Navigate
AI BENCHY
Advertise here

NVIDIA: Nemotron 3 Ultra vs Thinking Machines: Inkling

Nemotron 3 Ultra (medium) leads on average score with 7.5 vs 6.1. Inkling (low) has the lower benchmark cost at $0.187 vs $0.774. Inkling (low) is faster at 5.15s vs 32.21s, with pass rates of 68.2% vs 54.6%.

Recommended modelInkling (low)It offers the best overall trade-off: a competitive score (6.1), lower cost than Nemotron 3 Ultra (medium), and balanced response time.

Last updated at: 2026-07-18

Metric Nemotron 3 Ultra Nemotron 3 Ultra medium Release: 2026-06-04 Free Available Inkling Inkling low Release: 2026-07-18
Score 7.5 6.1
Rank #51 #119
Reliability 9.8 9.9
Consistency 8.5 8.6
Tests Correct
Attempt pass rate 68.2% 54.6%
Flaky tests 4 4
Total Runs 66 66
Cost per result 0.000 1.866
Total Cost $0.774 $0.187
Input Price $0.600 / 1M $1.000 / 1M
Output Price $3.600 / 1M $4.050 / 1M
Total Input Tokens 233,488 109,884
Output Tokens 57,916 8,579
Reasoning Tokens 128,062 10,343
Response Time (avg) 32.21s 5.15s
Response Time (max) 392.56s 41.58s
Response Time (total) 708.65s 113.39s

Hamster playing table tennis

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

#51 Nemotron 3 Ultra

medium
Invalid SVG
Cost
$0.000
Time
300.0s
Tokens
0 tok

#119 Thinking Machines: Inkling

low
Cost
$0.002
Time
6.1s
Tokens
502 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 Ultra 8.4 7.4 88.9% 1 26.53s 7,686 2,854 17,725
Inkling 5.1 7.2 22.2% 1 8.71s 7,374 355 4,961

Quick Compare

Switch Comparison Pair