# Inkling vs Laguna XS.2

> Side-by-side benchmark comparison for Inkling and Laguna XS.2 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/inkling-vs-laguna-xs-2
- Last updated: October 14, 2026

- Shared sourced benchmarks: 7
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Pick Inkling if you want the stronger benchmark profile. Laguna XS.2 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Inkling leads overall 52.13 to 34.
- The clearest category separation is in coding, where the averages are 34 for Inkling and 21.9 for Laguna XS.2.
- The biggest single benchmark swing is GPQA Diamond (Vals) in Knowledge, with scores of 87.1% and 55.1%.
- Laguna XS.2 is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Inkling also has the larger context window at 1M.

## Model Snapshot

| Property | Inkling | Laguna XS.2 |
|----------|----------|----------|
| Creator | Thinking Machines Lab | Poolside |
| Type | Open Weight | Open Weight |
| Reasoning | Hybrid | Reasoning |
| Context | 1M | 256K |
| Overall Score | 52.13 | null |
| Benchmarks Covered | 24 | 10 |
| Pricing (input/output) | $1.87 / $4.68 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- Inkling public-lane score: 36.2 (Supported · #72/124)
- Laguna XS.2 public-lane score: Coming soon

| Benchmark | Inkling | Laguna XS.2 | 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% | 25.8% | Inkling |
| CWE-bench v1 | 37.0% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 35.7% | Coming soon |

### Coding

- Winner: Inkling
- Inkling public-lane score: 34 (Supported · #80/149)
- Laguna XS.2 public-lane score: 21.9 (Supported · #116/149)

| Benchmark | Inkling | Laguna XS.2 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 77.6% | 69.9% | Inkling |
| SWE-bench Pro | 54.3% | 46.3% | Inkling |
| Terminal-Bench 2.1 | 63.8% | Coming soon | Coming soon |
| FrontierSWE v2 | 4.1% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 85.5% | 67.8% | Inkling |
| SWE-bench (Vals) | 77.6% | 55.2% | Inkling |
| SWE Multilingual | Coming soon | 57.7% | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 35.7% | Coming soon |

### Reasoning

- Winner: Not comparable
- Inkling public-lane score: 79 (#14/29)
- Laguna XS.2 public-lane score: Coming soon

### Multimodal & Grounded

- Winner: Not comparable
- Inkling public-lane score: 67.5 (#35/54)
- Laguna XS.2 public-lane score: Coming soon

| Benchmark | Inkling | Laguna XS.2 | 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: Not comparable
- Inkling public-lane score: 54.5 (Supported · #62/181)
- Laguna XS.2 public-lane score: Coming soon

| Benchmark | Inkling | Laguna XS.2 | 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% | 55.1% | Inkling |
| MMLU-Pro (Vals) | 86.3% | 69.1% | Inkling |

### Instruction Following

- Winner: Not comparable
- Inkling public-lane score: 87.6 (#35/128)
- Laguna XS.2 public-lane score: Coming soon

| Benchmark | Inkling | Laguna XS.2 | Winner |
|-----------|-----------|-----------|--------|
| IFBench | 79.8% | Coming soon | Coming soon |

### Mathematics

- Winner: Not comparable
- Inkling public-lane score: 58.3 (#11/12)
- Laguna XS.2 public-lane score: Coming soon

| Benchmark | Inkling | Laguna XS.2 | 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

### Which is better overall, Inkling or Laguna XS.2?

Inkling is ahead overall on BenchLM right now.

### Where is the biggest gap between Inkling and Laguna XS.2?

The widest category gap is in coding, where the averages are 34 for Inkling and 21.9 for Laguna XS.2.

### How many benchmarks does Inkling cover on BenchLM?

Inkling currently has 24 sourced benchmark scores on BenchLM.

### How many benchmarks does Laguna XS.2 cover on BenchLM?

Laguna XS.2 currently has 10 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Inkling vs Inkling-Small](/compare/inkling-vs-inkling-small)
- [Laguna XS.2 vs Inkling-Small](/compare/inkling-small-vs-laguna-xs-2)
- [Inkling vs Laguna S 2.1](/compare/inkling-vs-laguna-s-2-1)
- [Laguna XS.2 vs Laguna S 2.1](/compare/laguna-s-2-1-vs-laguna-xs-2)

## Explore More

- [Inkling profile](/models/inkling)
- [Laguna XS.2 profile](/models/laguna-xs-2)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)