| Accuracy64.5%Reported 64.5% with tools · Unit % Published Unconfirmed | HLE · Auto thinking · Max effort · 有工具- Settings
- Thinking auto;图中标为 Max effort;web search、web fetch、programmatic tool calling 和 code execution。
- Unknowns
- 采样参数未说明。
- Tools
- Tools allowed
- Reasoning budget
- max
- Framework
- not recorded
- Protocol
- Humanity's Last Exam, 2,500 questions; tool-assisted configuration.
- Conditions
- Main summary table does not name effort. System Card says thinking auto, 980K task budget, no compaction, Opus 4.6 grader; web search, web fetch, programmatic tool calling and code execution. 有工具变体使用 Appendix 9.1 的 HLE 来源 blocklist,并复核污染后重新判分。
| View this score in rankings |
|---|
| Accuracy47.6%Reported 47.6% · Unit % Published Unconfirmed | Low effort- Settings
- Low reasoning effort.
- Unknowns
- Sampling settings not stated unless recorded per result.
- Tools
- Tools allowed
- Reasoning budget
- low
- Framework
- not recorded
- Protocol
- Humanity's Last Exam, 2,500 questions; tool-assisted configuration.
- Conditions
- 工具包含 web search、web fetch、programmatic tool calling 和 code execution;effort 取图中明确标签。Thinking auto;980K task token budget;无 context compaction;Claude Opus 4.6 grader。Thinking mode 与 effort 分别记录。 有工具变体使用 Appendix 9.1 的 HLE 来源 blocklist,并复核污染后重新判分。
| View this score in rankings |
|---|
| Accuracy50.5%Reported 50.5% · Unit % Published Unconfirmed | Medium effort- Settings
- Medium reasoning effort.
- Unknowns
- Sampling settings not stated unless recorded per result.
- Tools
- Tools allowed
- Reasoning budget
- medium
- Framework
- not recorded
- Protocol
- Humanity's Last Exam, 2,500 questions; tool-assisted configuration.
- Conditions
- 工具包含 web search、web fetch、programmatic tool calling 和 code execution;effort 取图中明确标签。Thinking auto;980K task token budget;无 context compaction;Claude Opus 4.6 grader。Thinking mode 与 effort 分别记录。 有工具变体使用 Appendix 9.1 的 HLE 来源 blocklist,并复核污染后重新判分。
| View this score in rankings |
|---|
| Accuracy56.7%Reported 56.7% · Unit % Published Unconfirmed | High effort- Settings
- High reasoning effort.
- Unknowns
- Sampling settings not stated unless recorded per result.
- Tools
- Tools allowed
- Reasoning budget
- high
- Framework
- not recorded
- Protocol
- Humanity's Last Exam, 2,500 questions; tool-assisted configuration.
- Conditions
- 工具包含 web search、web fetch、programmatic tool calling 和 code execution;effort 取图中明确标签。Thinking auto;980K task token budget;无 context compaction;Claude Opus 4.6 grader。Thinking mode 与 effort 分别记录。 有工具变体使用 Appendix 9.1 的 HLE 来源 blocklist,并复核污染后重新判分。
| View this score in rankings |
|---|
| Accuracy62%Reported 62.0% · Unit % Published Unconfirmed | Xhigh effort- Settings
- Xhigh reasoning effort.
- Unknowns
- Sampling settings not stated unless recorded per result.
- Tools
- Tools allowed
- Reasoning budget
- xhigh
- Framework
- not recorded
- Protocol
- Humanity's Last Exam, 2,500 questions; tool-assisted configuration.
- Conditions
- 工具包含 web search、web fetch、programmatic tool calling 和 code execution;effort 取图中明确标签。Thinking auto;980K task token budget;无 context compaction;Claude Opus 4.6 grader。Thinking mode 与 effort 分别记录。 有工具变体使用 Appendix 9.1 的 HLE 来源 blocklist,并复核污染后重新判分。
| View this score in rankings |
|---|
| Accuracy41.4%Reported 41.4% · Unit % Published Unconfirmed | Low effort- Settings
- Low reasoning effort.
- Unknowns
- Sampling settings not stated unless recorded per result.
- Tools
- Tools forbidden
- Reasoning budget
- low
- Framework
- not recorded
- Protocol
- Humanity's Last Exam, 2,500 questions; reasoning-only configuration without tools.
- Conditions
- 无工具;effort 取图中明确标签。Thinking auto;980K task token budget;无 context compaction;Claude Opus 4.6 grader。Thinking mode 与 effort 分别记录。
| View this score in rankings |
|---|
| Accuracy43.2%Reported 43.2% · Unit % Published Unconfirmed | Medium effort- Settings
- Medium reasoning effort.
- Unknowns
- Sampling settings not stated unless recorded per result.
- Tools
- Tools forbidden
- Reasoning budget
- medium
- Framework
- not recorded
- Protocol
- Humanity's Last Exam, 2,500 questions; reasoning-only configuration without tools.
- Conditions
- 无工具;effort 取图中明确标签。Thinking auto;980K task token budget;无 context compaction;Claude Opus 4.6 grader。Thinking mode 与 effort 分别记录。
| View this score in rankings |
|---|
| Accuracy47.9%Reported 47.9% · Unit % Published Unconfirmed | High effort- Settings
- High reasoning effort.
- Unknowns
- Sampling settings not stated unless recorded per result.
- Tools
- Tools forbidden
- Reasoning budget
- high
- Framework
- not recorded
- Protocol
- Humanity's Last Exam, 2,500 questions; reasoning-only configuration without tools.
- Conditions
- 无工具;effort 取图中明确标签。Thinking auto;980K task token budget;无 context compaction;Claude Opus 4.6 grader。Thinking mode 与 effort 分别记录。
| View this score in rankings |
|---|
| Accuracy53%Reported 53.0% · Unit % Published Unconfirmed | Xhigh effort- Settings
- Xhigh reasoning effort.
- Unknowns
- Sampling settings not stated unless recorded per result.
- Tools
- Tools forbidden
- Reasoning budget
- xhigh
- Framework
- not recorded
- Protocol
- Humanity's Last Exam, 2,500 questions; reasoning-only configuration without tools.
- Conditions
- 无工具;effort 取图中明确标签。Thinking auto;980K task token budget;无 context compaction;Claude Opus 4.6 grader。Thinking mode 与 effort 分别记录。
| View this score in rankings |
|---|
| Accuracy56.9%Reported 56.9% · Unit % Published Unconfirmed | HLE · Auto thinking · Max effort · 无工具- Settings
- Thinking auto;Max effort;无工具。
- Unknowns
- 采样参数未说明。
- Tools
- Tools forbidden
- Reasoning budget
- max
- Framework
- not recorded
- Protocol
- Humanity's Last Exam, 2,500 questions; reasoning-only configuration without tools.
- Conditions
- 无工具;effort 取图中明确标签。Thinking auto;980K task token budget;无 context compaction;Claude Opus 4.6 grader。Thinking mode 与 effort 分别记录。
| View this score in rankings |
|---|