license: mit
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: 52.4
name: Artificial Analysis Coding Index
type: artificial_analysis_coding_index
value: 42.8
name: Artificial Analysis Math Index
type: artificial_analysis_math_index
value: 59
name: Mmlu Pro
type: mmlu_pro
value: 0.837
name: Gpqa
type: gpqa
value: 0.751
name: Hle
type: hle
value: 0.105
name: Livecodebench
type: livecodebench
value: 0.593
name: Scicode
type: scicode
value: 0.387
name: Aime 25
type: aime_25
value: 0.59
name: Ifbench
type: ifbench
value: 0.49
name: Lcr
type: lcr
value: 0.39
name: Terminalbench Hard
type: terminalbench_hard
value: 0.305
name: Tau2
type: tau2
value: 0.789
source:
name: Artificial Analysis API