Compare AI models

Specifications
Parameters
284B—
Context window
1M1M
API pricing
Cheapest input
$0.05Baidu—
Cheapest output
$0.10Baidu—
$15.00Baidu · fp8—
Benchmarks
BullshitBench v2
18%20%
Overview
CompanyDeepSeekGoogle
Release dateApr 24 2026May 19 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Gemini 3.5 Flash leads DeepSeek-V4-Flash on 1 of the 1 benchmark they both report (BullshitBench v2). DeepSeek-V4-Flash shipped 25 days before Gemini 3.5 Flash, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (DeepSeek-V4-Flash) vs 1M (Gemini 3.5 Flash). DeepSeek-V4-Flash is open weight, while Gemini 3.5 Flash is closed.

On BullshitBench v2, Gemini 3.5 Flash leads at 20% vs DeepSeek-V4-Flash at 18%.