Navigate
AI BENCHY
Advertise here

DeepSeek V4 Pro (high) vs Nemotron 3 Ultra (medium)

DeepSeek V4 Pro (high) leads on average score with 7.7 vs 7.6. DeepSeek V4 Pro (high) has the lower benchmark cost at $0.476 vs $0.701. Nemotron 3 Ultra (medium) is faster at 33.62s vs 92.50s, with pass rates of 63.6% vs 66.7%.

Last updated at: 2026-09-04

Rank
#88
Total Output Tokens
209,444
Response Time (avg)
92.50s
Total Cost
$0.476
Rank
#93
Total Output Tokens
184,405
Response Time (avg)
33.62s
Total Cost
$0.701
Recommended model Nemotron 3 Ultra (medium)

Its score stays close to the best score here (7.6 vs 7.7), while responding about 2.8x faster than DeepSeek V4 Pro (high).

Detailed comparison

Metric DeepSeek V4 Pro DeepSeek V4 Pro high Release: 2026-04-24 Nemotron 3 Ultra Nemotron 3 Ultra medium Release: 2026-06-04 Free Available
Score 7.7 7.6
Rank #88 #93
Reliability 10.0 9.8
Consistency 7.7 8.8
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 63.6% 66.7%
Flaky tests 6 3
Total Runs 66 66
Cost per result 2.251 0.000
Total Cost $0.476 $0.701
Input Price $1.002 / 1M $0.625 / 1M
Output Price $2.004 / 1M $3.125 / 1M
Total Input Tokens 90,757 233,415
Output Tokens 22,928 54,384
Reasoning Tokens 186,516 130,021
Response Time (avg) 92.50s 33.62s
Response Time (max) 416.76s 392.56s
Response Time (total) 2035.01s 739.59s
Parameters 1.6T total (49B active) 550B total (55B active)
Availability Open source Weights available

Model generation showcase

Hamster playing table tennis

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

#88 DeepSeek V4 Pro

high
Cost
$0.023
Time
257.6s
Tokens
14,870 tok

#93 Nemotron 3 Ultra

medium
Reached the allocated time limit (300 seconds) without receiving showcase output.
Cost
$0.000
Time
300.0s
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
DeepSeek V4 Pro 6.3 8.7 33.3% 0 243.00s 5,090 383 84,580
Nemotron 3 Ultra 8.4 7.4 88.9% 1 26.53s 7,686 2,854 17,725

Quick Compare

Switch Comparison Pair