https://www.rsi-benchmark.com/ 1 https://www.rsi-benchmark.com/tasks 0.9 https://www.rsi-benchmark.com/runs 0.8 https://www.rsi-benchmark.com/blog 0.5 https://www.rsi-benchmark.com/contribute 0.7 https://www.rsi-benchmark.com/guidelines 0.6 https://www.rsi-benchmark.com/legal/competition-terms 0.3 https://www.rsi-benchmark.com/tasks/on-policy-self-distillation 0.8 https://www.rsi-benchmark.com/tasks/jailbreak-robustness 0.8 https://www.rsi-benchmark.com/tasks/agent-swarm-optimization 0.8 https://www.rsi-benchmark.com/tasks/nano-gpt-data-curation 0.8 https://www.rsi-benchmark.com/runs/dclm-nano-curation__3WuREza 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__3WuREza/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__3WuREza/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__4yt6SE3 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__4yt6SE3/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__4yt6SE3/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__5zjKKAd 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__5zjKKAd/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__5zjKKAd/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__69HmyDM 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__69HmyDM/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__69HmyDM/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__7CCVfar 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__7CCVfar/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__7CCVfar/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__7sx25Ej 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__7sx25Ej/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__7sx25Ej/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__8WDjnVr 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__8WDjnVr/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__8WDjnVr/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__9upVhik 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__9upVhik/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__9upVhik/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__EVaJQmY 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__EVaJQmY/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__EVaJQmY/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__JXGjCVp 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__JXGjCVp/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__JXGjCVp/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__JnvJaaT 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__JnvJaaT/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__JnvJaaT/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__KgMs7QW 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__KgMs7QW/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__KgMs7QW/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__KzgeyF6 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__KzgeyF6/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__KzgeyF6/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__NAGsecC 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__NAGsecC/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__NAGsecC/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__NqS7udZ 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__NqS7udZ/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__NqS7udZ/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__PfpVxLk 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__PfpVxLk/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__PfpVxLk/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__SMvDtRx 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__SMvDtRx/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__SMvDtRx/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__UpMAMLW 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__UpMAMLW/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__UpMAMLW/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__V4TWBJJ 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__V4TWBJJ/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__V4TWBJJ/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__W6EguaR 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__W6EguaR/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__W6EguaR/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__XWHDKVK 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__XWHDKVK/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__XWHDKVK/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__XegPhjw 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__XegPhjw/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__XegPhjw/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__aTQyfVE 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__aTQyfVE/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__aTQyfVE/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__d9qdiJV 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__d9qdiJV/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__d9qdiJV/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__f5FdhJo 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__f5FdhJo/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__f5FdhJo/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__frqBRu3 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__frqBRu3/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__frqBRu3/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__gfZ879v 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__gfZ879v/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__gfZ879v/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__ignQSrt 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__ignQSrt/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__ignQSrt/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__nfvFpyv 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__nfvFpyv/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__nfvFpyv/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__u7ZtWPZ 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__u7ZtWPZ/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__u7ZtWPZ/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__vzTkueh 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__vzTkueh/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__vzTkueh/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__yfNnWEs 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__yfNnWEs/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__yfNnWEs/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__z2rZFLJ 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__z2rZFLJ/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__z2rZFLJ/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__zzFhaz8 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__zzFhaz8/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__zzFhaz8/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__2yV7BuE 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__2yV7BuE/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__2yV7BuE/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__3MHiHkh 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__3MHiHkh/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__3MHiHkh/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__4uHWTbn 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__4uHWTbn/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__4uHWTbn/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__6VRFg2T 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__6VRFg2T/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__6VRFg2T/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__7umcSHc 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__7umcSHc/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__7umcSHc/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__BJAS84o 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__BJAS84o/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__BJAS84o/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__CJi6xsp 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__CJi6xsp/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__CJi6xsp/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__EAKU6Ra 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__EAKU6Ra/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__EAKU6Ra/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__ETg2M2Y 