Navigate
AI BENCHY
Advertise here

NVIDIA: Nemotron 3 Super vs Thinking Machines: Inkling

Nemotron 3 Super (medium) leads on average score with 5.7 vs 5.2. Nemotron 3 Super (medium) has the lower benchmark cost at $0.066 vs $0.147. Inkling is faster at 3.50s vs 51.99s, with pass rates of 40.9% vs 28.8%.

Recommended modelNemotron 3 Super (medium)It has the best score here (5.7), while costing about 2.2x less than Inkling.

Last updated at: 2026-07-18

Metric Nemotron 3 Super Nemotron 3 Super medium Release: 2026-03-11 Free Available Inkling Inkling none Release: 2026-07-18
Score 5.7 5.2
Rank #136 #160
Reliability 8.7 9.9
Consistency 8.9 9.6
Tests Correct
Attempt pass rate 40.9% 28.8%
Flaky tests 3 1
Total Runs 66 66
Cost per result 0.004 2.448
Total Cost $0.066 $0.147
Input Price $0.210 / 1M $1.000 / 1M
Output Price $0.455 / 1M $4.050 / 1M
Total Input Tokens 81,429 104,111
Output Tokens 18,371 10,551
Reasoning Tokens 98,853 0
Response Time (avg) 51.99s 3.50s
Response Time (max) 431.98s 48.02s
Response Time (total) 1039.89s 77.09s

Hamster playing table tennis

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

#136 Nemotron 3 Super

medium
Cost
$0.000
Time
272.6s
Tokens
5,296 tok

#160 Thinking Machines: Inkling

none
Provider returned error
Cost
$0.000
Time
5.3s
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
Nemotron 3 Super 3.1 10.0 0.0% 0 147.32s 2,275 797 4,424
Inkling 4.5 10.0 0.0% 0 1.01s 7,356 436 0

Quick Compare

Switch Comparison Pair