Navigate
AI BENCHY
AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com

AI BENCHY Compare

DeepSeek: DeepSeek V4 Flash vs Gemini 3 PRO Preview

Summary

DeepSeek V4 Flash vs Gemini 3 PRO Preview benchmark comparison: DeepSeek V4 Flash leads on average score with 8.3 vs 6.2. DeepSeek V4 Flash has the lower benchmark cost at $0.027 vs $0.385. Gemini 3 PRO Preview is faster at 9.05s vs 45.85s, with pass rates of 74.6% vs 66.7%.

Recommended model: DeepSeek V4 Flash - It has the best score here (8.3), while costing about 14.7x less than Gemini 3 PRO Preview.

Last updated at: 2026-06-18

Metric DeepSeek V4 Flash DeepSeek V4 Flash high Release: 2026-04-24 Gemini 3 PRO Preview Gemini 3 PRO Preview medium Release: 2025-11-18
Score 8.3 6.2
Rank #23 #91
Reliability 10.0 N/A
Consistency 8.5 10.0
Tests Correct
Attempt pass rate 74.6% 66.7%
Flaky tests 4 0
Total Runs 63 63
Cost per result 0.299 1.406
Total Cost $0.027 $0.385
Input Price $0.090 / 1M $9.506 / 1M
Output Price $0.180 / 1M $9.506 / 1M
Total Input Tokens 39,745 28,848
Output Tokens 10,310 1,490
Reasoning Tokens 123,501 10,102
Response Time (avg) 45.85s 9.05s
Response Time (max) 218.13s 26.24s
Response Time (total) 962.79s 90.53s

Generation showcase

Hamster playing table tennis

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

#23 DeepSeek V4 Flash

high
Cost
$0.003
Time
93.1s
Tokens
7,926 tok

#91 Gemini 3 PRO Preview

medium
No endpoints found for google/gemini-3-pro-preview.
Cost
$0.000
Time
0.1s
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

Anti-AI Tricks Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Flash 8.3 10.0 75.0% 0 28.51s 540 140 7,770
Gemini 3 PRO Preview 10.0 10.0 100.0% 0 14.99s 500 149 1,485
Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Flash 7.8 10.0 66.7% 0 50.60s 7,279 395 34,862
Gemini 3 PRO Preview 3.0 10.0 0.0% 0 0ms 0 0 0
Combined Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Flash 10.0 10.0 100.0% 0 76.57s 14,016 465 7,347
Gemini 3 PRO Preview 3.0 10.0 0.0% 0 10.37s 13,211 351 952
Data parsing and extraction Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Flash 10.0 10.0 100.0% 0 28.03s 7,290 201 1,179
Gemini 3 PRO Preview 10.0 10.0 100.0% 0 10.84s 7,259 279 3,156
Domain specific Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Flash 4.1 4.4 44.5% 2 100.31s 666 27 59,249
Gemini 3 PRO Preview 5.3 10.0 33.3% 0 7.01s 643 15 1,195
General Intelligence Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Flash 6.1 3.1 66.7% 1 25.15s 471 79 632
Gemini 3 PRO Preview 10.0 10.0 100.0% 0 9.34s 486 78 374
Instructions following Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Flash 10.0 10.0 100.0% 0 15.36s 627 63 1,622
Gemini 3 PRO Preview 9.8 10.0 100.0% 0 3.26s 623 69 754
Puzzle Solving Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Flash 8.2 7.2 88.9% 1 26.11s 594 196 1,767
Gemini 3 PRO Preview 10.0 10.0 100.0% 0 3.88s 570 225 1,215
Tool Calling Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Flash 10.0 10.0 100.0% 0 74.73s 8,079 228 542
Gemini 3 PRO Preview 10.0 10.0 100.0% 0 11.96s 5,556 324 971
Trivia Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Flash 3.0 10.0 0.0% 0 54.46s 183 8,516 8,531
Gemini 3 PRO Preview 3.0 10.0 0.0% 0 0ms 0 0 0

Quick Compare

Switch Comparison Pair