DeepSeek-V4.1-FlashvsGPT-5.5-Pro

DeepSeek-V4.1-Flash
GPT-5.5-Pro
API pricing
Input price
$30.00
Output price
$180.00
Benchmarks
Humanity's Last Exam · with tools
63.9%57.2%
Benchmarks
BullshitBench v2
36%
DeepSWE 1.1
74.2%
Next.js Evals
77%
NL2Repo-Bench
65.4%
Terminal-Bench 4.0
31.2%
Terminal-Bench 3.0
30%
Terminal-Bench 2.1
90.6%
BrowseComp
90.1%
CyberGym
88.1%
Humanity's Last Exam · no tools
36.8%
FrontierMath · Tier 1–3
52.4%
FrontierMath · Tier 4
39.6%
GPQA Diamond
90.9%
Agent's Last Exam · pass@1
31.8%
AutomationBench
54.8%
GDPval (win/tie rate)
82.3%
Chartography · with tools
78.9%
Overview
CompanyDeepSeekOpenAI
Release dateSep 10 2026Apr 23 2026
AccessProprietaryProprietary

Other comparisons

DeepSeek-V4.1-FlashvsClaude Fable 5.1GPT-5.5-ProvsClaude Fable 5.1DeepSeek-V4.1-FlashvsGemini 3.8 FlashGPT-5.5-ProvsGemini 3.8 FlashDeepSeek-V4.1-FlashvsMuse Spark 1.3GPT-5.5-ProvsMuse Spark 1.3DeepSeek-V4.1-FlashvsGrok 4.6GPT-5.5-ProvsGrok 4.6DeepSeek-V4.1-FlashvsMistral Medium 3.5GPT-5.5-ProvsMistral Medium 3.5DeepSeek-V4.1-FlashvsKimi K3GPT-5.5-ProvsKimi K3

Frequently asked questions

DeepSeek-V4.1-Flash leads GPT-5.5-Pro on 1 of the 1 benchmark they both report (Humanity's Last Exam). Only GPT-5.5-Pro has a verified first-party API price: $30.00 per million input tokens and $180.00 per million output tokens. No pay-as-you-go API rate is tracked for DeepSeek-V4.1-Flash. GPT-5.5-Pro shipped 140 days before DeepSeek-V4.1-Flash, 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 Humanity's Last Exam · with tools, DeepSeek-V4.1-Flash leads at 63.9% vs GPT-5.5-Pro at 57.2%.