Navigate
AI BENCHY
Advertise here

DeepSeek V3.2 (medium) vs Mercury 2 (medium)

The average score is effectively tied at 7.0 vs 7.0. DeepSeek V3.2 (medium) has the lower benchmark cost at $0.078 vs $0.094. Mercury 2 (medium) is faster at 2.95s vs 68.43s, with pass rates of 65.2% vs 53.0%.

Last updated at: 2026-09-02

Rank
#128
Total Output Tokens
128,787
Response Time (avg)
68.43s
Total Cost
$0.078
Rank
#131
Total Output Tokens
87,554
Response Time (avg)
2.95s
Total Cost
$0.094
Recommended model Mercury 2 (medium)

It has the best score here (7.0), while responding about 23.2x faster than DeepSeek V3.2 (medium).

Detailed comparison

Metric DeepSeek V3.2 DeepSeek V3.2 medium Release: 2025-12-01 Mercury 2 Mercury 2 medium Release: 2026-02-24
Score 7.0 7.0
Rank #128 #131
Reliability 10.0 10.0
Consistency 7.4 8.4
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 65.2% 53.0%
Flaky tests 7 4
Total Runs 66 66
Cost per result 0.672 0.933
Total Cost $0.078 $0.094
Input Price $0.269 / 1M $0.250 / 1M
Output Price $0.400 / 1M $0.750 / 1M
Total Input Tokens 101,056 110,515
Output Tokens 11,832 10,325
Reasoning Tokens 116,955 77,229
Response Time (avg) 68.43s 2.95s
Response Time (max) 376.10s 14.63s
Response Time (total) 1505.53s 61.89s
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.

#128 DeepSeek V3.2

medium
Cost
$0.001
Time
53.6s
Tokens
1,932 tok

#131 Mercury 2

medium
Cost
$0.002
Time
2.1s
Tokens
1,702 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 6.0 7.2 55.6% 1 248.68s 5,717 649 52,014
Mercury 2 8.2 7.7 77.8% 1 2.04s 7,065 296 11,328

Quick Compare

Switch Comparison Pair