DeepSeek-V4-Flash-0731vsGemini 3.6 Flash

DeepSeek-V4-Flash-0731
Gemini 3.6 Flash
API pricing
Input price
$0.22$0.75
Output price
$0.66$3.75
Cached input price
$0.007$0.075
Cheapest input
$0.0352Baidu
Cheapest output
$0.10OpenInference
Benchmarks
BullshitBench v2
39%39%
Benchmarks
Gray Swan IPI · k = 1
7.3%
Gray Swan IPI · k = 10
32.2%
Gray Swan IPI · k = 15
37.3%
ProgramBench
0.5%
SWE-Bench Verified
79%
DeepSWE 1.1
49%
MLE-Bench
63.9%
Terminal-Bench 2.1
82.7%
Toolathlon-Verified
70.3%
BU Bench
68%
BrowseComp
73.2%
CyberGym
76.7%
Humanity's Last Exam · with tools
34.8%
OSWorld-Verified
83%
AutomationBench
25.1%
GDPval-AA v2
1421
threejseval
1423
Overview
CompanyDeepSeekGoogle
Release dateJul 31 2026Jul 21 2026
AccessProprietaryProprietary

Other comparisons

DeepSeek-V4-Flash-0731vsClaude Fable 5.1Gemini 3.6 FlashvsClaude Fable 5.1DeepSeek-V4-Flash-0731vsGPT-6 AstraGemini 3.6 FlashvsGPT-6 AstraDeepSeek-V4-Flash-0731vsMuse Spark 1.3Gemini 3.6 FlashvsMuse Spark 1.3DeepSeek-V4-Flash-0731vsGrok 4.6Gemini 3.6 FlashvsGrok 4.6DeepSeek-V4-Flash-0731vsMistral Medium 3.5Gemini 3.6 FlashvsMistral Medium 3.5DeepSeek-V4-Flash-0731vsKimi K3Gemini 3.6 FlashvsKimi K3

Frequently asked questions

DeepSeek-V4-Flash-0731 and Gemini 3.6 Flash are evenly matched across the 1 benchmark they both report (BullshitBench v2). DeepSeek-V4-Flash-0731 is cheaper on both input and output: $0.22 vs $0.75 per million input tokens, and $0.66 vs $3.75 per million output tokens. Figures are base-tier rates. Gemini 3.6 Flash shipped 10 days before DeepSeek-V4-Flash-0731, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On BullshitBench v2, both models score 39%.