LIVE INTELLIGENCE · part of the Xentir AI Index

Gemini 2.5 Flash (Preview 04 17) vs gpt-oss-120b

Gemini 2.5 Flash (Preview 04 17) · Google DeepMind, released 2025-04-17
gpt-oss-120b OPEN WEIGHTS · OpenAI, released 2025-08-05

“Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource].” · epoch.ai/benchmarks · Licensed CC BY 4.0 · data last verified 2026-07-26 · Methodology · Data Sources

Head-to-head

Measured on 2 of 9 tracked benchmarks for both models — Gemini 2.5 Flash (Preview 04 17) leads on 1, gpt-oss-120b leads on 1.

Benchmark	Gemini 2.5 Flash (Preview 04 17)	gpt-oss-120b	Leads
Epoch Capabilities Index (ECI)	140.6	140.6	Gemini 2.5 Flash (Preview 04 17)
SWE-bench Verified	Not measured	Not measured	Not measured on both
GPQA Diamond	Not measured	0.758 (high-openai)	Not measured on both
MATH Level 5	Not measured	Not measured	Not measured on both
OTIS Mock AIME 2024-2025	0.731	0.889 (high-openai)	gpt-oss-120b
FrontierMath	Not measured	Not measured	Not measured on both
FrontierMath Tier 4	Not measured	Not measured	Not measured on both
SimpleQA Verified	Not measured	0.139 (high-openai)	Not measured on both
Chess Puzzles	Not measured	0.200 (high-openai)	Not measured on both

Benchmark results measure specific tasks and should not be treated as a universal measure of model quality. A model with no row here for a benchmark has not been measured on it — that is left blank, never estimated.

Full profiles

Gemini 2.5 Flash (Preview 04 17) → · gpt-oss-120b → · the full AI Model Rankings table