# Laguna XS.2 vs XLM-R large (550M) (Belebele English fine-tuning)

> Side-by-side benchmark comparison for Laguna XS.2 and XLM-R large (550M) (Belebele English fine-tuning) across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/laguna-xs-2-vs-native-belebele-xlm-r-large-550m-english-fine-tuning
- Last updated: October 1, 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 Laguna XS.2 and XLM-R large (550M) (Belebele English fine-tuning).

## Summary

- Laguna XS.2 and XLM-R large (550M) (Belebele English fine-tuning) 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 | Laguna XS.2 | XLM-R large (550M) (Belebele English fine-tuning) |
|----------|----------|----------|
| Creator | Poolside | Belebele authors |
| Type | Open Weight | Research system |
| Reasoning | Reasoning | Unspecified |
| Context | 256K | null |
| Independent public score (not head-to-head) | null | null |
| Benchmarks Covered | 10 | 0 |
| Pricing (input/output) | $0.00 / $0.00 | Pricing unavailable / Pricing unavailable |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Laguna XS.2 public-lane score: Coming soon
- XLM-R large (550M) (Belebele English fine-tuning) public-lane score: Coming soon

| Benchmark | Laguna XS.2 | XLM-R large (550M) (Belebele English fine-tuning) | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 35.7% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 25.8% | Coming soon | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Laguna XS.2 public-lane score: 24.1 (Supported · #109/144)
- XLM-R large (550M) (Belebele English fine-tuning) public-lane score: Coming soon

| Benchmark | Laguna XS.2 | XLM-R large (550M) (Belebele English fine-tuning) | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 69.9% | Coming soon | Coming soon |
| SWE Multilingual | 57.7% | Coming soon | Coming soon |
| SWE-bench Pro | 46.3% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | 35.7% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 67.8% | Coming soon | Coming soon |
| SWE-bench (Vals) | 55.2% | Coming soon | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Laguna XS.2 public-lane score: Coming soon
- XLM-R large (550M) (Belebele English fine-tuning) public-lane score: Coming soon

| Benchmark | Laguna XS.2 | XLM-R large (550M) (Belebele English fine-tuning) | Winner |
|-----------|-----------|-----------|--------|
| GPQA Diamond (Vals) | 55.1% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 69.1% | Coming soon | Coming soon |

## FAQ

### Can I compare Laguna XS.2 and XLM-R large (550M) (Belebele English fine-tuning) 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

- [Laguna XS.2 vs Laguna S 2.1](/compare/laguna-s-2-1-vs-laguna-xs-2)
- [XLM-R large (550M) (Belebele English fine-tuning) vs Laguna S 2.1](/compare/laguna-s-2-1-vs-native-belebele-xlm-r-large-550m-english-fine-tuning)
- [Laguna XS.2 vs Laguna M.1](/compare/laguna-m-1-vs-laguna-xs-2)
- [XLM-R large (550M) (Belebele English fine-tuning) vs Laguna M.1](/compare/laguna-m-1-vs-native-belebele-xlm-r-large-550m-english-fine-tuning)

## Explore More

- [Laguna XS.2 profile](/models/laguna-xs-2)
- [XLM-R large (550M) (Belebele English fine-tuning) profile](/models/native-belebele-xlm-r-large-550m-english-fine-tuning)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)