Coding
Like-for-like- Laguna M.1
- 29.7
- Supported · #140/151
- Laguna XS.2
- 24.7
- Supported · #148/151
- Basis
- BenchAlign lane · 6 vs 6 public rows
- Reading
- Laguna M.1 leads · intervals overlap
Laguna M.1 vs Laguna XS.2
Updated September 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload. This is a same-family comparison, so migration details appear when the source data supports them.
Decision reading
Laguna M.1 has the higher public score estimate, 3.93 versus 1.53, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
10 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Share or export
Which one for your work
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Coding work
Code generation, repair, and software-engineering tasks
Laguna M.1
Laguna M.1 leads on the public coding lane, 29.7 to 24.7, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Show secondary and unsupported calls
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Laguna M.1 and Laguna XS.2 are scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limited
Long documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented
Chat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Repository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
10 Shared
- Shared results
- 10
- Laguna M.1 only
- 0
- Laguna XS.2 only
- 0
- Like-for-like categories
- 1 / 8
2 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.
Agentic
Directional only- Laguna M.1
- 23.9
- Estimated · #147/152
- Laguna XS.2
- 22.4
- Estimated · #149/152
- Basis
- BenchAlign lane · 2 vs 2 public rows
- Reading
- Directional only
Knowledge
Directional only- Laguna M.1
- 18.6
- Estimated · #182/183
- Laguna XS.2
- 17.7
- Estimated · #183/183
- Basis
- BenchAlign lane · 2 vs 2 public rows
- Reading
- Directional only
Reasoning
Not comparable- Laguna M.1
- Not ranked
- Laguna XS.2
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Laguna M.1
- Not ranked
- Laguna XS.2
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Laguna M.1
- Not ranked
- Laguna XS.2
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Laguna M.1
- Not ranked
- Laguna XS.2
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Laguna M.1
- Not ranked
- Laguna XS.2
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Laguna M.1 | Laguna XS.2 | Basis | Reading |
|---|---|---|---|---|
| Coding | 29.7Supported · #140/151 | 24.7Supported · #148/151 | Like-for-likeBenchAlign lane · 6 vs 6 public rows | Laguna M.1 leads · intervals overlap |
| Agentic | 23.9Estimated · #147/152 | 22.4Estimated · #149/152 | Directional onlyBenchAlign lane · 2 vs 2 public rows | Directional only |
| Knowledge | 18.6Estimated · #182/183 | 17.7Estimated · #183/183 | Directional onlyBenchAlign lane · 2 vs 2 public rows | Directional only |
| Reasoning | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
Shape of the matched evidence
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
Terminal-Bench 2.0
Agentic
SWE Multilingual
Coding
SWE-bench Verified
Coding
SWE-bench Pro
Coding
LiveCodeBench (Vals)
Coding
What each workload costs
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
Chat turn
1K fresh input + 500 output tokens
- Laguna M.1
- API rate not published
- Fits in one request
- Laguna XS.2
- Self-hosted; infrastructure cost varies
- Fits in one request
Laguna M.1 has no comparable published API token rate. Laguna XS.2 has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Laguna M.1
- API rate not published
- Fits in one request
- Laguna XS.2
- Self-hosted; infrastructure cost varies
- Fits in one request
Laguna M.1 has no comparable published API token rate. Laguna XS.2 has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Laguna M.1
- API rate not published
- Fits in one request
- Cached-input rate unavailable
- Laguna XS.2
- Self-hosted; infrastructure cost varies
- Fits in one request
- Cached-input rate unavailable
Laguna M.1 has no comparable published API token rate. Laguna XS.2 has no comparable published API token rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationLaguna M.1Laguna XS.2
Context window
Maximum documented context; output-token limits may be lower.
Laguna M.1
256K
Laguna XS.2
256K
API model ID
Laguna M.1
Not sourced
Laguna XS.2
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Laguna M.1
No comparable hosted API rate
Laguna XS.2
No comparable hosted API rate
Documented inputs
Laguna M.1
Not sourced
Laguna XS.2
Not sourced
Documented outputs
Laguna M.1
Not sourced
Laguna XS.2
Not sourced
Provider availability
Laguna M.1
Not sourced
Laguna XS.2
Not sourced
Reasoning profile
Laguna M.1
Reasoning
Laguna XS.2
Reasoning
Weight access
Laguna M.1
Proprietary
Laguna XS.2
Open Weight
License
Laguna M.1
Proprietary
Laguna XS.2
Open Weight
Release date
Laguna M.1
2026-04-28
Laguna XS.2
2026-04-28
If you are choosing between sibling variants
- Deployment change
- Both entries list Poolside as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
- Quality signal
- Laguna M.1 has the higher public score estimate, 3.93 versus 1.53, but the 90% score intervals overlap.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- Both models list 256K.
Run the same representative tasks against both endpoints before changing production traffic.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence10 rows
Agentic
Terminal-Bench 2.0
Shared sourceLaguna M.145.8%Laguna XS.235.7%Laguna M.1 leads this result
Terminal-Bench 2.1 (Vals)
Laguna M.134.1%SourceLaguna XS.225.8%SourceLaguna M.1 leads this result
Coding
SWE-bench Verified
Shared sourceLaguna M.174.6%Laguna XS.269.9%Laguna M.1 leads this result
SWE Multilingual
Shared sourceLaguna M.163.1%Laguna XS.257.7%Laguna M.1 leads this result
SWE-bench Pro
Shared sourceLaguna M.149.2%Laguna XS.246.3%Laguna M.1 leads this result
Terminal-Bench 2.0
Shared sourceLaguna M.145.8%Laguna XS.235.7%Laguna M.1 leads this result
LiveCodeBench (Vals)
Laguna M.168.1%SourceLaguna XS.267.8%SourceLaguna M.1 leads this result
SWE-bench (Vals)
Laguna M.157.6%SourceLaguna XS.255.2%SourceLaguna M.1 leads this result
Knowledge
Frequently asked questions
Which is better, Laguna M.1 or Laguna XS.2?
Laguna M.1 has the higher public score estimate, 3.93 versus 1.53, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, Laguna M.1 or Laguna XS.2?
Laguna M.1 leads the public coding lane, 29.7 to 24.7, with Supported evidence for both models, although the 90% intervals overlap.
Which is better for agentic tasks, Laguna M.1 or Laguna XS.2?
Laguna M.1 scores higher for agentic tasks on the public lane, 23.9 to 22.4. Laguna M.1 and Laguna XS.2 are scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which costs less, Laguna M.1 or Laguna XS.2?
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Which has the larger context window, Laguna M.1 or Laguna XS.2?
Both models list the same context window, 256K.
Related comparisons
Last updated September 10, 2026
Watch Laguna M.1 vs Laguna XS.2
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.