Compare AI models

Specifications
Parameters
1.5B/7B/8B/14B/32B/70B117B
Context window
—128k
API pricing
Cheapest input
—$0.03AkashML
Cheapest output
—$0.15Near AI
—$13.50Venice · int4
Benchmarks
AIME 2024
70%95.8%
GPQA Diamond
65.2%80.1%
Overview
CompanyDeepSeekOpenAI
Release dateJan 20 2025Aug 5 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

gpt-oss-120b leads DeepSeek R1 Distill on 2 of the 2 benchmarks they both report (AIME 2024, GPQA Diamond). DeepSeek R1 Distill shipped 197 days before gpt-oss-120b, so benchmark comparisons should account for the intervening progress.

DeepSeek R1 Distill has 1.5B/7B/8B/14B/32B/70B parameters, while gpt-oss-120b has 117B.

On AIME 2024, gpt-oss-120b leads at 95.8% vs DeepSeek R1 Distill at 70%. On GPQA Diamond, gpt-oss-120b leads at 80.1% vs DeepSeek R1 Distill at 65.2%.