# Claude Opus 4.5 vs Inkling-Small

> Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 46.5 on the Noometry Index. Inkling-Small costs 16× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-opus-4-5-vs-inkling-small
- Last updated: 2026-10-10
- Shared benchmarks: 30

## Summary

- They share 30 benchmarks with published results for both. Claude Opus 4.5 scores higher in 7 categories and Inkling-Small in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Opus 4.5 leads 55.4 to 43.3.
- The biggest single-benchmark swing is ProofBench: 36% for Claude Opus 4.5 and 6% for Inkling-Small.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.
- Inkling-Small accepts more context: 524K tokens versus 200K.
- Inkling-Small has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Opus 4.5 | Inkling-Small |
|---|---|---|
| Provider | Anthropic | Thinking Machines Lab |
| Noometry Index | 50.5 | 46.5 |
| Rank | 39 | 57 |
| Context | 200K | 524K |
| Input $/M | $5 | $0.45 |
| Output $/M | $25 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Claude Opus 4.5: 55.4 (#21)
- Inkling-Small: 43.3 (#80)

| Benchmark | Claude Opus 4.5 | Inkling-Small |
|---|---|---|
| LMArena WebDev | 1493 | 1408 |
| LMArena Coding | 1504 | 1451 |
| SWE-bench Verified | 76.7% | — |
| SWE-bench Verified (bash only) | 76.8% | — |
| SWE-bench Multilingual | 70.7% | — |
| SciCode | — | 48.7% |
| GSO | 26.5% | — |
| WeirdML | 63.7% | — |
| ALE-Bench | 1,025 | — |
| AlgoTune | 1.77 | — |

## Agentic & Tool Use

- Claude Opus 4.5: 47.2 (#11)
- Inkling-Small: —

| Benchmark | Claude Opus 4.5 | Inkling-Small |
|---|---|---|
| Terminal-Bench | 63.1% | — |
| Berkeley Function Calling Leaderboard | 77.5% | — |
| GDPval | 45.5% | — |
| Remote Labor Index | 3.8% | — |
| τ²-bench Airline | 84% | — |
| τ²-bench Banking | 24.7% | — |
| τ²-bench Retail | 79.6% | — |
| τ²-bench Telecom | 92.3% | — |
| Cybench | 82% | — |
| DeepResearch Bench | 54.8% | — |
| OSWorld | 66.3% | — |
| BALROG | 43.5% | — |
| LMArena Search | 1180 | — |
| METR Time Horizons | 75% | — |
| Vending-Bench 2 | 4,967 | — |

## Reasoning

- Claude Opus 4.5: 42.5 (#43)
- Inkling-Small: 39.0 (#53)

| Benchmark | Claude Opus 4.5 | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | 37.6% | 40.1% |
| ARC-AGI-1 | 80% | 84% |
| Chess Puzzles | 12% | 18% |
| LMArena Hard Prompts | 1476 | 1424 |
| Mystery Game Puzzles | 22% | 6% |
| Epoch Capabilities Index | 150.1 | 150.13 |
| SimpleBench | 62% | — |
| Kagi LLM Benchmark | 80.2% | — |
| NYT Connections (extended) | 52.5% | — |
| CritPt | — | 8.3% |
| EnigmaEval | 11.9% | — |
| EBR-Bench | 14.3% | — |
| DTBench | 89.9% | — |
| LMCA | 44.5% | — |
| ForecastBench | 60.7 | — |

## Math

- Claude Opus 4.5: 38.5 (#85)
- Inkling-Small: 44.9 (#65)

| Benchmark | Claude Opus 4.5 | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 34.4% | 46.3% |
| FrontierMath Tier 4 | 4.9% | 17.1% |
| OTIS Mock AIME 2024-2025 | 86.1% | 90% |
| ProofBench | 36% | 6% |
| LMArena Math | 1463 | 1453 |
| FrontierMath (Feb 2025 set) | 20.7% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Claude Opus 4.5: 56.4 (#38)
- Inkling-Small: 48.3 (#71)

| Benchmark | Claude Opus 4.5 | Inkling-Small |
|---|---|---|
| GPQA Diamond | 86% | 88.5% |
| SimpleQA Verified | 45.7% | 19.1% |
| LMArena Expert | 1488 | 1442 |
| Humanity's Last Exam | 25.2% | — |
| Vectara Hallucination Rate | 10.9% | — |

## Multimodal

- Claude Opus 4.5: 31.1 (#99)
- Inkling-Small: 38.4 (#59)

| Benchmark | Claude Opus 4.5 | Inkling-Small |
|---|---|---|
| LMArena Vision | — | 1235 |
| GeoBench | 75% | — |
| VPCT | 40% | — |
| Furniture Assembly | 28.3% | — |
| LMArena Document | 1462 | — |

## Multilingual

- Claude Opus 4.5: 54.5 (#45)
- Inkling-Small: 51.7 (#102)

| Benchmark | Claude Opus 4.5 | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1438 | 1400 |
| LMArena Chinese | 1470 | 1458 |
| LMArena French | 1471 | 1438 |
| LMArena German | 1449 | 1412 |
| LMArena Japanese | 1415 | 1399 |
| LMArena Korean | 1424 | 1355 |
| LMArena Russian | 1448 | 1392 |
| LMArena Spanish | 1455 | 1426 |

## Instruction Following

- Claude Opus 4.5: 77.7 (#20)
- Inkling-Small: 73.9 (#112)

| Benchmark | Claude Opus 4.5 | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1478 | 1397 |

## Long Context

- Claude Opus 4.5: 46.4 (#21)
- Inkling-Small: 42.7 (#113)

| Benchmark | Claude Opus 4.5 | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1480 | 1401 |
| CL-bench | 21.1% | — |

## Writing & Preference

- Claude Opus 4.5: 68.2 (#28)
- Inkling-Small: 59.8 (#102)

| Benchmark | Claude Opus 4.5 | Inkling-Small |
|---|---|---|
| LMArena Text | 1451 | 1413 |
| LMArena Creative Writing | 1445 | 1330 |
| EQ-Bench Creative Writing | 1687 | 1491 |
| LMArena Multi-Turn | 1466 | 1420 |

## FAQ

### Is Claude Opus 4.5 better than Inkling-Small?

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 46.5 on the Noometry Index. Inkling-Small costs 16× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

### Which is cheaper, Claude Opus 4.5 or Inkling-Small?

Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Claude Opus 4.5 lists at $5 and $25.

### Is Claude Opus 4.5 or Inkling-Small better for coding?

Claude Opus 4.5 scores higher on coding benchmarks: 55.4 versus 43.3 in the Noometry coding category.

### Which has the bigger context window?

Inkling-Small does, with 524K tokens against 200K.

### How many benchmarks do Claude Opus 4.5 and Inkling-Small share?

30 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and Inkling-Small has 33.