Navigate
Advertise here

DeepSeek V3.2 (medium) vs Mercury 2.5 (high)

Mercury 2.5 (high) leads on average score with 6.5 vs 6.3. Mercury 2.5 (high) has the lower benchmark cost at $0.044 vs $0.152. Mercury 2.5 (high) is faster at 7.62s vs 70.08s, with pass rates of 62.3% vs 59.4%.

Last updated at: 2026-11-22

Compared models

Rank
#329
Total Output Tokens
139,141
Response Time (avg)
70.08s
Total Cost
$0.152
Rank
#295
Total Output Tokens
193,676
Response Time (avg)
7.62s
Total Cost
$0.044
Recommended model Mercury 2.5 (high)

It has the best score here (6.5), while costing about 3.5x less than DeepSeek V3.2 (medium).

Detailed comparison

Metric DeepSeek V3.2 DeepSeek V3.2 medium Release: 2025-12-01 Mercury 2.5 Mercury 2.5 high Release: 2026-09-08
Score 6.3 6.5
Rank #329 #295
Reliability 10.0 9.8
Consistency 7.5 8.7
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 62.3% 59.4%
Flaky tests 7 4
Total Runs 69 69
Cost per result 1.250 0.362
Total Cost $0.152 $0.044
Input Price $0.280 / 1M $0.040 / 1M
Output Price $0.420 / 1M $0.150 / 1M
Cache Read Price $0.028 / 1M $0.004 / 1M
Cache Write Price N/A N/A
Total Input Tokens 306,662 358,562
Output Tokens 17,819 4,266
Reasoning Tokens 125,341 189,410
Response Time (avg) 70.08s 7.62s
Response Time (max) 376.10s 80.30s
Response Time (total) 1611.86s 175.36s
Parameters 671B total (37B active) ~100B
Availability Open source Closed

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

Model generation showcase

Hamster playing table tennis

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

#329 DeepSeek V3.2

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

#295 Mercury 2.5

high
Cost
$0.001
Time
3.5s
Tokens
2,447 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 2.5 6.4 7.8 44.4% 1 6.58s 7,757 415 44,012

Switch Comparison Pair