DeepSeek-V4-FlashvsGemini 3.0 Flash

DeepSeek-V4-Flash
Gemini 3.0 Flash
API pricing
Cheapest input
$0.0679DigitalOcean$0.25Google AI Studio
Cheapest output
$0.1621StreamLake$1.50Google AI Studio
Benchmarks
GPQA Diamond
88.1%90.4%
Benchmarks
BullshitBench v2
18%
SWE-Bench Pro
49.6%
SWE-Bench Verified
78%
LiveCodeBench
91.6%
Terminal-Bench 2.1
58%
MCP Atlas
62%
Toolathlon
49.4%
Humanity's Last Exam · no tools
33.7%
ARC-AGI-2
33.6%
OSWorld-Verified
65.1%
Finance Agent v2
42.6%
GDPval-AA
1204
CharXiv Reasoning
80.3%
MMMU-Pro
81.2%
Blueprint-Bench 2
0%
MRCR v2 (8-needle) · 128k average
67.2%
MRCR v2 (8-needle) · 1M pointwise
22.1%
Overview
CompanyDeepSeekGoogle
Release dateApr 24 2026Dec 17 2025
AccessOpen WeightProprietary

Other comparisons

DeepSeek-V4-FlashvsClaude Fable 5.1Gemini 3.0 FlashvsClaude Fable 5.1DeepSeek-V4-FlashvsGPT-6 AstraGemini 3.0 FlashvsGPT-6 AstraDeepSeek-V4-FlashvsMuse Spark 1.3Gemini 3.0 FlashvsMuse Spark 1.3DeepSeek-V4-FlashvsGrok 4.6Gemini 3.0 FlashvsGrok 4.6DeepSeek-V4-FlashvsMistral Medium 3.5Gemini 3.0 FlashvsMistral Medium 3.5DeepSeek-V4-FlashvsKimi K3Gemini 3.0 FlashvsKimi K3

Frequently asked questions

Gemini 3.0 Flash leads DeepSeek-V4-Flash on 1 of the 1 benchmark they both report (GPQA Diamond). Gemini 3.0 Flash shipped 128 days before DeepSeek-V4-Flash, so benchmark comparisons should account for the intervening progress.

DeepSeek-V4-Flash is open weight, while Gemini 3.0 Flash is proprietary.

On GPQA Diamond, Gemini 3.0 Flash leads at 90.4% vs DeepSeek-V4-Flash at 88.1%.