Navigate
AI BENCHY
Your ad here

AI BENCHY Compare

DeepSeek: DeepSeek V4 Flash vs HY3 Preview

Last updated at: 2026-04-24

Metric DeepSeek V4 Flash DeepSeek V4 Flash none Release: 2026-04-24 HY3 Preview HY3 Preview high Release: 2026-04-22 Free Available
Score 5.3 8.5
Rank #89 #9
Consistency 9.1 8.8
Tests Correct
Attempt pass rate 33.3% 81.5%
Flaky tests 2 3
Total Runs 54 50
Cost per result 0.147 0.000
Total Cost $0.008 $0.000
Input Price $0.140 / 1M $0.000 / 1M
Output Price $0.280 / 1M $0.000 / 1M
Output Tokens 4,444 238,920
Reasoning Tokens 0 0
Response Time (avg) 29.39s 55.19s
Response Time (max) 111.96s 149.94s
Response Time (total) 529.10s 938.23s

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 3.0 10.0 0.0% 0 20.18s 174 0
HY3 Preview 10.0 10.0 100.0% 0 32.69s 26,550 0
Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Flash 6.3 10.0 0.0% 0 24.04s 471 0
HY3 Preview 10.0 10.0 100.0% 0 99.76s 38,167 0
Combined Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Flash 4.5 2.1 66.7% 1 111.96s 2,664 0
HY3 Preview 10.0 10.0 100.0% 0 113.09s 31,319 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 23.79s 195 0
HY3 Preview 6.5 10.0 50.0% 0 12.11s 4,323 0
Domain specific Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Flash 5.3 10.0 33.3% 0 19.73s 18 0
HY3 Preview 5.3 7.2 44.4% 1 109.04s 87,559 0
General Intelligence Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Flash 4.2 9.9 0.0% 0 23.74s 67 0
HY3 Preview 10.0 10.0 100.0% 0 24.31s 5,490 0
Instructions following Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Flash 6.5 10.0 50.0% 0 17.54s 321 0
HY3 Preview 8.5 6.8 83.3% 1 34.02s 13,331 0
Puzzle Solving Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Flash 3.1 7.3 11.1% 1 22.96s 207 0
HY3 Preview 9.0 7.9 88.9% 1 28.07s 21,811 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 77.93s 327 0
HY3 Preview 10.0 10.0 100.0% 0 78.83s 10,370 0

Quick Compare

Switch Comparison Pair