Compare AI models

Specifications
Parameters
—117B
Context window
1M128k
API pricing
Cheapest input
—$0.03AkashML
Cheapest output
—$0.15Near AI
—$13.50Venice · int4
Benchmarks
BullshitBench v2
20%12%
Humanity's Last Exam · no tools
40.2%14.9%
Overview
CompanyGoogleOpenAI
Release dateMay 19 2026Aug 5 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemini 3.5 Flash leads gpt-oss-120b on 2 of the 2 benchmarks they both report (BullshitBench v2, Humanity's Last Exam). gpt-oss-120b shipped 287 days before Gemini 3.5 Flash, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Gemini 3.5 Flash) vs 128k (gpt-oss-120b). Gemini 3.5 Flash is closed, while gpt-oss-120b is open weight.

On BullshitBench v2, Gemini 3.5 Flash leads at 20% vs gpt-oss-120b at 12%. On Humanity's Last Exam · no tools, Gemini 3.5 Flash leads at 40.2% vs gpt-oss-120b at 14.9%.