Skip to content

Runs

Every solver attempt on record, graded by the task's verifier.

agent-swarm-optimization0.448
gpt-5.6-sol
2h 57m345 actionsswarm-aime-optimization__R6Lb9Ae
agent-swarm-optimization0.818
claude-opus-5
5h 16m163 actionsswarm-aime-optimization__kfV24B9
nano-gpt-data-curation321.290
claude-opus-4-8
1h 6m84 actionsdclm-nano-curation__GKXSUa7
nano-gpt-data-curation370.310
claude-opus-4-8
46m66 actionsdclm-nano-curation__BJAS84o
nano-gpt-data-curation364.700
claude-opus-4-8
1h 15m99 actionsdclm-nano-curation__wasW5uR
nano-gpt-data-curation332.560
claude-opus-4-8
1h 21m87 actionsdclm-nano-curation__7umcSHc
nano-gpt-data-curation315.670
claude-opus-4-8
44m56 actionsdclm-nano-curation__6VRFg2T
nano-gpt-data-curation336.180
claude-opus-4-8
59m65 actionsdclm-nano-curation__SWfSgxK
nano-gpt-data-curation322.460
claude-opus-4-8
42m36 actionsdclm-nano-curation__UFqhk3Z
nano-gpt-data-curation299.880
claude-opus-4-8
35m65 actionsdclm-nano-curation__awciJhD
nano-gpt-data-curation379.850
claude-opus-4-8
59m37 actionsdclm-nano-curation__LYgVBSB
nano-gpt-data-curation337.550
claude-opus-4-8
24m36 actionsdclm-nano-curation__Z4r6k8s
nano-gpt-data-curation327.790
claude-opus-4-8
32m49 actionsdclm-nano-curation__2yV7BuE
nano-gpt-data-curation343.840
claude-opus-4-8
39m36 actionsdclm-nano-curation__FwSgZtE
nano-gpt-data-curation415.520
claude-opus-4-8
1h 9m111 actionsdclm-nano-curation__4uHWTbn
nano-gpt-data-curation368.690
claude-opus-4-8
40m49 actionsdclm-nano-curation__YJRWvfs
nano-gpt-data-curation302.020
claude-opus-4-8
1h 5m79 actionsdclm-nano-curation__ETg2M2Y
nano-gpt-data-curation330.290
claude-opus-4-8
30m31 actionsdclm-nano-curation__xzFWmY4
nano-gpt-data-curation364.870
claude-opus-4-8
19m27 actionsdclm-nano-curation__oQnQLfN
nano-gpt-data-curation348.060
claude-opus-4-8
40m40 actionsdclm-nano-curation__PTUx94M
nano-gpt-data-curation358.070
claude-opus-4-8
47m48 actionsdclm-nano-curation__mqoYzmu
nano-gpt-data-curation308.110
claude-opus-4-8
1h 22m84 actionsdclm-nano-curation__ohgR2nu
nano-gpt-data-curation298.370
claude-opus-4-8
39m42 actionsdclm-nano-curation__RKmSGRj
nano-gpt-data-curation296.430
claude-opus-4-8
53m61 actionsdclm-nano-curation__3MHiHkh
nano-gpt-data-curation354.110
claude-opus-4-8
1h 9m102 actionsdclm-nano-curation__TGPvq9r
nano-gpt-data-curation319.810
claude-opus-4-8
1h73 actionsdclm-nano-curation__eYKuduN
nano-gpt-data-curation330.960
claude-opus-4-8
43m61 actionsdclm-nano-curation__iADFZ4p
nano-gpt-data-curation348.860
claude-opus-4-8
1h 1m82 actionsdclm-nano-curation__gSSiCuY
nano-gpt-data-curation310.820
claude-opus-4-8
1h 10m92 actionsdclm-nano-curation__Hk847sf
nano-gpt-data-curation349.200
claude-opus-4-8
51m61 actionsdclm-nano-curation__EAKU6Ra
nano-gpt-data-curation346.450
claude-opus-4-8
1h 1m67 actionsdclm-nano-curation__u8hwsKZ