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__ETg2M2Y/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__ETg2M2Y/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__FwSgZtE 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__FwSgZtE/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__FwSgZtE/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__GKXSUa7 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__GKXSUa7/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__GKXSUa7/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__Hk847sf 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__Hk847sf/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__Hk847sf/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__K2QidbF 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__K2QidbF/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__K2QidbF/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__LYgVBSB 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__LYgVBSB/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__LYgVBSB/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__NFLvnqE 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__NFLvnqE/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__NFLvnqE/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__PTUx94M 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__PTUx94M/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__PTUx94M/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__RKmSGRj 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__RKmSGRj/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__RKmSGRj/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__SWfSgxK 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__SWfSgxK/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__SWfSgxK/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__TGPvq9r 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__TGPvq9r/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__TGPvq9r/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__UFqhk3Z 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__UFqhk3Z/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__UFqhk3Z/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__YJRWvfs 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__YJRWvfs/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__YJRWvfs/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__YiLXzw2 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__YiLXzw2/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__YiLXzw2/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__Z4r6k8s 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__Z4r6k8s/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__Z4r6k8s/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__aQTkr5P 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__aQTkr5P/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__aQTkr5P/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__awciJhD 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__awciJhD/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__awciJhD/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__eYKuduN 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__eYKuduN/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__eYKuduN/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__gSSiCuY 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__gSSiCuY/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__gSSiCuY/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__iADFZ4p 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__iADFZ4p/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__iADFZ4p/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__mqoYzmu 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__mqoYzmu/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__mqoYzmu/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__oQnQLfN 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__oQnQLfN/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__oQnQLfN/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__ohgR2nu 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__ohgR2nu/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__ohgR2nu/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__u8hwsKZ 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__u8hwsKZ/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__u8hwsKZ/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__wPVYcnk 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__wPVYcnk/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__wPVYcnk/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__wasW5uR 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__wasW5uR/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__wasW5uR/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__xJxXGaB 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__xJxXGaB/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__xJxXGaB/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__xo46Sta 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__xo46Sta/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__xo46Sta/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__xzFWmY4 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__xzFWmY4/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__xzFWmY4/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__4gETduU 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__4gETduU/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__4gETduU/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__8gThzQg 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__8gThzQg/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__8gThzQg/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__AoiWXUF 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__AoiWXUF/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__AoiWXUF/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__BebKMFd 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__BebKMFd/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__BebKMFd/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__BgDz4nG 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__BgDz4nG/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__BgDz4nG/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__D5SotNq 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__D5SotNq/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__D5SotNq/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__DZac9UG 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__DZac9UG/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__DZac9UG/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__EHmEPWe 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__EHmEPWe/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__EHmEPWe/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__H6LNrrM 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__H6LNrrM/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__H6LNrrM/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__HBfU9js 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__HBfU9js/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__HBfU9js/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__HzsPDMT 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__HzsPDMT/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__HzsPDMT/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__KmpadEA 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__KmpadEA/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__KmpadEA/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__LDprjkQ 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__LDprjkQ/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__LDprjkQ/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__MDUDMmY 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__MDUDMmY/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__MDUDMmY/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__MPsY5uL 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__MPsY5uL/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__MPsY5uL/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__PCUF55U 