Advertise here
#59

Mercury 2

Inception Release: 2026-02-24 Tested on: 2026-04-11 01:44 inception/mercury-2::medium
~100BOtherClosedEstimated
(medium) (none)

Summary

Mercury 2 scores 6.5 on AI BENCHY and ranks #59. It has N/A reliability, a 53.7% pass rate, $0.047 total cost, and 2.21s average response time.

What makes Mercury 2 unique: Its total benchmark cost is unusually low for its score range. It is notably fast compared with similar models.

Model facts

Researched on 2026-08-12

Estimated
Parameters
~100B
Architecture
Other
Availability
Closed
License
-

Best estimate from public evidence; the vendor did not disclose every value. Diffusion transformer; parameter topology and count are undisclosed.

Parameter source Availability source

Score

6.5

Consistency

8.6

Reliability

N/A

Total Cost (Current Price)

$0.047

Total Output Tokens

52,305

Total Input Tokens

0

Input Price

$0.250 / 1M

Output Price

$0.750 / 1M

Cache Read Price

N/A

Cache Write Price

N/A

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 10

Attempt pass rate: 53.7%

Flaky tests

3

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

Response Time (avg)

2.21s

Response Time (max): 14.63s

Response Time (total): 37.51s

Wrong answer: 6 Did not follow instructions: 4

Hamster playing table tennis

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

#59 Mercury 2

medium
Cost
$0.002
Time
2.1s
Tokens
1,702 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-08-14 03:05 Re-test 7.0 10.0 $0.094 Compare
2026-07-16 23:14 New test added 7.0 10.0 $0.093 Compare
2026-06-04 14:27 New test added 6.6 10.0 $0.058 Compare
2026-05-22 00:40 Re-test 6.3 10.0 $0.055 Compare
2026-04-11 01:44 First recorded run 6.5 N/A $0.047 Current run

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 2mediumvsLongCat 2.0lowMercury 2mediumvsStep 3.7 FlashhighMercury 2mediumvsQwen3.7 FlashmediumMercury 2mediumvsBeam 1.0 501B A23BmediumMercury 2mediumvsGLM 5.2noneMercury 2mediumvsKAT-Coder-Pro V2.5lowMercury 2mediumvsGPT-5.5noneMercury 2mediumvsClaude Sonnet 5.5mediumMercury 2mediumvsGLM 5.3 FlashlowMercury 2mediumvsQwen3.6 35B A3Bmedium

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 6.9 9.9
Coding 10.0 10.0
Combined 10.0 10.0
Data parsing and extraction 7.3 5.9
Domain specific 2.9 7.2
General Intelligence 4.8 10.0
Instructions following 10.0 10.0
Puzzle Solving 3.9 7.5
Tool Calling 10.0 10.0

Compared models