Navigate
Advertise here

Mercury 2.5 vs Grok 4.20

Grok 4.20 leads on average score with 4.1 vs 3.9. Mercury 2.5 has the lower benchmark cost at $0.016 vs $0.057. Grok 4.20 is faster at 1.11s vs 2.45s, with pass rates of 25.8% vs 27.3%.

Last updated at: 2026-09-08

Compared models

Rank
#312
Total Output Tokens
71,143
Response Time (avg)
2.45s
Total Cost
$0.016
Rank
#304
Total Output Tokens
1,923
Response Time (avg)
1.11s
Total Cost
$0.057
Recommended model Grok 4.20

It has the best score here (4.1), while responding about 2.2x faster than Mercury 2.5.

Detailed comparison

Metric Mercury 2.5 Mercury 2.5 none Release: 2026-09-08 Grok 4.20 Grok 4.20 none Release: 2026-03-31
Score 3.9 4.1
Rank #312 #304
Reliability 10.0 N/A
Consistency 7.5 8.1
Attempts 66/66 54/66
Tests Correct
Attempt pass rate 25.8% 27.3%
Flaky tests 7 0
Total Runs 66 54
Cost per result 0.782 1.570
Total Cost $0.016 $0.057
Input Price $0.040 / 1M $1.250 / 1M
Output Price $0.150 / 1M $2.500 / 1M
Total Input Tokens 123,740 41,313
Output Tokens 71,143 1,923
Reasoning Tokens 0 0
Response Time (avg) 2.45s 1.11s
Response Time (max) 36.48s 6.04s
Response Time (total) 53.83s 19.96s
Parameters ~100B ~1T total (~100B active)
Availability Closed Closed

Model generation showcase

Hamster playing table tennis

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

#312 Mercury 2.5

none
Cost
$0.001
Time
2.7s
Tokens
2,749 tok

#304 xAI: Grok 4.20

none
Cost
$0.004
Time
6.5s
Tokens
1,367 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 3.7 7.0 22.2% 1 12.50s 7,888 61,297 0
Grok 4.20 1.1 3.1 0.0% 0 1.22s 1,074 312 0

Quick Compare

Switch Comparison Pair