Navigate
Advertise here

North Mini Code (default) vs Granite 4.2 8B (high)

The average score is effectively tied at 4.7 vs 4.7. North Mini Code (default) has the lower benchmark cost at $0.000 vs $0.111. North Mini Code (default) is faster at 29.47s vs 235.35s, with pass rates of 17.4% vs 37.7%.

Last updated at: 2026-11-16

Compared models

Rank
#421
Total Output Tokens
26,954
Response Time (avg)
29.47s
Total Cost
$0.000
Rank
#423
Total Output Tokens
576,052
Response Time (avg)
235.35s
Total Cost
$0.111
Recommended model North Mini Code (default)

It has the best score here (4.7), while responding about 8.0x faster than Granite 4.2 8B (high).

Detailed comparison

Metric North Mini Code North Mini Code default Release: 2026-06-18 Free Available Granite 4.2 8B Granite 4.2 8B high Release: 2026-09-02
Score 4.7 4.7
Rank #421 #423
Reliability 8.9 8.2
Consistency 9.9 6.4
Attempts 63/69 69/69
Tests Correct
Attempt pass rate 17.4% 37.7%
Flaky tests 0 10
Total Runs 63 69
Cost per result 0.000 2.751
Total Cost $0.000 $0.111
Input Price $0.000 / 1M $0.060 / 1M
Output Price $0.000 / 1M $0.250 / 1M
Cache Read Price N/A $0.015 / 1M
Cache Write Price N/A N/A
Total Input Tokens 177,989 282,658
Output Tokens 26,954 198,563
Reasoning Tokens 0 462,804
Response Time (avg) 29.47s 235.35s
Response Time (max) 159.85s 685.87s
Response Time (total) 677.70s 5413.09s
Parameters 30B total (3B active) 8B
Availability Open source Open source

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.

#421 North Mini Code

default
Cost
$0.000
Time
266.1s
Tokens
63,551 tok

#423 IBM: Granite 4.2 8B

high
Provider returned error
Cost
$0.000
Time
0.2s
Tokens
0 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
North Mini Code 3.9 10.0 0.0% 0 21.96s 7,119 504 0
Granite 4.2 8B 3.8 4.3 33.3% 2 515.34s 7,047 42,438 154,749

Switch Comparison Pair