# Inkling vs ScaleDown Extract

> Side-by-side benchmark comparison for Inkling and ScaleDown Extract across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/inkling-vs-scaledown-extract
- Last updated: October 13, 2026

- Shared sourced benchmarks: 0
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

No benchmark verdict yet: there is no shared sourced benchmark row for Inkling and ScaleDown Extract.

## Summary

- Inkling and ScaleDown Extract do not currently share a sourced benchmark row. The mirror therefore compares metadata, pricing, context windows, and each model's separately reported coverage without naming a benchmark winner.

## Model Snapshot

| Property | Inkling | ScaleDown Extract |
|----------|----------|----------|
| Creator | Thinking Machines Lab | ScaleDown |
| Type | Open Weight | Proprietary |
| Reasoning | Hybrid | Unspecified |
| Context | 1M | 1M |
| Independent public score (not head-to-head) | 52.11 | null |
| Benchmarks Covered | 24 | 0 |
| Pricing (input/output) | $1.87 / $4.68 | $0.05 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Inkling public-lane score: 36.2 (Supported · #72/123)
- ScaleDown Extract public-lane score: Coming soon

| Benchmark | Inkling | ScaleDown Extract | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 63.8% | Coming soon | Coming soon |
| BrowseComp | 77.1% | Coming soon | Coming soon |
| MCP Atlas | 74.1% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 47.6% | Coming soon | Coming soon |
| CWE-bench v1 | 37.0% | Coming soon | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Inkling public-lane score: 34.1 (Supported · #80/148)
- ScaleDown Extract public-lane score: Coming soon

| Benchmark | Inkling | ScaleDown Extract | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 77.6% | Coming soon | Coming soon |
| SWE-bench Pro | 54.3% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 63.8% | Coming soon | Coming soon |
| FrontierSWE v2 | 4.1% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 85.5% | Coming soon | Coming soon |
| SWE-bench (Vals) | 77.6% | Coming soon | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- Inkling public-lane score: 79 (#14/29)
- ScaleDown Extract public-lane score: Coming soon

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- Inkling public-lane score: 67.5 (#35/54)
- ScaleDown Extract public-lane score: Coming soon

| Benchmark | Inkling | ScaleDown Extract | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 73.5% | Coming soon | Coming soon |
| CharXiv | 82% | Coming soon | Coming soon |
| CharXiv w/o tools | 78.1% | Coming soon | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Inkling public-lane score: 54.2 (Supported · #62/180)
- ScaleDown Extract public-lane score: Coming soon

| Benchmark | Inkling | ScaleDown Extract | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 87.9% | Coming soon | Coming soon |
| GPQA-D | 87.9% | Coming soon | Coming soon |
| HLE | 46% | Coming soon | Coming soon |
| HLE w/o tools | 30% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 87.1% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 86.3% | Coming soon | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- Inkling public-lane score: 87.6 (#35/127)
- ScaleDown Extract public-lane score: Coming soon

| Benchmark | Inkling | ScaleDown Extract | Winner |
|-----------|-----------|-----------|--------|
| IFBench | 79.8% | Coming soon | Coming soon |

### Mathematics

- Winner: Insufficient shared evidence
- Inkling public-lane score: 58.3 (#11/12)
- ScaleDown Extract public-lane score: Coming soon

| Benchmark | Inkling | ScaleDown Extract | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | 97.1% | Coming soon | Coming soon |
| FrontierMath v2 (Tiers 1-3) | 33.333% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 4.878% | Coming soon | Coming soon |

## FAQ

### Can I compare Inkling and ScaleDown Extract on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but sourced benchmark coverage is still incomplete for a fair score-level comparison.

### Why does this page show "coming soon" values?

BenchLM only calls winners when public benchmark coverage is available on both sides of the comparison.

## Related Comparisons

- [Inkling vs Inkling-Small](/compare/inkling-vs-inkling-small)
- [ScaleDown Extract vs Inkling-Small](/compare/inkling-small-vs-scaledown-extract)
- [Inkling vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-inkling)
- [ScaleDown Extract vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-scaledown-extract)

## Explore More

- [Inkling profile](/models/inkling)
- [ScaleDown Extract profile](/models/scaledown-extract)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)