Nanbeige4.3-33B
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 45.5 · 9项基准
推理求解 32.7
Terminal-Bench-Science · 0.00952380952380952 比例
Artificial Analysis · 独立评测 · 0.1.0
Nanbeige4.3-33B · Artificial Analysis current published protocol; terminal-bench-science
HLE · 0.069 比例
Artificial Analysis · 独立评测 · Diamond
Nanbeige4.3-33B · Artificial Analysis current published protocol; hle-diamond
CritPt · 0.155 比例
Artificial Analysis · 独立评测 · 2 Hard
Nanbeige4.3-33B · Artificial Analysis current published protocol; critpt-v2-hard
工具与任务执行 62.8
Terminal-Bench · 0.297979797979798 比例
Artificial Analysis · 独立评测 · 4.0
Nanbeige4.3-33B · Artificial Analysis current published protocol; terminalbench-4-0
AutomationBench · 0.5311537657440716 比例
Artificial Analysis · 独立评测 · current published task suite
Nanbeige4.3-33B · Artificial Analysis current published protocol; automationbench-aa
AA-Briefcase · 1161.84 分
Artificial Analysis · 独立评测 · 1.1
Nanbeige4.3-33B · Artificial Analysis current published protocol; aa-briefcase
编程 36.7
FrontierCode · 0.10717702020202 比例
Artificial Analysis · 独立评测 · 2.0
Nanbeige4.3-33B · Artificial Analysis current published protocol; frontiercode-2-0
语言与信息处理 48.5
GDP.pdf · 0.112 比例
Artificial Analysis · 独立评测 · current published task suite
Nanbeige4.3-33B · Artificial Analysis current published protocol; gdp-pdf
AA-Omniscience · 0.11666666666666667 比例
Artificial Analysis · 独立评测 · 1.1
Nanbeige4.3-33B · Artificial Analysis current published protocol; omniscience-accuracy
AA-Omniscience · 0.8181132075471698 比例
Artificial Analysis · 独立评测 · 1.1
Nanbeige4.3-33B · Artificial Analysis current published protocol; omniscience-non-hallucination