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.
工具
禁止工具
推理预算
未记录
框架
未记录
协议
No-tools variant; Scale leaderboard.
条件
Gemini pass@1; single attempt unless stated otherwise.
Gemini 2.5 Pro (GA) · Humanity's Last Exam · 2,500-question benchmark · Scores and configurations
Gemini 2.5 Pro (GA) record for Humanity's Last Exam · 2,500-question benchmark. 1 score record for this release, including 1 exact value (may include historical records). Includes 2 source locations.
Gemini 2.5 Pro (GA) · Humanity's Last Exam scores and configurations
Metric and score
Configuration and evaluation conditions
Sources
Accuracy21.6%Reported 21.6% · 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.
Tools
Tools forbidden
Reasoning budget
not recorded
Framework
not recorded
Protocol
No-tools variant; Scale leaderboard.
Conditions
Gemini pass@1; single attempt unless stated otherwise.