| model-index: | |
| - name: MackenzieTest | |
| results: | |
| - task: | |
| type: evaluation | |
| dataset: | |
| name: Artificial Analysis Benchmarks | |
| type: artificial_analysis | |
| metrics: | |
| - name: Artificial Analysis Intelligence Index | |
| type: artificial_analysis_intelligence_index | |
| value: 30.5 | |
| - name: Artificial Analysis Coding Index | |
| type: artificial_analysis_coding_index | |
| value: 21 | |
| - name: Artificial Analysis Math Index | |
| type: artificial_analysis_math_index | |
| value: 30 | |
| - name: Mmlu Pro | |
| type: mmlu_pro | |
| value: 0.693 | |
| - name: Gpqa | |
| type: gpqa | |
| value: 0.572 | |
| - name: Hle | |
| type: hle | |
| value: 0.046 | |
| - name: Livecodebench | |
| type: livecodebench | |
| value: 0.351 | |
| - name: Scicode | |
| type: scicode | |
| value: 0.236 | |
| - name: Aime 25 | |
| type: aime_25 | |
| value: 0.3 | |
| - name: Ifbench | |
| type: ifbench | |
| value: 0.32 | |
| - name: Lcr | |
| type: lcr | |
| value: 0.22 | |
| - name: Terminalbench Hard | |
| type: terminalbench_hard | |
| value: 0.043 | |
| - name: Tau2 | |
| type: tau2 | |
| value: 0.272 | |
| source: | |
| name: Artificial Analysis API | |
| url: https://artificialanalysis.ai | |