K2 Horizon 375B A23B
公开成绩与计算依据
综合参考分根据已公开的评测资料整理。查看发布日期依据
综合参考分 43.4 · 12项基准
推理求解 35.2
GPQA Diamond · 0.872727272727273 比例
Artificial Analysis · 独立评测 · Diamond
K2 Horizon 375B A23B · Current AA standalone protocol. Status verified in aa-method-current.md section gpqa-diamond
Terminal-Bench-Science · 0 比例
Artificial Analysis · 独立评测 · 0.1.0
K2 Horizon 375B A23B · Artificial Analysis current published protocol; terminal-bench-science
HLE · 0.102 比例
Artificial Analysis · 独立评测 · Diamond
K2 Horizon 375B A23B · Artificial Analysis current published protocol; hle-diamond
CritPt · 0.12 比例
Artificial Analysis · 独立评测 · 2 Hard
K2 Horizon 375B A23B · Artificial Analysis current published protocol; critpt-v2-hard
工具与任务执行 58.0
tau3-Banking · 0.342268041237113 比例
Artificial Analysis · 独立评测 · 1.0.1
K2 Horizon 375B A23B · Current AA standalone protocol. Status verified in aa-method-current.md section tau3-banking
GDPval-AA · 1365.05 分
Artificial Analysis · 独立评测 · 2.1
K2 Horizon 375B A23B · Artificial Analysis current published protocol; gdpval-aa-normalized
Terminal-Bench · 0.0151515151515152 比例
Artificial Analysis · 独立评测 · 4.0
K2 Horizon 375B A23B · Artificial Analysis current published protocol; terminalbench-4-0
AutomationBench · 0.3720802754388014 比例
Artificial Analysis · 独立评测 · current published task suite
K2 Horizon 375B A23B · Artificial Analysis current published protocol; automationbench-aa
AA-Briefcase · 1292.48 分
Artificial Analysis · 独立评测 · 1.1
K2 Horizon 375B A23B · Artificial Analysis current published protocol; aa-briefcase
编程 38.8
FrontierCode · 0.118471464646465 比例
Artificial Analysis · 独立评测 · 2.0
K2 Horizon 375B A23B · Artificial Analysis current published protocol; frontiercode-2-0
语言与信息处理 39.8
GDP.pdf · 0.074 比例
Artificial Analysis · 独立评测 · current published task suite
K2 Horizon 375B A23B · Artificial Analysis current published protocol; gdp-pdf
AA-Omniscience · 0.18633333333333332 比例
Artificial Analysis · 独立评测 · 1.1
K2 Horizon 375B A23B · Artificial Analysis current published protocol; omniscience-accuracy
AA-Omniscience · 0.7095452683326506 比例
Artificial Analysis · 独立评测 · 1.1
K2 Horizon 375B A23B · Artificial Analysis current published protocol; omniscience-non-hallucination