 51.2% | — |
| Furniture Assembly | 83.3% | — |

## Multilingual

- Claude Opus 5.5: 59.1 (#2)
- Inkling: 54.0 (#52)

| Benchmark | Claude Opus 5.5 | Inkling |
|---|---|---|
| LMArena Non-English | 1507 | 1434 |
| LMArena Chinese | 1588 | 1490 |
| LMArena French | 1514 | 1458 |
| LMArena Russian | 1520 | 1429 |
| LMArena Spanish | 1507 | 1448 |
| LMArena German | — | 1446 |
| LMArena Japanese | — | 1429 |
| LMArena Korean | — | 1404 |

## Instruction Following

- Claude Opus 5.5: 80.0 (#3)
- Inkling: 75.1 (#71)

| Benchmark | Claude Opus 5.5 | Inkling |
|---|---|---|
| LMArena Instruction Following | 1537 | 1426 |

## Long Context

- Claude Opus 5.5: 47.1 (#19)
- Inkling: 43.8 (#86)

| Benchmark | Claude Opus 5.5 | Inkling |
|---|---|---|
| LMArena Longer Query | 1532 | 1434 |

## Writing & Preference

- Claude Opus 5.5: 78.2 (#3)
- Inkling: 65.2 (#51)

| Benchmark | Claude Opus 5.5 | Inkling |
|---|---|---|
| LMArena Text | 1515 | 1441 |
| LMArena Creative Writing | 1533 | 1387 |
| EQ-Bench Creative Writing | 2050 | 1611 |
| LMArena Multi-Turn | 1499 | 1436 |
| EQ-Bench 4 | — | 1226 |

## FAQ

### Is Claude Opus 5.5 better than Inkling?

Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 44.1 on the Noometry Index. Inkling costs 3.1× less per token, which makes it the better buy when Claude Opus 5.5's lead doesn't matter for your workload.

### Which is cheaper, Claude Opus 5.5 or Inkling?

Inkling is cheaper. It lists at $1.87 per million input tokens and $4.68 per million output tokens; Claude Opus 5.5 lists at $4 and $20.

### Is Claude Opus 5.5 or Inkling better for coding?

Claude Opus 5.5 scores higher on coding benchmarks: 71.9 versus 34.5 in the Noometry coding category.

### Which has the bigger context window?

Claude Opus 5.5 does, with 1M tokens against 66K.

### How many benchmarks do Claude Opus 5.5 and Inkling share?

33 benchmarks have published results for both models. Claude Opus 5.5 has 44 scored results on Noometry and Inkling has 41.