Solar Open2 250B
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 54.2 · 7项基准
推理求解 55.9
GPQA Diamond · 0.856565656565657 比例
Artificial Analysis · 独立评测 · Diamond
Solar Open2 250B · Current AA standalone protocol. Status verified in aa-method-current.md section gpqa-diamond
工具与任务执行 20.2
APEX-Agents · 16.6
huggingface.co · 官方发布比较 · current published task suite
Solar Open 2 250B-A15B · Official published comparison; APEX-Agents; exact column Solar Open 2 250B-A15B. Footnotes and all competing runs retained in source.
tau3-Banking · 0.216494845360825 比例
Artificial Analysis · 独立评测 · 1.0.1
Solar Open2 250B · Current AA standalone protocol. Status verified in aa-method-current.md section tau3-banking
GDPval-AA · 978 分
Artificial Analysis · 独立评测 · 2.1
Solar Open2 250B · Artificial Analysis current published protocol; gdpval-aa-normalized
MCP Atlas · 58.2
huggingface.co · 官方发布比较 · 1000 tasks
Solar Open 2 250B-A15B · Official published comparison; MCP-Atlas; exact column Solar Open 2 250B-A15B. Footnotes and all competing runs retained in source.
语言与信息处理 94.4
IFBench · 80.0
huggingface.co · 官方发布比较 · current published task suite
Solar Open 2 250B-A15B · Official published comparison; IFBench; exact column Solar Open 2 250B-A15B. Footnotes and all competing runs retained in source.
MMLU-Pro · 86.2
huggingface.co · 官方发布比较 · current maintainer dataset
Solar Open 2 250B-A15B · Official published comparison; MMLU-Pro; exact column Solar Open 2 250B-A15B. Footnotes and all competing runs retained in source.
资料来源
- 版本日期来源 · 版本资料 · 2026-10-29查阅
- huggingface.co · official_release_comparison · 2026-10-29查阅
- 发布日期依据 · release