DeepSeek-V4.1-Flashvsgpt-oss-120b

DeepSeek-V4.1-Flash
gpt-oss-120b
Specifications
Parameters
117B
Context window
128k
API pricing
Cheapest input
$0.03AkashML
Cheapest output
$0.17AkashML
Benchmarks
Humanity's Last Exam · no tools
36.8%14.9%
Humanity's Last Exam · with tools
63.9%19%
GPQA Diamond
90.9%80.1%
Benchmarks
BullshitBench v2
11%
SWE-Bench Verified
62.4%
DeepSWE 1.1
74.2%
NL2Repo-Bench
65.4%
Terminal-Bench 4.0
31.2%
Terminal-Bench 3.0
30%
Terminal-Bench 2.1
90.6%
CyberGym
88.1%
MMLU
90%
Agent's Last Exam · pass@1
31.8%
AutomationBench
54.8%
Chartography · with tools
78.9%
Overview
CompanyDeepSeekOpenAI
Release dateSep 10 2026Aug 5 2025
AccessProprietaryOpen Weight

Other comparisons

DeepSeek-V4.1-FlashvsClaude Fable 5.1gpt-oss-120bvsClaude Fable 5.1DeepSeek-V4.1-FlashvsGemini 3.8 Flashgpt-oss-120bvsGemini 3.8 FlashDeepSeek-V4.1-FlashvsMuse Spark 1.3gpt-oss-120bvsMuse Spark 1.3DeepSeek-V4.1-FlashvsGrok 4.6gpt-oss-120bvsGrok 4.6DeepSeek-V4.1-FlashvsMistral Medium 3.5gpt-oss-120bvsMistral Medium 3.5DeepSeek-V4.1-FlashvsKimi K3gpt-oss-120bvsKimi K3

Frequently asked questions

DeepSeek-V4.1-Flash leads gpt-oss-120b on 3 of the 3 benchmarks they both report (Humanity's Last Exam, GPQA Diamond). gpt-oss-120b shipped 401 days before DeepSeek-V4.1-Flash, so benchmark comparisons should account for the intervening progress.

DeepSeek-V4.1-Flash is proprietary, while gpt-oss-120b is open weight.

On Humanity's Last Exam · no tools, DeepSeek-V4.1-Flash leads at 36.8% vs gpt-oss-120b at 14.9%. On Humanity's Last Exam · with tools, DeepSeek-V4.1-Flash leads at 63.9% vs gpt-oss-120b at 19%. On GPQA Diamond, DeepSeek-V4.1-Flash leads at 90.9% vs gpt-oss-120b at 80.1%.