Navigate
AI BENCHY
Advertise here

DeepSeek V3.2 vs Mercury 2.5 Preview

DeepSeek V3.2 leads on average score with 5.0 vs 4.9. Mercury 2.5 Preview has the lower benchmark cost at $0.018 vs $0.054. Mercury 2.5 Preview is faster at 3.51s vs 17.89s, with pass rates of 36.4% vs 30.3%.

Last updated at: 2026-09-02

Rank
#256
Total Output Tokens
42,099
Response Time (avg)
17.89s
Total Cost
$0.054
Rank
#259
Total Output Tokens
82,585
Response Time (avg)
3.51s
Total Cost
$0.018
Recommended model Mercury 2.5 Preview

Its score stays close to the best score here (4.9 vs 5.0), while costing about 3.0x less than DeepSeek V3.2.

Detailed comparison

Metric DeepSeek V3.2 DeepSeek V3.2 none Release: 2025-12-01 Mercury 2.5 Preview Mercury 2.5 Preview none Release: 2026-09-02
Score 5.0 4.9
Rank #256 #259
Reliability 10.0 10.0
Consistency 8.1 8.3
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 36.4% 30.3%
Flaky tests 5 5
Total Runs 66 66
Cost per result 0.870 0.440
Total Cost $0.054 $0.018
Input Price $0.269 / 1M $0.040 / 1M
Output Price $0.400 / 1M $0.150 / 1M
Total Input Tokens 135,831 130,296
Output Tokens 42,099 82,585
Reasoning Tokens 0 0
Response Time (avg) 17.89s 3.51s
Response Time (max) 115.89s 60.70s
Response Time (total) 393.53s 77.28s
Parameters 671B total (37B active) ~100B
Availability Open source Closed

Model generation showcase

Hamster playing table tennis

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

#256 DeepSeek V3.2

none
Cost
$0.002
Time
7.0s
Tokens
1,046 tok

#259 Mercury 2.5 Preview

none
Invalid SVG
Cost
$0.001
Time
3.3s
Tokens
3,122 tok

Top Models by Score

Score vs Total Cost

Response Time (avg)

Score vs Response Time (avg)

Total Output Tokens

Score vs Total Output Tokens

Category Breakdown

Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V3.2 3.1 6.9 11.1% 1 14.54s 7,279 4,528 0
Mercury 2.5 Preview 4.7 7.9 22.2% 1 459ms 7,850 650 0

Quick Compare

Switch Comparison Pair