nano-gpt-data-curation350.740
claude-opus-4-8
46m50 actionsdclm-nano-curation__xo46Sta
nano-gpt-data-curation333.700
claude-opus-4-8
31m34 actionsdclm-nano-curation__CJi6xsp
nano-gpt-data-curation348.420
claude-opus-4-8
39m35 actionsdclm-nano-curation__K2QidbF
nano-gpt-data-curation326.120
claude-opus-4-8
45m50 actionsdclm-nano-curation__aQTkr5P
nano-gpt-data-curation357.000
claude-opus-4-8
21m25 actionsdclm-nano-curation__YiLXzw2
nano-gpt-data-curation312.110
claude-opus-4-8
1h 16m97 actionsdclm-nano-curation__xJxXGaB
nano-gpt-data-curation343.200
claude-opus-4-8
40m36 actionsdclm-nano-curation__wPVYcnk
nano-gpt-data-curation366.740
claude-opus-4-8
43m45 actionsdclm-nano-curation__NFLvnqE
jailbreak-robustness84.713
claude-opus-5
4h 27m307 actionssafety-qwen3-jailbreak__QUkfs8J
jailbreak-robustness85.122
claude-opus-5
1h 44m90 actionssafety-qwen3-jailbreak__ZvH5Sny
nano-gpt-data-curation300.020
claude-opus-5
1h 7m85 actionsdclm-nano-curation__kmNk7VX
nano-gpt-data-curation323.440
claude-opus-5
1h 17m121 actionsdclm-nano-curation__r4AKe3x
nano-gpt-data-curation306.650
claude-opus-5
1h 10m78 actionsdclm-nano-curation__xrPbCYK
nano-gpt-data-curation308.880
gpt-5.6-sol
57m222 actionsdclm-nano-curation__f5FdhJo
nano-gpt-data-curation350.790
gpt-5.6-sol
53m202 actionsdclm-nano-curation__KgMs7QW
nano-gpt-data-curation306.710
gpt-5.6-sol
1h 13m233 actionsdclm-nano-curation__aTQyfVE
nano-gpt-data-curation329.850
gpt-5.6-sol
1h 1m219 actionsdclm-nano-curation__ignQSrt
nano-gpt-data-curation329.480
gpt-5.6-sol
1h 22m285 actionsdclm-nano-curation__NqS7udZ
nano-gpt-data-curation301.790
claude-opus-5
1h 8m60 actionsdclm-nano-curation__uCfhEL6
nano-gpt-data-curation329.220
gpt-5.6-sol
52m217 actionsdclm-nano-curation__nfvFpyv
nano-gpt-data-curation328.220
claude-opus-5
1h 10m49 actionsdclm-nano-curation__HzsPDMT
nano-gpt-data-curation348.850
claude-opus-5
1h 16m71 actionsdclm-nano-curation__EHmEPWe
nano-gpt-data-curation304.640
claude-opus-5
1h 19m68 actionsdclm-nano-curation__VqEFXf4
nano-gpt-data-curation305.420
gpt-5.6-sol
1h 12m269 actionsdclm-nano-curation__SMvDtRx
nano-gpt-data-curation338.210
gpt-5.6-sol
60m273 actionsdclm-nano-curation__zzFhaz8
nano-gpt-data-curation338.020
gpt-5.6-sol
48m183 actionsdclm-nano-curation__EVaJQmY
nano-gpt-data-curation358.540
claude-opus-5
1h 20m46 actionsdclm-nano-curation__twR79Yh
nano-gpt-data-curation327.200
claude-opus-5
41m106 actionsdclm-nano-curation__PCUF55U
nano-gpt-data-curation288.270
claude-opus-5
59m67 actionsdclm-nano-curation__edCjgpD
nano-gpt-data-curation303.510
claude-opus-5
57m61 actionsdclm-nano-curation__phgXX4s
nano-gpt-data-curation309.650
claude-opus-5
1h 11m91 actionsdclm-nano-curation__s2euUXT
nano-gpt-data-curation329.340
claude-opus-5
53m61 actionsdclm-nano-curation__MDUDMmY
