Skip to content
ModelCap

Head-to-head comparison

Claude Haiku 4.5 vs Laguna XS.2

Claude Haiku 4.5 (Anthropic) and Laguna XS.2 (Poolside) compared on the ModelCap Index, API price, context window, provider availability, weight access and every public benchmark board they share. Figures are the same ones shown on the live rankings; nothing here is a hidden score.

Snapshot as of 9 September 2026

As of 9 September 2026, Claude Haiku 4.5 holds the stronger ModelCap Index position (#58 vs #60); and Laguna XS.2 ships open weights.

Which should you choose?

Choose Claude Haiku 4.5 if…

  • you want the stronger overall ModelCap Index position — #58 against #60 (55.1 vs 54.3 points).
  • you want provider choice — 4 listed API providers against 0.

Choose Laguna XS.2 if…

  • you want to self-host: Laguna XS.2 ships open weights while Claude Haiku 4.5 is api only.
  • you want the more recently listed model — Laguna XS.2 was listed 23 April 2026, Claude Haiku 4.5 15 October 2025.

Claude Haiku 4.5 vs Laguna XS.2: specs, pricing and context

Specification comparison of Claude Haiku 4.5 and Laguna XS.2
FieldClaude Haiku 4.5AnthropicLaguna XS.2Poolside
ModelCap Index position#58#60
Index score55.154.3
EvidenceMeasuredEstimated
Input price / 1M tokens$1.00Unlisted
Output price / 1M tokens$5.00Unlisted
Context window200K tokens— tokens
Max output tokens64K
API providers listed40
Weight accessAPI onlyOpen weights
Input modalitiesText, Image, FileText
First listed15 October 202523 April 2026
PublisherAnthropicPoolside

Evidence: 3 public benchmark observations across 3 boards · 4 reported rows against measured corpus ladders (62%); global-corpus-prior over 182 held-out anchors (38%); shrunk 0.5 toward the measured corpus. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.

Benchmark scores: Claude Haiku 4.5 vs Laguna XS.2

Public benchmark boards where Claude Haiku 4.5 or Laguna XS.2 has a published result
BoardClaude Haiku 4.5Laguna XS.2Leads
Arena codingArena (LMArena)14811476–1485Only one result
ARC-AGI-2ARC Prize Foundation4.0%ThinkingOnly one result
SWE-benchSWE-bench (Princeton / SWE-agent team)66.6%HighOnly one result
BFCL V4UC Berkeley (Gorilla)68.7Function callingOnly one result

Scores are the sources' own published figures for each model's best evaluated configuration; ModelCap never re-runs a benchmark.

Want a different pairing? Open the interactive comparison tool to swap either model for any current ranked language model.

Claude Haiku 4.5 vs Laguna XS.2: common questions

Is Claude Haiku 4.5 better than Laguna XS.2?

Claude Haiku 4.5 ranks higher on the ModelCap Index as of 9 September 2026: #58 against #60. That is a capability ranking built from public benchmark evidence with published uncertainty; whether it is "better" for you also depends on price, context and where you can run it. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.

Is Claude Haiku 4.5 cheaper than Laguna XS.2?

At least one of the two has no listed API price on ModelCap right now, so no price comparison is made.

Which has the bigger context window, Claude Haiku 4.5 or Laguna XS.2?

Both publish a 200K-token context window.

Which is better for coding, Claude Haiku 4.5 or Laguna XS.2?

The two models do not share a coding benchmark board on ModelCap yet, so no head-to-head coding score is published; the ModelCap Index position is the closest overall signal.

Are Claude Haiku 4.5 and Laguna XS.2 open-weight models?

Claude Haiku 4.5: API only. Laguna XS.2: Open weights. Open weights mean the checkpoint can be downloaded and self-hosted under its licence; API-only models are available solely through hosted endpoints.

Where can I run Claude Haiku 4.5 and Laguna XS.2?

ModelCap currently lists 4 API providers for Claude Haiku 4.5 and 0 for Laguna XS.2, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.

How current is this Claude Haiku 4.5 vs Laguna XS.2 comparison?

Every figure comes from the sealed ModelCap dataset published 9 September 2026; the page re-renders within a minute of each data refresh, and the ModelCap Index positions are the same ones shown on the live rankings.

Explore further