EvalEval Coalition
EvalEval Coalition collaborates with Apertus 1.5 for transparent benchmarking EuroHPC supercomputing centers provide NVIDIA GPU infrastructure and services for open research Anthropic Opus 5.5 solved 92% of the problems on the TheoPhysEval benchmark Anthropic Opus 5.5 runs in the Claude Code environment TrainLoop post-trained Nemotron 3.5 Super VL· Graphiti 生成的实体摘要
关系变化
按生效时间- EvalEval CoalitionSOLVEDTheoPhysEval benchmark
Anthropic Opus 5.5 solved 92% of the problems on the TheoPhysEval benchmark
- EvalEval CoalitionRUNS INClaude Code
Anthropic Opus 5.5 runs in the Claude Code environment
- EvalEval CoalitionPROVIDESNVIDIA GPU infrastructure
EuroHPC supercomputing centers provide NVIDIA GPU infrastructure and services for open research
- EvalEval CoalitionCOLLABORATES WITHApertus 1.5
EvalEval Coalition collaborates with Apertus 1.5 for transparent benchmarking
- EvalEval CoalitionPOST TRAINEDNemotron 3.5 Super VL
TrainLoop post-trained Nemotron 3.5 Super VL
关系是 Graphiti 从报道中提取的事实陈述，不是原文引述；失效时间表示后来的报道显示这条关系已不成立。