Compare AI models

Specifications
Parameters
671B21B
Context window
128k128k
API pricing
Cheapest input
—$0.018AkashML
Cheapest output
—$0.09AkashML
—$8.10Darkbloom · fp8
Benchmarks
SWE-Bench Verified
49.2%60.7%
AIME 2024
79.8%92.1%
GPQA Diamond
71.5%71.5%
MMLU
90.8%85.3%
Overview
CompanyDeepSeekOpenAI
Release dateJan 20 2025Aug 5 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

gpt-oss-20b leads DeepSeek R1 on 2 of the 4 benchmarks they both report (SWE-Bench Verified, AIME 2024, GPQA Diamond, MMLU). DeepSeek R1 shipped 197 days before gpt-oss-20b, so benchmark comparisons should account for the intervening progress.

DeepSeek R1 has 671B parameters, while gpt-oss-20b has 21B. Context windows are 128k (DeepSeek R1) vs 128k (gpt-oss-20b).

On SWE-Bench Verified, gpt-oss-20b leads at 60.7% vs DeepSeek R1 at 49.2%. On AIME 2024, gpt-oss-20b leads at 92.1% vs DeepSeek R1 at 79.8%. On GPQA Diamond, both models score 71.5%. On MMLU, DeepSeek R1 leads at 90.8% vs gpt-oss-20b at 85.3%.