# Claude Opus 4.8 vs Inkling-Small

> Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 46.5 on the Noometry Index. Inkling-Small costs 16× less per token, which makes it the better buy when Claude Opus 4.8's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-opus-4-8-vs-inkling-small
- Last updated: 2026-10-10
- Shared benchmarks: 33

## Summary

- They share 33 benchmarks with published results for both. Claude Opus 4.8 scores higher in 9 categories and Inkling-Small in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 4.8 leads 78.2 to 44.9.
- The biggest single-benchmark swing is ProofBench: 69% for Claude Opus 4.8 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 4.8.
- Claude Opus 4.8 accepts more context: 1M tokens versus 524K.
- Inkling-Small has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Opus 4.8 | Inkling-Small |
|---|---|---|
| Provider | Anthropic | Thinking Machines Lab |
| Noometry Index | 60.7 | 46.5 |
| Rank | 9 | 57 |
| Context | 1M | 524K |
| Input $/M | $5 | $0.45 |
| Output $/M | $25 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Claude Opus 4.8: 60.2 (#9)
- Inkling-Small: 43.3 (#80)

| Benchmark | Claude Opus 4.8 | Inkling-Small |
|---|---|---|
| LMArena WebDev | 1556 | 1408 |
| SciCode | 53.5% | 48.7% |
| LMArena Coding | 1491 | 1451 |
| DeepSWE | 59% | — |
| FrontierCode | 46.5% | — |
| GSO | 47.1% | — |
| WeirdML | 82.9% | — |
| ALE-Bench | 1,564 | — |

## Agentic & Tool Use

- Claude Opus 4.8: 47.6 (#10)
- Inkling-Small: —

| Benchmark | Claude Opus 4.8 | Inkling-Small |
|---|---|---|
| APEX-Agents | 48.9% | — |
| OSWorld 2.0 | 20.6% | — |
| Remote Labor Index | 8.3% | — |
| τ²-bench Banking | 39.7% | — |
| DeepResearch Bench | 50.2% | — |
| PostTrainBench | 33.8% | — |
| GBAEval | 70.9% | — |
| GDP.pdf | 24% | — |
| LMArena Search | 1204 | — |
| Vending-Bench 2 | 5,787 | — |

## Reasoning

- Claude Opus 4.8: 64.6 (#14)
- Inkling-Small: 39.0 (#53)

| Benchmark | Claude Opus 4.8 | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | 72.1% | 40.1% |
| ARC-AGI-1 | 92.5% | 84% |
| CritPt | 20.9% | 8.3% |
| Chess Puzzles | 34% | 18% |
| LMArena Hard Prompts | 1481 | 1424 |
| Mystery Game Puzzles | 36% | 6% |
| Epoch Capabilities Index | 158.3 | 150.13 |
| SimpleBench | 64.8% | — |
| Kagi LLM Benchmark | 88.8% | — |
| NYT Connections (extended) | 91.1% | — |
| EnigmaEval | 23.5% | — |
| EBR-Bench | 28.6% | — |
| DTBench | 94.9% | — |
| LMCA | 57.5% | — |
| Surface Evolver Bench | 87.5% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 59.9 | — |

## Math

- Claude Opus 4.8: 78.2 (#11)
- Inkling-Small: 44.9 (#65)

| Benchmark | Claude Opus 4.8 | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 80% | 46.3% |
| FrontierMath Tier 4 | 56.1% | 17.1% |
| OTIS Mock AIME 2024-2025 | 98.3% | 90% |
| ProofBench | 69% | 6% |
| LMArena Math | 1487 | 1453 |
| MathArena Final-Answer Competitions | 91.8% | — |
| FrontierMath (Feb 2025 set) | 47.2% | — |
| FrontierMath Tier 4 (v1) | 31.3% | — |

## Knowledge

- Claude Opus 4.8: 61.3 (#26)
- Inkling-Small: 48.3 (#71)

| Benchmark | Claude Opus 4.8 | Inkling-Small |
|---|---|---|
| GPQA Diamond | 91% | 88.5% |
| SimpleQA Verified | 53% | 19.1% |
| LMArena Expert | 1501 | 1442 |

## Multimodal

- Claude Opus 4.8: 43.2 (#20)
- Inkling-Small: 38.4 (#59)

| Benchmark | Claude Opus 4.8 | Inkling-Small |
|---|---|---|
| LMArena Vision | 1295 | 1235 |
| Blueprint-Bench 2 | 14.5% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1475 | — |

## Multilingual

- Claude Opus 4.8: 55.4 (#31)
- Inkling-Small: 51.7 (#102)

| Benchmark | Claude Opus 4.8 | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1450 | 1400 |
| LMArena Chinese | 1509 | 1458 |
| LMArena French | 1482 | 1438 |
| LMArena German | 1470 | 1412 |
| LMArena Japanese | 1440 | 1399 |
| LMArena Korean | 1432 | 1355 |
| LMArena Russian | 1476 | 1392 |
| LMArena Spanish | 1470 | 1426 |

## Instruction Following

- Claude Opus 4.8: 77.6 (#22)
- Inkling-Small: 73.9 (#112)

| Benchmark | Claude Opus 4.8 | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1476 | 1397 |

## Long Context

- Claude Opus 4.8: 45.4 (#37)
- Inkling-Small: 42.7 (#113)

| Benchmark | Claude Opus 4.8 | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1482 | 1401 |

## Writing & Preference

- Claude Opus 4.8: 72.1 (#17)
- Inkling-Small: 59.8 (#102)

| Benchmark | Claude Opus 4.8 | Inkling-Small |
|---|---|---|
| LMArena Text | 1460 | 1413 |
| LMArena Creative Writing | 1453 | 1330 |
| EQ-Bench Creative Writing | 1840 | 1491 |
| LMArena Multi-Turn | 1476 | 1420 |
| EQ-Bench 4 | 1281 | — |

## FAQ

### Is Claude Opus 4.8 better than Inkling-Small?

Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 46.5 on the Noometry Index. Inkling-Small costs 16× less per token, which makes it the better buy when Claude Opus 4.8's lead doesn't matter for your workload.

### Which is cheaper, Claude Opus 4.8 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 4.8 lists at $5 and $25.

### Is Claude Opus 4.8 or Inkling-Small better for coding?

Claude Opus 4.8 scores higher on coding benchmarks: 60.2 versus 43.3 in the Noometry coding category.

### Which has the bigger context window?

Claude Opus 4.8 does, with 1M tokens against 524K.

### How many benchmarks do Claude Opus 4.8 and Inkling-Small share?

33 benchmarks have published results for both models. Claude Opus 4.8 has 65 scored results on Noometry and Inkling-Small has 33.