Home Model series Gemini Flash-Lite Gemini 3.5 Flash-Lite Gemini 3.5 Flash-Lite · CharXiv Reasoning · Version/split not stated in selected source · Scores and configurations Gemini 3.5 Flash-Lite · CharXiv Reasoning · Version/split not stated in selected source · Scores and configurations Gemini 3.5 Flash-Lite record for CharXiv Reasoning · Version/split not stated in selected source. 2 score records for this release, including 2 exact values (may include historical records). Includes 2 source locations.
Scores and evaluation conditions Gemini 3.5 Flash-Lite · CharXiv Reasoning scores and configurations Metric and score Configuration and evaluation conditions Sources Accuracy 74.5% Reported 74.5% · Unit % Published Unconfirmed
Gemini 3.5 Flash-Lite high thinking Settings Gemini API gemini-3.5-flash-lite; high thinking; default sampling; pass@1 except where noted. Unknowns Exact thinking budget and sampling parameters are not published. Tools Tools forbidden Reasoning budget high Framework not recorded Protocol CharXiv Reasoning, no tools; self-computed. Conditions Gemini API, high thinking; split/version unstated. View this score in rankings Accuracy 76.5% Reported 76.5% · Unit % Published Unconfirmed
Gemini 3.5 Flash-Lite high thinking Settings Gemini API gemini-3.5-flash-lite; high thinking; default sampling; pass@1 except where noted. Unknowns Exact thinking budget and sampling parameters are not published. Tools Tools allowed Reasoning budget high Framework not recorded Protocol CharXiv Reasoning with tools; Gemini uses search and code execution; self-computed. Conditions Gemini API, high thinking; split/version unstated. View this score in rankings
Benchmark versions and metrics Aliases CharXiv Reasoning
Accuracy · % · Higher is better