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__PCUF55U/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__PCUF55U/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__SREjBg2 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__SREjBg2/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__SREjBg2/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__U9oLS3w 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__U9oLS3w/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__U9oLS3w/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__VqEFXf4 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__VqEFXf4/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__VqEFXf4/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__Wz5kwvV 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__Wz5kwvV/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__Wz5kwvV/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__YA9bqxQ 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__YA9bqxQ/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__YA9bqxQ/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__YxBhtKq 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__YxBhtKq/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__YxBhtKq/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__ZPqRAkS 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__ZPqRAkS/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__ZPqRAkS/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__boCjom2 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__boCjom2/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__boCjom2/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__edCjgpD 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__edCjgpD/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__edCjgpD/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__kmNk7VX 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__kmNk7VX/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__kmNk7VX/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__nEEkAJz 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__nEEkAJz/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__nEEkAJz/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__phgXX4s 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__phgXX4s/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__phgXX4s/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__q2CFtsE 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__q2CFtsE/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__q2CFtsE/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__qs2bLDV 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__qs2bLDV/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__qs2bLDV/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__r4AKe3x 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__r4AKe3x/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__r4AKe3x/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__rQEvmaF 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__rQEvmaF/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__rQEvmaF/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__s2euUXT 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__s2euUXT/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__s2euUXT/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__twR79Yh 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__twR79Yh/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__twR79Yh/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__uCfhEL6 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__uCfhEL6/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__uCfhEL6/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__xNCncBo 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__xNCncBo/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__xNCncBo/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__xrPbCYK 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__xrPbCYK/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__xrPbCYK/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__yc6JrsF 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__yc6JrsF/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__yc6JrsF/trace 0.2 https://www.rsi-benchmark.com/runs/dclm-nano-curation__zQZFhRN 0.4 https://www.rsi-benchmark.com/runs/dclm-nano-curation__zQZFhRN/evaluation 0.3 https://www.rsi-benchmark.com/runs/dclm-nano-curation__zQZFhRN/trace 0.2 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__3tyLi4e 0.4 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__3tyLi4e/evaluation 0.3 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__3tyLi4e/trace 0.2 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__RqGcDty 0.4 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__RqGcDty/evaluation 0.3 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__RqGcDty/trace 0.2 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__eNDoWrD 0.4 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__eNDoWrD/evaluation 0.3 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__eNDoWrD/trace 0.2 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__kuc95M7 0.4 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__kuc95M7/evaluation 0.3 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__kuc95M7/trace 0.2 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__F2Xe6j3 0.4 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__F2Xe6j3/evaluation 0.3 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__F2Xe6j3/trace 0.2 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__LSVoBuR 0.4 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__LSVoBuR/evaluation 0.3 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__LSVoBuR/trace 0.2 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__g75tHnA 0.4 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__g75tHnA/evaluation 0.3 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__g75tHnA/trace 0.2 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__r6P3Lfd 0.4 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__r6P3Lfd/evaluation 0.3 https://www.rsi-benchmark.com/runs/opsd-aime24-4gpus__r6P3Lfd/trace 0.2 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__UApBU9n 0.4 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__UApBU9n/evaluation 0.3 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__UApBU9n/trace 0.2 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__XNPUqgv 0.4 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__XNPUqgv/evaluation 0.3 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__XNPUqgv/trace 0.2 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__Z7ckqwX 0.4 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__Z7ckqwX/evaluation 0.3 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__Z7ckqwX/trace 0.2 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__shjZkUr 0.4 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__shjZkUr/evaluation 0.3 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__shjZkUr/trace 0.2 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__LQZVM55 0.4 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__LQZVM55/evaluation 0.3 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__LQZVM55/trace 0.2 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__QUkfs8J 0.4 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__QUkfs8J/evaluation 0.3 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__QUkfs8J/trace 0.2 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__ZvH5Sny 0.4 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__ZvH5Sny/evaluation 0.3 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__ZvH5Sny/trace 0.2 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__q5qpejH 0.4 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__q5qpejH/evaluation 0.3 https://www.rsi-benchmark.com/runs/safety-qwen3-jailbreak__q5qpejH/trace 0.2 https://www.rsi-benchmark.com/runs/swarm-aime-optimization__R6Lb9Ae 0.4 https://www.rsi-benchmark.com/runs/swarm-aime-optimization__R6Lb9Ae/evaluation 0.3 https://www.rsi-benchmark.com/runs/swarm-aime-optimization__R6Lb9Ae/trace 0.2 https://www.rsi-benchmark.com/runs/swarm-aime-optimization__kfV24B9 0.4 https://www.rsi-benchmark.com/runs/swarm-aime-optimization__kfV24B9/evaluation 0.3 https://www.rsi-benchmark.com/runs/swarm-aime-optimization__kfV24B9/trace 0.2 https://www.rsi-benchmark.com/blog/announcing-rsi-bench 0.5