AI Studio API model id gemini-2.5-pro; default sampling settings. Technical report states Gemini scores are pass@1 and single-attempt unless specified. Aider Polyglot averages 3 trials; SWE-bench uses the internal agentic harness; Vibe-Eval uses Gemini as judge.
未知项
Thinking budget and any non-default settings for individual evaluations are not stated except where noted in each protocol.
Gemini 2.5 Pro (GA) · ZeroBench · Average over 4 runs · Scores and configurations
Gemini 2.5 Pro (GA) record for ZeroBench · Average over 4 runs. 1 score record for this release, including 1 exact value (may include historical records). Includes 2 source locations.
Gemini 2.5 Pro (GA) · ZeroBench scores and configurations
Metric and score
Configuration and evaluation conditions
Sources
Judge score4.5%Reported 4.5% · Unit %
Published Unconfirmed
Gemini 2.5 Pro stable API
Settings
AI Studio API model id gemini-2.5-pro; default sampling settings. Technical report states Gemini scores are pass@1 and single-attempt unless specified. Aider Polyglot averages 3 trials; SWE-bench uses the internal agentic harness; Vibe-Eval uses Gemini as judge.
Unknowns
Thinking budget and any non-default settings for individual evaluations are not stated except where noted in each protocol.