Navigate
Advertise here

Mercury 2.5 (high) vs Kimi K2.5 (medium)

Mercury 2.5 (high) leads on average score with 7.1 vs 7.0. Mercury 2.5 (high) has the lower benchmark cost at $0.031 vs $0.479. Mercury 2.5 (high) is faster at 4.32s vs 98.19s, with pass rates of 62.1% vs 63.6%.

Last updated at: 2026-09-10

Compared models

Rank
#138
Total Output Tokens
174,547
Response Time (avg)
4.32s
Total Cost
$0.031
Rank
#147
Total Output Tokens
220,942
Response Time (avg)
98.19s
Total Cost
$0.479
Recommended model Mercury 2.5 (high)

It has the best score here (7.1), while costing about 15.5x less than Kimi K2.5 (medium).

Detailed comparison

Metric Mercury 2.5 Mercury 2.5 high Release: 2026-09-08 Kimi K2.5 Kimi K2.5 medium Release: 2026-01-27
Score 7.1 7.0
Rank #138 #147
Reliability 9.7 10.0
Consistency 8.6 7.0
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 62.1% 63.6%
Flaky tests 4 8
Total Runs 66 66
Cost per result 0.259 4.849
Total Cost $0.031 $0.479
Input Price $0.040 / 1M $0.450 / 1M
Output Price $0.150 / 1M $2.250 / 1M
Total Input Tokens 120,068 118,496
Output Tokens 3,402 53,522
Reasoning Tokens 171,145 167,420
Response Time (avg) 4.32s 98.19s
Response Time (max) 23.63s 281.00s
Response Time (total) 95.06s 1571.05s
Parameters ~100B 1T total (32B active)
Availability Closed Weights available

Model generation showcase

Hamster playing table tennis

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

#138 Mercury 2.5

high
Cost
$0.001
Time
3.5s
Tokens
2,447 tok

#147 MoonshotAI: Kimi K2.5

medium
Cost
$0.030
Time
58.6s
Tokens
8,683 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
Mercury 2.5 6.4 7.8 44.4% 1 6.58s 7,757 415 44,012
Kimi K2.5 6.1 4.6 66.7% 2 217.49s 6,935 5,705 74,693

Quick Compare

Switch Comparison Pair