nano-gpt-data-curation310.290
gpt-5.6-sol
1h 22m299 actionsdclm-nano-curation__7sx25Ej
nano-gpt-data-curation275.710
claude-opus-5
1h 9m87 actionsdclm-nano-curation__ZPqRAkS
nano-gpt-data-curation303.580
claude-opus-5
1h43 actionsdclm-nano-curation__YxBhtKq
nano-gpt-data-curation333.760
gpt-5.6-sol
33m218 actionsdclm-nano-curation__9upVhik
nano-gpt-data-curation311.480
claude-opus-5
1h 2m71 actionsdclm-nano-curation__nEEkAJz
nano-gpt-data-curation341.410
claude-opus-5
43m33 actionsdclm-nano-curation__MPsY5uL
nano-gpt-data-curation400.420
gpt-5.6-sol
47m138 actionsdclm-nano-curation__W6EguaR
nano-gpt-data-curation319.140
gpt-5.6-sol
1h 15m282 actionsdclm-nano-curation__69HmyDM
nano-gpt-data-curation345.290
claude-opus-5
46m29 actionsdclm-nano-curation__SREjBg2
nano-gpt-data-curation352.340
gpt-5.6-sol
59m223 actionsdclm-nano-curation__KzgeyF6
nano-gpt-data-curation348.640
gpt-5.6-sol
1h 13m261 actionsdclm-nano-curation__XegPhjw
nano-gpt-data-curation324.110
gpt-5.6-sol
39m180 actionsdclm-nano-curation__frqBRu3
nano-gpt-data-curation328.970
gpt-5.6-sol
1h210 actionsdclm-nano-curation__z2rZFLJ
nano-gpt-data-curation307.040
claude-opus-5
49m45 actionsdclm-nano-curation__yc6JrsF
nano-gpt-data-curation287.980
claude-opus-5
1h 17m61 actionsdclm-nano-curation__qs2bLDV
nano-gpt-data-curation313.250
gpt-5.6-sol
1h 14m241 actionsdclm-nano-curation__V4TWBJJ
nano-gpt-data-curation329.440
gpt-5.6-sol
1h 9m249 actionsdclm-nano-curation__JXGjCVp
nano-gpt-data-curation329.880
gpt-5.6-sol
1h 26m304 actionsdclm-nano-curation__4yt6SE3
nano-gpt-data-curation355.460
gpt-5.6-sol
1h 4m217 actionsdclm-nano-curation__5zjKKAd
nano-gpt-data-curation327.680
claude-opus-5
53m45 actionsdclm-nano-curation__rQEvmaF
nano-gpt-data-curation339.590
gpt-5.6-sol
47m164 actionsdclm-nano-curation__8WDjnVr
nano-gpt-data-curation341.250
claude-opus-5
1h 16m57 actionsdclm-nano-curation__AoiWXUF
nano-gpt-data-curation288.000
claude-opus-5
60m51 actionsdclm-nano-curation__BebKMFd
nano-gpt-data-curation362.620
gpt-5.6-sol
42m160 actionsdclm-nano-curation__3WuREza
nano-gpt-data-curation353.340
claude-opus-5
38m34 actionsdclm-nano-curation__HBfU9js
nano-gpt-data-curation404.830
gpt-5.6-sol
19m58 actionsdclm-nano-curation__JnvJaaT
nano-gpt-data-curation398.670
gpt-5.6-sol
45m155 actionsdclm-nano-curation__gfZ879v
nano-gpt-data-curation342.200
gpt-5.6-sol
50m212 actionsdclm-nano-curation__yfNnWEs
nano-gpt-data-curation419.020
gpt-5.6-sol
28m89 actionsdclm-nano-curation__PfpVxLk
nano-gpt-data-curation350.280
gpt-5.6-sol
1h 13m280 actionsdclm-nano-curation__vzTkueh
nano-gpt-data-curation324.230
claude-opus-5
1h 13m66 actionsdclm-nano-curation__YA9bqxQ
nano-gpt-data-curation348.460
claude-opus-5
1h 3m99 actionsdclm-nano-curation__4gETduU
nano-gpt-data-curation324.110
claude-opus-5
40m30 actionsdclm-nano-curation__zQZFhRN
