# Laguna M.1 vs Laguna XS.2

> Side-by-side benchmark comparison for Laguna M.1 and Laguna XS.2 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/laguna-m-1-vs-laguna-xs-2
- Last updated: September 10, 2026

- Shared sourced benchmarks: 10
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Pick Laguna M.1 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

- Laguna M.1 leads overall 3.93 to 1.53.
- The clearest category separation is in coding, where the averages are 29.7 for Laguna M.1 and 24.7 for Laguna XS.2.
- The biggest single benchmark swing is GPQA Diamond (Vals) in Knowledge, with scores of 27.0% and 55.1%.
- Laguna XS.2 is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.

## Model Snapshot

| Property | Laguna M.1 | Laguna XS.2 |
|----------|----------|----------|
| Creator | Poolside | Poolside |
| Type | Proprietary | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 256K | 256K |
| Overall Score | 3.93 | 1.53 |
| Benchmarks Covered | 10 | 10 |
| Pricing (input/output) | Pricing unavailable / Pricing unavailable | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Coming soon
- Laguna M.1 public-lane score: 23.9 (Estimated · #147/152)
- Laguna XS.2 public-lane score: 22.4 (Estimated · #149/152)

| Benchmark | Laguna M.1 | Laguna XS.2 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 45.8% | 35.7% | Laguna M.1 |
| Terminal-Bench 2.1 (Vals) | 34.1% | 25.8% | Laguna M.1 |

### Coding

- Winner: Laguna M.1
- Laguna M.1 public-lane score: 29.7 (Supported · #140/151)
- Laguna XS.2 public-lane score: 24.7 (Supported · #148/151)

| Benchmark | Laguna M.1 | Laguna XS.2 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 74.6% | 69.9% | Laguna M.1 |
| SWE Multilingual | 63.1% | 57.7% | Laguna M.1 |
| SWE-bench Pro | 49.2% | 46.3% | Laguna M.1 |
| Terminal-Bench 2.0 | 45.8% | 35.7% | Laguna M.1 |
| LiveCodeBench (Vals) | 68.1% | 67.8% | Laguna M.1 |
| SWE-bench (Vals) | 57.6% | 55.2% | Laguna M.1 |

### Knowledge

- Winner: Coming soon
- Laguna M.1 public-lane score: 18.6 (Estimated · #182/183)
- Laguna XS.2 public-lane score: 17.7 (Estimated · #183/183)

| Benchmark | Laguna M.1 | Laguna XS.2 | Winner |
|-----------|-----------|-----------|--------|
| GPQA Diamond (Vals) | 27.0% | 55.1% | Laguna XS.2 |
| MMLU-Pro (Vals) | 68.8% | 69.1% | Laguna XS.2 |

## FAQ

### Which is better overall, Laguna M.1 or Laguna XS.2?

Laguna M.1 is ahead overall on BenchLM right now.

### Where is the biggest gap between Laguna M.1 and Laguna XS.2?

The widest category gap is in coding, where the averages are 29.7 for Laguna M.1 and 24.7 for Laguna XS.2.

### How many benchmarks does Laguna M.1 cover on BenchLM?

Laguna M.1 currently has 10 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

- [Laguna M.1 vs Laguna S 2.1](/compare/laguna-m-1-vs-laguna-s-2-1)
- [Laguna XS.2 vs Laguna S 2.1](/compare/laguna-s-2-1-vs-laguna-xs-2)
- [Laguna M.1 vs Laguna XS 2.1](/compare/laguna-m-1-vs-laguna-xs-2-1)
- [Laguna XS.2 vs Laguna XS 2.1](/compare/laguna-xs-2-vs-laguna-xs-2-1)

## Explore More

- [Laguna M.1 profile](/models/laguna-m-1)
- [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)