Compare AI models

Specifications
Parameters
117B4B/30B/235B
Context window
128k256k
API pricing
Cheapest input
$0.03AkashML—
Cheapest output
$0.15Near AI—
$13.50Venice · int4—
Benchmarks
AIME 2025
92.5%92.3%
GPQA Diamond
80.1%81.1%
Overview
CompanyOpenAIQwen
Release dateAug 5 2025Jul 21 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

gpt-oss-120b and Qwen3-2507 are evenly matched across the 2 benchmarks they both report (AIME 2025, GPQA Diamond). Qwen3-2507 shipped 15 days before gpt-oss-120b, so benchmark comparisons should account for the intervening progress.

gpt-oss-120b has 117B parameters, while Qwen3-2507 has 4B/30B/235B. Context windows are 128k (gpt-oss-120b) vs 256k (Qwen3-2507).

On AIME 2025, gpt-oss-120b leads at 92.5% vs Qwen3-2507 at 92.3%. On GPQA Diamond, Qwen3-2507 leads at 81.1% vs gpt-oss-120b at 80.1%.