nano-gpt-data-curation347.840
claude-opus-5
46m39 actionsdclm-nano-curation__KmpadEA
nano-gpt-data-curation349.100
gpt-5.6-sol
1h 6m267 actionsdclm-nano-curation__7CCVfar
nano-gpt-data-curation315.490
claude-opus-5
1h 6m80 actionsdclm-nano-curation__xNCncBo
nano-gpt-data-curation331.080
claude-opus-5
27m44 actionsdclm-nano-curation__8gThzQg
nano-gpt-data-curation309.320
claude-opus-5
1h 8m71 actionsdclm-nano-curation__U9oLS3w
nano-gpt-data-curation332.120
claude-opus-5
1h 4m78 actionsdclm-nano-curation__q2CFtsE
nano-gpt-data-curation391.890
gpt-5.6-sol
31m122 actionsdclm-nano-curation__UpMAMLW
nano-gpt-data-curation293.410
claude-opus-5
1h 5m53 actionsdclm-nano-curation__Wz5kwvV
nano-gpt-data-curation308.240
claude-opus-5
52m68 actionsdclm-nano-curation__boCjom2
nano-gpt-data-curation318.280
claude-opus-5
1h 16m99 actionsdclm-nano-curation__DZac9UG
nano-gpt-data-curation315.420
gpt-5.6-sol
1h 16m264 actionsdclm-nano-curation__NAGsecC
nano-gpt-data-curation341.270
claude-opus-5
1h 18m90 actionsdclm-nano-curation__H6LNrrM
nano-gpt-data-curation312.850
claude-opus-5
59m48 actionsdclm-nano-curation__LDprjkQ
nano-gpt-data-curation377.620
gpt-5.6-sol
43m115 actionsdclm-nano-curation__u7ZtWPZ
nano-gpt-data-curation311.880
gpt-5.6-sol
50m187 actionsdclm-nano-curation__XWHDKVK
nano-gpt-data-curation341.160
claude-opus-5
1h 16m84 actionsdclm-nano-curation__D5SotNq
nano-gpt-data-curation323.530
gpt-5.6-sol
1h 6m259 actionsdclm-nano-curation__d9qdiJV
nano-gpt-data-curation313.840
claude-opus-5
1h 12m55 actionsdclm-nano-curation__BgDz4nG
jailbreak-robustness82.152
gpt-5.6-sol
1h 35m257 actionssafety-qwen3-jailbreak__UApBU9n
jailbreak-robustness77.890
gpt-5.6-sol
2h313 actionssafety-qwen3-jailbreak__Z7ckqwX
jailbreak-robustness86.860
gpt-5.6-sol
59m160 actionssafety-qwen3-jailbreak__shjZkUr
jailbreak-robustness83.917
gpt-5.6-sol
1h 6m152 actionssafety-qwen3-jailbreak__XNPUqgv
jailbreak-robustness80.185
claude-opus-5
3h 16m145 actionssafety-qwen3-jailbreak__LQZVM55
jailbreak-robustness88.030
claude-opus-5
3h 18m164 actionssafety-qwen3-jailbreak__q5qpejH
on-policy-self-distillation55.222
gpt-5.6-sol
7h 59m596 actionsopsd-aime24-4gpus__kuc95M7
on-policy-self-distillation54.000
gpt-5.6-sol
8h 10m636 actionsopsd-aime24-4gpus__3tyLi4e
on-policy-self-distillation56.167
claude-opus-5
8h 50m148 actionsopsd-aime24-4gpus__g75tHnA
on-policy-self-distillation54.333
claude-opus-5
9h 4m148 actionsopsd-aime24-4gpus__LSVoBuR
on-policy-self-distillation55.056
gpt-5.6-sol
6h 30m627 actionsopsd-aime24-4gpus__RqGcDty
on-policy-self-distillation56.556
gpt-5.6-sol
9h 21m428 actionsopsd-aime24-4gpus__eNDoWrD
on-policy-self-distillation46.778
claude-opus-5
6h 10m110 actionsopsd-aime24-4gpus__F2Xe6j3
on-policy-self-distillation54.722
claude-opus-5
8h 21m142 actionsopsd-aime24-4gpus__r6P3Lfd