Navigate
AI BENCHY
Your ad here

AI BENCHY Compare

DeepSeek: DeepSeek V4 Flash vs HY3 Preview

Last updated at: 2026-04-27

Metric DeepSeek V4 Flash DeepSeek V4 Flash high Release: 2026-04-24 HY3 Preview HY3 Preview medium Release: 2026-04-22 Free Available
Score 7.8 8.1
Rank #41 #33
Reliability 10.0 N/A
Consistency 7.8 9.6
Tests Correct
Attempt pass rate 79.6% 74.1%
Flaky tests 5 1
Total Runs 54 54
Cost per result 0.277 0.000
Total Cost $0.031 $0.000
Input Price $0.140 / 1M $0.000 / 1M
Output Price $0.280 / 1M $0.000 / 1M
Output Tokens 1,765 65,057
Reasoning Tokens 90,299 0
Response Time (avg) 45.41s 14.63s
Response Time (max) 218.13s 46.04s
Response Time (total) 817.30s 248.72s

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 Flash 8.3 10.0 75.0% 0 28.51s 140 7,770
HY3 Preview 10.0 10.0 100.0% 0 6.59s 5,955 0
Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Flash 10.0 10.0 100.0% 0 62.48s 369 9,361
HY3 Preview 10.0 10.0 100.0% 0 31.37s 8,054 0
Combined Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Flash 10.0 10.0 100.0% 0 76.57s 465 7,347
HY3 Preview 10.0 10.0 100.0% 0 46.04s 12,018 0
Data parsing and extraction Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Flash 10.0 10.0 100.0% 0 28.03s 201 1,179
HY3 Preview 6.5 10.0 50.0% 0 5.25s 930 0
Domain specific Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Flash 4.1 4.4 44.5% 2 100.31s 27 59,249
HY3 Preview 5.3 10.0 33.3% 0 22.30s 22,527 0
General Intelligence Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Flash 6.1 3.1 66.7% 1 25.15s 79 632
HY3 Preview 10.0 10.0 100.0% 0 16.84s 2,448 0
Instructions following Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Flash 10.0 10.0 100.0% 0 15.36s 63 1,622
HY3 Preview 10.0 10.0 100.0% 0 6.16s 2,967 0
Puzzle Solving Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Flash 6.4 4.5 77.8% 2 25.53s 193 2,597
HY3 Preview 5.3 7.4 44.4% 1 9.55s 7,062 0
Tool Calling Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Flash 10.0 10.0 100.0% 0 74.73s 228 542
HY3 Preview 10.0 10.0 100.0% 0 15.02s 3,096 0

Quick Compare

Switch Comparison Pair