Compare AI models

Specifications
Parameters
16B117B
Context window
32k128k
API pricing
Cheapest input
—$0.03AkashML
Cheapest output
—$0.15Near AI
—$13.50Venice · int4
Benchmarks
MMLU
55.7%90%
Overview
CompanyDeepSeekOpenAI
Release dateMay 16 2024Aug 5 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

gpt-oss-120b leads DeepSeek V2 Lite on 1 of the 1 benchmark they both report (MMLU). DeepSeek V2 Lite shipped 446 days before gpt-oss-120b, so benchmark comparisons should account for the intervening progress.

DeepSeek V2 Lite has 16B parameters, while gpt-oss-120b has 117B. Context windows are 32k (DeepSeek V2 Lite) vs 128k (gpt-oss-120b).

On MMLU, gpt-oss-120b leads at 90% vs DeepSeek V2 Lite at 55.7%.