The AI arena is free today

Open Superagent

Claude Sonnet 5 vs Mercury 3

Claude Sonnet 5 leads the LLM Stats Score 47.2 to 36.1. Mercury 3 is 24.6x cheaper per token.

Anthropic · Inception · Updated for 2026

Which is better?

Claude Sonnet 5 leads the overall LLM Stats Score 47.2 to 36.1, ranking #36 overall.

On price, Mercury 3 is roughly 24.6x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

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

Choose Claude Sonnet 5

  • overall performance matters — it scores 47.2 and ranks #36 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes

Choose Mercury 3

  • cost matters — it's about 24.6x cheaper per token
  • you want the most recent training data — it shipped Oct 2026

At a glance

The differences that matter most.

Claude Sonnet 5
Anthropic
Mercury 3
Inception
Core performance indexes
LLM Stats Score
47.2
#36
36.1
#98
Reasoning
46.9
#29
34.8
#103
Coding
34.1
#36
21.5
#105
Agents
29.9
#49
19.4
#84
Cost, coverage & limits
Benchmark wins
—
—
Input price
$2.00 / M
$0.10 / M
Output price
$10.00 / M
$0.35 / M
Context window
1,000,000
1,000,000

Individual benchmarks

23 reported for Claude Sonnet 5 · 12 for Mercury 3

No common benchmarks found

Claude Sonnet 5 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

Mercury 3 costs less

For input processing, Claude Sonnet 5 ($2.00/1M tokens) is 20.0x more expensive than Mercury 3 ($0.10/1M tokens).

For output processing, Claude Sonnet 5 ($10.00/1M tokens) is 28.6x more expensive than Mercury 3 ($0.35/1M tokens).

In conclusion, Claude Sonnet 5 is more expensive than Mercury 3.*

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

Lowest available price from all providers
Thu Oct 29 2026 • llm-stats.com
Anthropic
Claude Sonnet 5
Input tokens$2.00
Output tokens$10.00
Best providerAnthropic
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

Both models have the same input context window of 1,000,000 tokens. Mercury 3 can generate longer responses up to 131,072 tokens, while Claude Sonnet 5 is limited to 64,000 tokens.

Anthropic
Claude Sonnet 5
Input1,000,000 tokens
Output64,000 tokens
Inception
Mercury 3
Input1,000,000 tokens
Output131,072 tokens
Thu Oct 29 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Claude Sonnet 5 supports multimodal inputs, whereas Mercury 3 does not.

Claude Sonnet 5 can handle both text and other forms of data like images, making it suitable for multimodal applications.

Claude Sonnet 5

Text
Images
Audio
Video

Mercury 3

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under proprietary licenses.

Both models have usage restrictions defined by their respective organizations.

Claude Sonnet 5

Proprietary

Closed source

Mercury 3

Proprietary

Closed source

Release Timeline

When each model was launched

Claude Sonnet 5 was released on 2026-06-30, while Mercury 3 was released on 2026-10-19.

Mercury 3 is 4 months newer than Claude Sonnet 5.

Claude Sonnet 5

Jun 30, 2026

3 months ago

Mercury 3

Oct 19, 2026

1 weeks 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

Claude Sonnet 5 is available from Anthropic, DeepInfra. Mercury 3 is available from Inception.

Claude Sonnet 5

anthropic logo
Anthropic
Input Price:Input: $2.00/1MOutput Price:Output: $10.00/1M
deepinfra logo
Deepinfra
Input Price:Input: $3.00/1MOutput Price:Output: $15.00/1M

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 Claude Sonnet 5 and Mercury 3 side-by-side, then vote on the output you prefer.

Claude Sonnet 5
✓ Preferred
Mercury 3
Open in Playground

FAQ

Common questions about Claude Sonnet 5 vs Mercury 3.

Which is better, Claude Sonnet 5 or Mercury 3?

Claude Sonnet 5 leads the LLM Stats Score 47.2 to 36.1. Claude Sonnet 5 is made by Anthropic 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 Claude Sonnet 5 compare to Mercury 3 in benchmarks?

Claude Sonnet 5 scores CharXiv-R: 88.3%, ChartMuseum: 86.7%, SWE-Bench Verified: 85.2%, BrowseComp: 84.7%, GDP.pdf: 81.6%. Mercury 3 scores GPQA: 89.2%, AA-LCR: 77.7%, IFBench: 76.8%, MRCR v2: 75.5%, DeepSearchQA: 71.3%.

Is Claude Sonnet 5 cheaper than Mercury 3?

Mercury 3 is 20.0x cheaper for input tokens. Claude Sonnet 5 costs $2.00/M input and $10.00/M output via anthropic. Mercury 3 costs $0.10/M input and $0.35/M output via inception.

What are the context window sizes for Claude Sonnet 5 and Mercury 3?

Claude Sonnet 5 supports 1.0M 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 Claude Sonnet 5 and Mercury 3?

Key differences include LLM Stats Score (47.2 vs 36.1), input pricing ($2.00 vs $0.10/M), multimodal support (yes vs no). See the full comparison above for benchmark-by-benchmark results.

Who makes Claude Sonnet 5 and Mercury 3?

Claude Sonnet 5 is developed by Anthropic and Mercury 3 is developed by Inception.

Related comparisons