Navigate
AI BENCHY
Your ad here

AI BENCHY Compare

DeepSeek: DeepSeek V4 Pro vs HY3 Preview

Last updated at: 2026-04-24

Metric DeepSeek V4 Pro DeepSeek V4 Pro high Release: 2026-04-24 HY3 Preview HY3 Preview low Release: 2026-04-22 Free Available
Score 8.2 8.1
Rank #20 #24
Reliability N/A N/A
Consistency 9.6 9.5
Tests Correct
Attempt pass rate 74.1% 75.9%
Flaky tests 1 1
Total Runs 24 50
Cost per result 1.224 0.000
Total Cost $0.160 $0.000
Input Price $1.740 / 1M $0.000 / 1M
Output Price $3.480 / 1M $0.000 / 1M
Output Tokens 671 65,778
Reasoning Tokens 39,383 0
Response Time (avg) 71.21s 23.98s
Response Time (max) 351.99s 78.74s
Response Time (total) 1281.73s 407.72s

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

Anti-AI Tricks Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Pro 8.3 10.0 75.0% 0 26.93s 70 2,008
HY3 Preview 10.0 10.0 100.0% 0 16.61s 7,905 0
Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Pro 10.0 10.0 100.0% 0 93.00s 82 2,808
HY3 Preview 10.0 10.0 100.0% 0 27.94s 7,907 0
Combined Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Pro 10.0 10.0 100.0% 0 71.08s 134 2,163
HY3 Preview 10.0 10.0 100.0% 0 78.74s 12,975 0
Data parsing and extraction Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Pro 10.0 10.0 100.0% 0 63.00s 67 1,071
HY3 Preview 6.5 10.0 50.0% 0 5.85s 1,022 0
Domain specific Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Pro 5.3 10.0 33.3% 0 202.56s 11 25,343
HY3 Preview 5.9 7.2 55.6% 1 40.44s 23,121 0
General Intelligence Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Pro 5.0 10.0 0.0% 0 26.96s 51 734
HY3 Preview 10.0 10.0 100.0% 0 16.44s 2,185 0
Instructions following Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Pro 10.0 10.0 100.0% 0 14.60s 21 1,236
HY3 Preview 10.0 10.0 100.0% 0 15.98s 2,475 0
Puzzle Solving Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Pro 7.6 7.4 77.8% 1 69.69s 151 3,847
HY3 Preview 5.3 10.0 33.3% 0 13.73s 6,985 0
Tool Calling Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Pro 10.0 10.0 100.0% 0 11.05s 84 173
HY3 Preview 10.0 10.0 100.0% 0 17.84s 1,203 0

Quick Compare

Switch Comparison Pair