AI BENCHY
AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com
#91

Mercury 2.5 Preview

Inception Release: 2026-09-02 Tested on: 2026-09-02 02:06 inception/mercury-2.5-preview::medium
~100BOtherClosedEstimated
(high) (medium) (low) (none)

Summary

Mercury 2.5 Preview scores 7.5 on AI BENCHY and ranks #91. It has 10.0 reliability, a 69.7% pass rate, $0.024 total cost, and 3.58s average response time.

What makes Mercury 2.5 Preview unique: It stands out most in Anti-AI Tricks, where it ranks #1, while Tool Calling is its weakest area at #16. Its total benchmark cost is unusually low for its score range. It is notably fast compared with similar models.

Model facts

Researched on 2026-09-02

Estimated
Parameters
~100B
Architecture
Other
Availability
Closed
License
-

Best estimate from public evidence; the vendor did not disclose every value. Inception identifies Mercury 2.5 as a diffusion LLM but does not disclose its parameter count; the estimate follows the Mercury 2 family record.

Parameter source Availability source

Score

7.5

Consistency

9.6

Reliability

10.0

Total Cost (Current Price)

$0.024

Total Output Tokens

127,034

Total Input Tokens

112,713

Input Price

$0.040 / 1M

Output Price

$0.150 / 1M

Tests Correct

Wrong Tests: 7

Attempt pass rate: 69.7%

Flaky tests

1

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

3.58s

Response Time (max): 17.84s

Response Time (total): 78.66s

Wrong answer: 4 API error: 1 Did not follow instructions: 1 No answer: 1

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#91 Mercury 2.5 Preview

medium
Cost
$0.001
Time
2.7s
Tokens
2,241 tok

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Mercury 2.5 PreviewmediumvsQwen3.5-27BmediumMercury 2.5 PreviewmediumvsGPT-5.4 MinimediumMercury 2.5 PreviewmediumvsQwen3.5 Plus 2026-02-15mediumMercury 2.5 PreviewmediumvsGrok Build 0.1mediumMercury 2.5 PreviewmediumvsGPT 5.3 ChatnoneMercury 2.5 PreviewmediumvsGemini 3.1 Flash Lite PreviewmediumMercury 2.5 PreviewmediumvsMiniMax M3mediumMercury 2.5 PreviewmediumvsQwen3.7 MaxnoneMercury 2.5 PreviewmediumvsGPT-5.6 TerralowMercury 2.5 PreviewmediumvsKimi K2.7 Codemedium

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 10.0 10.0
Coding 7.8 10.0
Combined 6.5 10.0
Data parsing and extraction 10.0 10.0
Domain specific 5.3 7.2
General Intelligence 5.0 10.0
Instructions following 9.8 10.0
Puzzle Solving 10.0 10.0
Tool Calling 3.0 10.0
Trivia 3.0 10.0

Compared models