Navigate
AI BENCHY
Advertise here

DeepSeek V4 Pro (high) vs Gemini 3 Flash Preview (medium)

Gemini 3 Flash Preview (medium) leads on average score with 9.6 vs 7.7. DeepSeek V4 Pro (high) has the lower benchmark cost at $0.200 vs $0.742. Gemini 3 Flash Preview (medium) is faster at 19.20s vs 79.14s, with pass rates of 63.6% vs 98.5%.

Last updated at: 2026-07-25

Rank
#53
Total Output Tokens
189,181
Response Time (avg)
79.14s
Total Cost
$0.200
Rank
#3
Total Output Tokens
232,650
Response Time (avg)
19.20s
Total Cost
$0.742
Recommended model Gemini 3 Flash Preview (medium)

It has the best score here (9.6), while responding about 4.1x faster than DeepSeek V4 Pro (high).

Detailed comparison

Metric DeepSeek V4 Pro DeepSeek V4 Pro high Release: 2026-04-24 Gemini 3 Flash Preview Gemini 3 Flash Preview medium Release: 2025-12-17
Score 7.7 9.6
Rank #53 #3
Reliability 10.0 10.0
Consistency 7.7 9.7
Tests Correct
Attempt pass rate 63.6% 98.5%
Flaky tests 6 1
Total Runs 66 66
Cost per result 2.000 3.533
Total Cost $0.200 $0.742
Input Price $0.435 / 1M $0.500 / 1M
Output Price $0.870 / 1M $3.000 / 1M
Total Input Tokens 90,748 87,861
Output Tokens 10,462 5,486
Reasoning Tokens 178,719 227,164
Response Time (avg) 79.14s 19.20s
Response Time (max) 416.76s 117.26s
Response Time (total) 1740.97s 422.42s

Hamster playing table tennis

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

#53 DeepSeek V4 Pro

high
Cost
$0.023
Time
257.6s
Tokens
14,870 tok

#3 Gemini 3 Flash Preview

medium
Cost
$0.010
Time
18.4s
Tokens
3,351 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

Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 6.3 8.7 33.3% 0 243.00s 5,090 383 84,580
Gemini 3 Flash Preview 8.6 7.6 88.9% 1 84.40s 8,122 462 161,084

Quick Compare

Switch Comparison Pair