The AI arena is free today

Open Superagent

Laguna XS 2.1 vs Mercury 3

Mercury 3 leads the LLM Stats Score 36.1 to 23.9. Laguna XS 2.1 is 1.3x cheaper per token.

Poolside · Inception · Updated for 2026

Which is better?

Mercury 3 leads the overall LLM Stats Score 36.1 to 23.9, ranking #98 overall.

On price, Laguna XS 2.1 is roughly 1.3x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Mercury 3 also accepts a larger context window (1,000,000 input tokens), making it the stronger choice for long documents and large codebases.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Laguna XS 2.1

  • cost matters — it's about 1.3x cheaper per token
  • you need open weights you can self-host or fine-tune

Choose Mercury 3

  • overall performance matters — it scores 36.1 and ranks #98 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you process long inputs — it offers a 1,000,000 token context window
  • you want the most recent training data — it shipped Oct 2026

At a glance

The differences that matter most.

Core performance indexes
23.9
#188
36.1
#98
24.0
#181
34.8
#103
14.2
#157
21.5
#105
2.6
#189
19.4
#84
Cost, coverage & limits
Benchmark wins
—
—
Input price
$0.10 / M
$0.10 / M
Output price
$0.20 / M
$0.35 / M
Context window
262,144
1,000,000

Individual benchmarks

4 reported for Laguna XS 2.1 · 12 for Mercury 3

No common benchmarks found

Laguna XS 2.1 and Mercury 3don't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Laguna XS 2.1 costs less

For input processing, Laguna XS 2.1 ($0.10/1M tokens) costs the same as Mercury 3 ($0.10/1M tokens).

For output processing, Laguna XS 2.1 ($0.20/1M tokens) is 1.7x cheaper than Mercury 3 ($0.35/1M tokens).

In conclusion, Mercury 3 is more expensive than Laguna XS 2.1.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Fri Oct 23 2026 • llm-stats.com
Poolside
Laguna XS 2.1
Input tokens$0.10
Output tokens$0.20
Best providerPoolside
Inception
Mercury 3
Input tokens$0.10
Output tokens$0.35
Best providerInception
Notice missing or incorrect data?

Context Window

Maximum input and output token capacity

Mercury 3 accepts 1,000,000 input tokens compared to Laguna XS 2.1's 262,144 tokens. Only Mercury 3 specifies output context (131,072 tokens).

Poolside
Laguna XS 2.1
Input262,144 tokens
Output- tokens
Inception
Mercury 3
Input1,000,000 tokens
Output131,072 tokens
Fri Oct 23 2026 • llm-stats.com

License

Usage and distribution terms

Laguna XS 2.1 is licensed under OpenMDW License v1.1, while Mercury 3 uses a proprietary license.

License differences may affect how you can use these models in commercial or open-source projects.

Laguna XS 2.1

OpenMDW License v1.1

Open weights

Mercury 3

Proprietary

Closed source

Release Timeline

When each model was launched

Laguna XS 2.1 was released on 2026-07-02, while Mercury 3 was released on 2026-10-19.

Mercury 3 is 4 months newer than Laguna XS 2.1.

Laguna XS 2.1

Jul 2, 2026

3 months ago

Mercury 3

Oct 19, 2026

0 days ago

3mo newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Provider Availability

Laguna XS 2.1 is available from Poolside. Mercury 3 is available from Inception.

Laguna XS 2.1

poolside logo
Poolside
Input Price:Input: $0.10/1MOutput Price:Output: $0.20/1M

Mercury 3

inception logo
Inception
Input Price:Input: $0.10/1MOutput Price:Output: $0.35/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against Laguna XS 2.1 and Mercury 3 side-by-side, then vote on the output you prefer.

Laguna XS 2.1
✓ Preferred
Mercury 3
Open in Playground

FAQ

Common questions about Laguna XS 2.1 vs Mercury 3.

Which is better, Laguna XS 2.1 or Mercury 3?

Mercury 3 leads the LLM Stats Score 36.1 to 23.9. Laguna XS 2.1 is made by Poolside and Mercury 3 is made by Inception. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Laguna XS 2.1 compare to Mercury 3 in benchmarks?

Laguna XS 2.1 scores SWE-Bench Verified: 70.9%, SWE-bench Multilingual: 63.1%, SWE-Bench Pro: 47.6%, Terminal-Bench 2.0: 37.5%. Mercury 3 scores GPQA: 89.2%, AA-LCR: 77.7%, IFBench: 76.8%, MRCR v2: 75.5%, DeepSearchQA: 71.3%.

Is Laguna XS 2.1 cheaper than Mercury 3?

Both models cost $0.10 per million input tokens.

What are the context window sizes for Laguna XS 2.1 and Mercury 3?

Laguna XS 2.1 supports 262K tokens and Mercury 3 supports 1.0M tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Laguna XS 2.1 and Mercury 3?

Key differences include LLM Stats Score (23.9 vs 36.1), context window (262K vs 1.0M), licensing (OpenMDW License v1.1 vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes Laguna XS 2.1 and Mercury 3?

Laguna XS 2.1 is developed by Poolside and Mercury 3 is developed by Inception.