Navigate
AI BENCHY
Advertise here

AI BENCHY Compare

DeepSeek: DeepSeek V4 Pro vs Google: Gemini 3.5 Flash

Last updated at: 2026-05-22

Metric DeepSeek V4 Pro DeepSeek V4 Pro high Release: 2026-04-24 Gemini 3.5 Flash Gemini 3.5 Flash high Release: 2026-05-19
Score 6.6 9.6
Rank #80 #2
Reliability 9.0 10.0
Consistency 8.3 9.6
Tests Correct
Attempt pass rate 66.7% 96.7%
Flaky tests 4 1
Total Runs 60 60
Cost per result 1.927 5.231
Total Cost $0.212 $0.994
Input Price $0.435 / 1M $1.500 / 1M
Output Price $0.870 / 1M $9.000 / 1M
Output Tokens 12,211 1,969
Reasoning Tokens 53,774 102,679
Response Time (avg) 58.93s 8.30s
Response Time (max) 358.35s 34.82s
Response Time (total) 1119.75s 165.92s

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 7.4 10.0 75.0% 0 16.53s 71 3,617
Gemini 3.5 Flash 10.0 10.0 100.0% 0 2.57s 174 4,997
Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Pro 2.8 5.0 25.0% 1 51.77s 105 2,641
Gemini 3.5 Flash 10.0 10.0 100.0% 0 24.62s 450 34,170
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 65.02s 465 5,914
Gemini 3.5 Flash 10.0 10.0 100.0% 0 22.37s 351 16,323
Data parsing and extraction Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Pro 8.8 10.0 100.0% 0 23.62s 229 1,710
Gemini 3.5 Flash 10.0 10.0 100.0% 0 6.43s 279 8,466
Domain specific Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Pro 3.0 6.9 16.7% 1 205.66s 10,529 28,089
Gemini 3.5 Flash 7.6 7.2 77.8% 1 14.09s 12 24,721
General Intelligence Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Pro 6.1 3.1 66.7% 1 25.09s 76 1,152
Gemini 3.5 Flash 10.0 10.0 100.0% 0 3.63s 115 1,650
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 41.16s 205 2,416
Gemini 3.5 Flash 10.0 10.0 100.0% 0 3.35s 70 3,799
Puzzle Solving Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Pro 7.4 7.2 88.9% 1 34.92s 106 3,835
Gemini 3.5 Flash 10.0 10.0 100.0% 0 3.23s 241 4,940
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 21.33s 372 593
Gemini 3.5 Flash 9.8 10.0 100.0% 0 4.96s 265 1,608
Trivia Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
DeepSeek V4 Pro 3.0 10.0 0.0% 0 39.14s 53 3,807
Gemini 3.5 Flash 10.0 10.0 100.0% 0 3.94s 12 2,005

Quick Compare

Switch Comparison Pair