允许工具 / medium / 框架未记录 · Humanity’s Last Exam; with web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · 允许工具 / medium / 框架未记录 · Humanity’s Last Exam; with web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget.
允许工具 / high / 框架未记录 · Humanity’s Last Exam; with web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · 允许工具 / high / 框架未记录 · Humanity’s Last Exam; with web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget.
允许工具 / max / 框架未记录 · Humanity’s Last Exam; with web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · 允许工具 / max / 框架未记录 · Humanity’s Last Exam; with web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget.
禁止工具 / medium / 框架未记录 · HLE; no tools; medium effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · 禁止工具 / medium / 框架未记录 · HLE; no tools; medium effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
禁止工具 / high / 框架未记录 · HLE; no tools; high effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · 禁止工具 / high / 框架未记录 · HLE; no tools; high effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
禁止工具 / max / 框架未记录 · HLE; no tools; max effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · 禁止工具 / max / 框架未记录 · HLE; no tools; max effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
允许工具 / low / 框架未记录 · HLE; web search, web fetch, programmatic tools, and code execution; low effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · 允许工具 / low / 框架未记录 · HLE; web search, web fetch, programmatic tools, and code execution; low effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
允许工具 / medium / 框架未记录 · HLE; web search, web fetch, programmatic tools, and code execution; medium effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · 允许工具 / medium / 框架未记录 · HLE; web search, web fetch, programmatic tools, and code execution; medium effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
允许工具 / high / 框架未记录 · HLE; web search, web fetch, programmatic tools, and code execution; high effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · 允许工具 / high / 框架未记录 · HLE; web search, web fetch, programmatic tools, and code execution; high effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
允许工具 / xhigh / 框架未记录 · HLE; web search, web fetch, programmatic tools, and code execution; xhigh effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · 允许工具 / xhigh / 框架未记录 · HLE; web search, web fetch, programmatic tools, and code execution; xhigh effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
禁止工具 / high / 框架未记录 · Full set (text + multimodal); no tools; Gemini 3.1 Pro Thinking (High).
Humanity's Last Exam · 2,500-question benchmark · Accuracy · 禁止工具 / high / 框架未记录 · Full set (text + multimodal); no tools; Gemini 3.1 Pro Thinking (High).
Regular display scope. Rankings are grouped by metric and evaluation protocol. Recorded tool access, budgets, and frameworks are shown separately. Scores remain available for reference when conditions are unspecified.
Accuracy %
Tools forbidden / max / Framework not recorded · Humanity’s Last Exam; no tools; 980k-token task budget; no context compaction.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools forbidden / max / Framework not recorded · Humanity’s Last Exam; no tools; 980k-token task budget; no context compaction.
Tools allowed / low / Framework not recorded · Humanity’s Last Exam; with web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools allowed / low / Framework not recorded · Humanity’s Last Exam; with web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget.
Tools allowed / medium / Framework not recorded · Humanity’s Last Exam; with web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools allowed / medium / Framework not recorded · Humanity’s Last Exam; with web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget.
Tools allowed / high / Framework not recorded · Humanity’s Last Exam; with web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools allowed / high / Framework not recorded · Humanity’s Last Exam; with web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget.
Tools allowed / xhigh / Framework not recorded · Humanity’s Last Exam; with web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools allowed / xhigh / Framework not recorded · Humanity’s Last Exam; with web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget.
Tools allowed / max / Framework not recorded · Humanity’s Last Exam; with web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools allowed / max / Framework not recorded · Humanity’s Last Exam; with web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget.
Tools forbidden / medium / Framework not recorded · Humanity’s Last Exam; no tools; 980k-token task budget.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools forbidden / medium / Framework not recorded · Humanity’s Last Exam; no tools; 980k-token task budget.
Tools forbidden / high / Framework not recorded · Humanity’s Last Exam; no tools; 980k-token task budget.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools forbidden / high / Framework not recorded · Humanity’s Last Exam; no tools; 980k-token task budget.
