Navigate
Advertise here

Granite 4.2 8B (medium) vs Inkling Small (medium)

Granite 4.2 8B (medium) leads on average score with 6.1 vs 6.0. Granite 4.2 8B (medium) has the lower benchmark cost at $0.029 vs $0.113. Inkling Small (medium) is faster at 6.03s vs 50.47s, with pass rates of 37.7% vs 50.7%.

Last updated at: 2026-10-16

Compared models

Rank
#267
Total Output Tokens
50,045
Response Time (avg)
50.47s
Total Cost
$0.029
Rank
#273
Total Output Tokens
56,269
Response Time (avg)
6.03s
Total Cost
$0.113
Recommended model Granite 4.2 8B (medium)

It has the best score here (6.1), while costing about 4.0x less than Inkling Small (medium).

Detailed comparison

Metric Granite 4.2 8B Granite 4.2 8B medium Release: 2026-09-02 Inkling Small Inkling Small medium Release: 2026-08-01 Free Available
Score 6.1 6.0
Rank #267 #273
Reliability 8.9 10.0
Consistency 9.7 9.1
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 37.7% 50.7%
Flaky tests 1 3
Total Runs 69 69
Cost per result 0.354 1.177
Total Cost $0.029 $0.113
Input Price $0.060 / 1M $0.450 / 1M
Output Price $0.250 / 1M $1.200 / 1M
Cache Read Price $0.015 / 1M $0.100 / 1M
Cache Write Price N/A N/A
Total Input Tokens 259,708 100,255
Output Tokens 16,567 6,422
Reasoning Tokens 33,580 49,847
Response Time (avg) 50.47s 6.03s
Response Time (max) 557.96s 17.26s
Response Time (total) 1160.91s 138.65s
Parameters 8B 276B total (12B active)
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.

#267 IBM: Granite 4.2 8B

medium
Provider returned error
Cost
$0.000
Time
0.2s
Tokens
0 tok

#273 Thinking Machines: Inkling Small

medium
Cost
$0.003
Time
13.4s
Tokens
1,753 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
Granite 4.2 8B 5.5 10.0 33.3% 0 12.09s 8,439 2,445 3,900
Inkling Small 7.8 10.0 66.7% 0 10.49s 7,374 434 13,783

Switch Comparison Pair