Grok-4.20 Beta Reasoning vs Mercury 3
Grok-4.20 Beta Reasoning and Mercury 3 are closely matched at 23.4 and 36.1 on the LLM Stats Score. Mercury 3 is 18.5x cheaper per token.
xAI · Inception · Updated for 2026
Which is better?
Grok-4.20 Beta Reasoning and Mercury 3 are closely matched on the overall LLM Stats Score at 23.4 and 36.1.
On price, Mercury 3 is roughly 18.5x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
Grok-4.20 Beta Reasoning also accepts a larger context window (2,000,000 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 Grok-4.20 Beta Reasoning
- you process long inputs — it offers a 2,000,000 token context window
Choose Mercury 3
- your work emphasizes reasoning — it leads those capability indexes
- cost matters — it's about 18.5x cheaper per token
- you want the most recent training data — it shipped Oct 2026
At a glance
The differences that matter most.
Individual benchmarks
1 reported for Grok-4.20 Beta Reasoning · 12 for Mercury 3
Grok-4.20 Beta Reasoning 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
For input processing, Grok-4.20 Beta Reasoning ($2.00/1M tokens) is 20.0x more expensive than Mercury 3 ($0.10/1M tokens).
For output processing, Grok-4.20 Beta Reasoning ($6.00/1M tokens) is 17.1x more expensive than Mercury 3 ($0.35/1M tokens).
In conclusion, Grok-4.20 Beta Reasoning is more expensive than Mercury 3.*
* Using a 3:1 ratio of input to output tokens
Context Window
Maximum input and output token capacity
Grok-4.20 Beta Reasoning accepts 2,000,000 input tokens compared to Mercury 3's 1,000,000 tokens. Mercury 3 can generate longer responses up to 131,072 tokens, while Grok-4.20 Beta Reasoning is limited to 30,000 tokens.
Input capabilities
Documented input modalities across available providers
Grok-4.20 Beta Reasoning supports multimodal inputs, whereas Mercury 3 does not.
Grok-4.20 Beta Reasoning can handle both text and other forms of data like images, making it suitable for multimodal applications.
Grok-4.20 Beta Reasoning
Mercury 3
License
Usage and distribution terms
Both models are licensed under proprietary licenses.
Both models have usage restrictions defined by their respective organizations.
Proprietary
Closed source
Proprietary
Closed source
Release Timeline
When each model was launched
Grok-4.20 Beta Reasoning was released on 2026-03-09, while Mercury 3 was released on 2026-10-19.
Mercury 3 is 7 months newer than Grok-4.20 Beta Reasoning.
Mar 9, 2026
7 months ago
Oct 19, 2026
6 days ago
7mo newerKnowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Provider Availability
Grok-4.20 Beta Reasoning is available from xAI. Mercury 3 is available from Inception.
Grok-4.20 Beta Reasoning
Mercury 3
Outputs Comparison
Judge for yourself.
Run your own prompts against Grok-4.20 Beta Reasoning and Mercury 3 side-by-side, then vote on the output you prefer.
FAQ
Common questions about Grok-4.20 Beta Reasoning vs Mercury 3.