Tools allowed / max / Framework not recorded · Humanity's Last Exam, 2,500 questions; tool-assisted configuration.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools allowed / max / Framework not recorded · Humanity's Last Exam, 2,500 questions; tool-assisted configuration.
Tools allowed / medium / Framework not recorded · Humanity's Last Exam, 2,500 questions; tool-assisted configuration.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools allowed / medium / Framework not recorded · Humanity's Last Exam, 2,500 questions; tool-assisted configuration.
Tools allowed / high / Framework not recorded · Humanity's Last Exam, 2,500 questions; tool-assisted configuration.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools allowed / high / Framework not recorded · Humanity's Last Exam, 2,500 questions; tool-assisted configuration.
Tools forbidden / medium / Framework not recorded · Humanity's Last Exam, 2,500 questions; reasoning-only configuration without tools.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools forbidden / medium / Framework not recorded · Humanity's Last Exam, 2,500 questions; reasoning-only configuration without tools.
Tools forbidden / high / Framework not recorded · Humanity's Last Exam, 2,500 questions; reasoning-only configuration without tools.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools forbidden / high / Framework not recorded · Humanity's Last Exam, 2,500 questions; reasoning-only configuration without tools.
Tools forbidden / max / Framework not recorded · Humanity's Last Exam, 2,500 questions; reasoning-only configuration without tools.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools forbidden / max / Framework not recorded · Humanity's Last Exam, 2,500 questions; reasoning-only configuration without tools.
Tools forbidden / low / Framework not recorded · HLE; no tools; low effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools forbidden / low / Framework not recorded · HLE; no tools; low effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Tools forbidden / medium / Framework not recorded · HLE; no tools; medium effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools forbidden / medium / Framework not recorded · HLE; no tools; medium effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Tools forbidden / high / Framework not recorded · HLE; no tools; high effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools forbidden / high / Framework not recorded · HLE; no tools; high effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Tools forbidden / xhigh / Framework not recorded · HLE; no tools; xhigh effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools forbidden / xhigh / Framework not recorded · HLE; no tools; xhigh effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Tools forbidden / max / Framework not recorded · HLE; no tools; max effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools forbidden / max / Framework not recorded · HLE; no tools; max effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Tools allowed / low / Framework not recorded · HLE; web search, web fetch, programmatic tools, and code execution; low effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools allowed / low / Framework not recorded · HLE; web search, web fetch, programmatic tools, and code execution; low effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Tools allowed / medium / Framework not recorded · HLE; web search, web fetch, programmatic tools, and code execution; medium effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools allowed / medium / Framework not recorded · HLE; web search, web fetch, programmatic tools, and code execution; medium effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Tools allowed / high / Framework not recorded · HLE; web search, web fetch, programmatic tools, and code execution; high effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools allowed / high / Framework not recorded · HLE; web search, web fetch, programmatic tools, and code execution; high effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Tools allowed / xhigh / Framework not recorded · HLE; web search, web fetch, programmatic tools, and code execution; xhigh effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools allowed / xhigh / Framework not recorded · HLE; web search, web fetch, programmatic tools, and code execution; xhigh effort; adaptive thinking; 1M total-token cap; no context compaction; Claude Opus 4.6 grader.
Tools forbidden / Reasoning budget not recorded / Framework not recorded · Conditions not specified
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools forbidden / Reasoning budget not recorded / Framework not recorded · Conditions not specified
Tools forbidden / high / Framework not recorded · Full set (text + multimodal); no tools; Gemini 3.1 Pro Thinking (High).
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools forbidden / high / Framework not recorded · Full set (text + multimodal); no tools; Gemini 3.1 Pro Thinking (High).
Tools allowed / high / Framework not recorded · Full set (text + multimodal); Search (blocklist) + Code; Gemini 3.1 Pro Thinking (High).
Humanity's Last Exam · 2,500-question benchmark · Accuracy · Tools allowed / high / Framework not recorded · Full set (text + multimodal); Search (blocklist) + Code; Gemini 3.1 Pro Thinking (High).