Home Model series Gemini 4 Argon Gemini 4 Argon Gemini 4 Argon · Terminal-Bench-Science · 0.1 · Scores and configurations Gemini 4 Argon · Terminal-Bench-Science · 0.1 · Scores and configurations Gemini 4 Argon record for Terminal-Bench-Science · 0.1. 2 score records for this release, including 2 exact values (may include historical records). Includes 2 source locations.
Scores and evaluation conditions Gemini 4 Argon · Terminal-Bench-Science scores and configurations Metric and score Configuration and evaluation conditions Sources Score 52.9% Reported 52.9% · Unit % Published Unconfirmed
Gemini 4 Argon highest thinking Settings Gemini API model gemini-4-argon; highest thinking settings; default sampling unless benchmark method states otherwise; pass@1 except where stated. Unknowns Exact thinking budget and sampling parameters are not published.、原文仅称 highest thinking settings,未确认对应的公开档位名称。 Tools Tool access not recorded Reasoning budget not recorded Framework not recorded Protocol Terminal-Bench-Science 0.1 Artificial Analysis results. Conditions Gemini 4 highest thinking; pass@1 unless stated. View this score in rankings Score 57.6% Reported 57.6% · Unit % Published Unconfirmed
Gemini 4 Argon highest thinking Settings Gemini API model gemini-4-argon; highest thinking settings; default sampling unless benchmark method states otherwise; pass@1 except where stated. Unknowns Exact thinking budget and sampling parameters are not published.、原文仅称 highest thinking settings,未确认对应的公开档位名称。 Tools Tool access not recorded Reasoning budget not recorded Framework not recorded Protocol Gemini 4 Argon self-computed; six-times verifier timeout to address timeout issues. Conditions Results as of September 2026; distinct method from the 52.9% Artificial Analysis row in October paired table. View this score in rankings
Benchmark versions and metrics Aliases Terminal-Bench-Science 0.1
Score · % · Higher is better