llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model DirectoryCompare Models

Scoring & Data

Scoring & Data
393 models668 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll BenchmarksReasoningMath

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai

Poolside model product

Laguna S 2.1

1 model: an open-weight Mixture-of-Experts coding model with 118B total parameters and 8B activated per token (256 routed experts + 1 shared; 48 layers).

Updated Aug 17, 2026. Default version: Laguna S 2.1

Compare
LLMBoard Score69.8Laguna S 2.1
Coverage20%5 benchmark families
Context window1MTokens
Official input priceN/AOfficial price unavailable

On this page

  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Runtime
  • Specification
  • Versions
  • Compare
  • Similar models
  • About
  • FAQ

Laguna S 2.1 Capability Profile

This profile uses the model's current scored version. Arena ratings and prices are shown separately.

Laguna S 2.1 LLMBoard score breakdown

Laguna S 2.1 Benchmark Results

Benchmark scores for Laguna S 2.1.

6 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkSWE Atlas - Codebase QnAScore46.2%Rank01Participants2Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkSWE-bench MultilingualScore78.5%Rank03Participants38Percentile94.6%EvidenceCEvaluatedAug 17, 2026
BenchmarkSWE-Bench ProScore59.4%Rank15Participants50Percentile71.4%EvidenceCEvaluatedAug 17, 2026
BenchmarkTerminal-Bench 2.1Score70.2%Rank19Participants28Percentile33.3%EvidenceCEvaluatedAug 17, 2026
BenchmarkToolathlonScore49.7%Rank19Participants37Percentile50.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkDeepSWE 1.1Score40.4%Rank21Participants25Percentile16.7%EvidenceCEvaluatedAug 17, 2026

Laguna S 2.1 Arena Results

Preference and agent-evaluation results for the default version.

No Arena results

The default version does not have a matching Arena result yet.

Laguna S 2.1 Pricing

Official vendor API pricing appears first, followed by individual provider offers.

Official API
N/A
Official provider
N/A
Lowest third-party
From $0.09 input, $0.18 output per 1M via OpenRouter
Tracked offerings
6
6 rows
Columns

Show columns

Sort by
Provider
Provider model ID
Region
Input / 1M
Output / 1M
Context
Updated
ProviderPoolsideProvider model IDpoolside/laguna-s-2.1RegionglobalInput / 1MN/AOutput / 1MN/AContext1MUpdatedAug 17, 2026
ProviderOpenRouterProvider model IDpoolside/laguna-s-2.1RegionglobalInput / 1M$0.09Output / 1M$0.18Context1MUpdatedAug 17, 2026
ProviderNanoGPTProvider model IDpoolside/laguna-s-2.1RegionglobalInput / 1M$0.10Output / 1M$0.20Context1MUpdatedAug 17, 2026
ProviderVercel AI GatewayProvider model IDpoolside/laguna-s-2.1RegionglobalInput / 1M$0.10Output / 1M$0.20Context1MUpdatedAug 17, 2026
ProviderKilo GatewayProvider model IDpoolside/laguna-s-2.1RegionglobalInput / 1M$0.10Output / 1M$0.20Context1MUpdatedAug 17, 2026
ProviderPioneerProvider model IDpoolside/laguna-s-2.1RegionglobalInput / 1M$0.10Output / 1M$0.20Context1MUpdatedAug 17, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

Laguna S 2.1 Runtime Performance

Provider-specific output speed and catalog latency for Laguna S 2.1. Runtime does not affect the capability score.

No runtime data

No provider-specific speed or latency record is linked to the default version yet.

Browse runtime rankings

Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.

Laguna S 2.1 Specifications

Technical details for the model's default version.

Version
Laguna S 2.1
Released
Jul 21, 2026
Knowledge cutoff
Unknown
Parameters
118B
Context window
1M
Max output
32.8K
Inputs
text
Outputs
text
Open weights
Yes
License
OpenMDW License v1.1

Laguna S 2.1 Versions

Available versions of this model. The score column identifies the version used in the overall ranking.

1 rows
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionLaguna S 2.1ReleasedJul 21, 2026LLMBoard69.8Parameters118BContext1MMax output32.8KOpen weightsYesLicenseOpenMDW License v1.1

Laguna S 2.1 vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

Laguna S 2.1vsMiniMax M3Laguna S 2.1vsHy3Laguna S 2.1vsGPT-5.2Laguna S 2.1vsClaude Opus 4.5Laguna S 2.1vsGLM 5.1Laguna S 2.1vsSeed 2.0 Pro

Models similar to Laguna S 2.1

Recommendations prioritize the same model type and family, then the closest LLMBoard score.

#131-28.9
PO

Laguna XS 2.1

Poolside

40.9 LLMBoard

DetailsCompare
#40+0.2
OP

GPT-5.2

OpenAI

70.0 LLMBoard

DetailsCompare
#42-0.5
AN

Claude Opus 4.5

Anthropic

69.3 LLMBoard

DetailsCompare
#43-0.5
ZA

GLM 5.1

Zhipu AI

69.3 LLMBoard

DetailsCompare
#44-0.8
BY

Seed 2.0 Pro

ByteDance

69.0 LLMBoard

DetailsCompare
#39+0.9
TE

Hy3

Tencent

70.7 LLMBoard

DetailsCompare

What is Laguna S 2.1?

Key information about Laguna S 2.1 and its available data.

1 model: an open-weight Mixture-of-Experts coding model with 118B total parameters and 8B activated per token (256 routed experts + 1 shared; 48 layers).

It targets long-horizon and agentic coding with interleaved thinking, a 1,048,576-token context window in thinking and no-thinking modes, and text-to-text only modalities. 1).

Data as of 2026-08-17.

FAQ

Common questions about Laguna S 2.1.

When was Laguna S 2.1 released?

Laguna S 2.1's default version was released on Jul 21, 2026.

How much does Laguna S 2.1 cost?

No official standard PAYG price is currently available for Laguna S 2.1. The lowest tracked third-party offer starts at $0.09 input and $0.18 output via OpenRouter.

Who created Laguna S 2.1?

Laguna S 2.1 was created by Poolside.

What is the context window for Laguna S 2.1?

The default version has a 1M token context window.

Is Laguna S 2.1 open weight?

Yes. The default version is marked as open weight under OpenMDW License v1.1.

How many API providers offer Laguna S 2.1?

6 provider offerings are linked to the default version.

What models should I compare Laguna S 2.1 with?

Nearby ranked alternatives include MiniMax M3, Hy3, GPT-5.2.