Home Model series Gemini 4 Argon Gemini 4 Argon Gemini 4 Argon · DeepSWE · v1.1 · Scores and configurations Gemini 4 Argon · DeepSWE · v1.1 · Scores and configurations Gemini 4 Argon record for DeepSWE · v1.1. 1 score record for this release, including 1 exact value (may include historical records). Includes 1 source location.
Scores and evaluation conditions Gemini 4 Argon · DeepSWE scores and configurations Metric and score Configuration and evaluation conditions Sources Score 77.9% Reported 77.9% · 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 high Framework mini-swe-agent Protocol Self-computed with mini-swe-agent harness; uses highest scoring Gemini thinking level reported on the main leaderboard. Conditions Gemini API; high thinking; pass@1; results as of September 2026. View this score in rankings
Benchmark versions and metrics Aliases DeepSWE v1.1
Score · % · Higher is better