ANNOUNCE  box benchbox · cards GPU-46890836-d8f, GPU-7aa0be10-974 · arm openjev-fp8-readout-32k · task along · start 2026-09-21T21:11:10Z · expect ~6 min
census (arm 9, num_ctx 32768): longest page 80515 tokens, 2 pages still overlong: the-open-call, three-new-voices-at-the-narrators-chair
  on-01                        yes    -> REFUSED: overlong                       — (80515 tokens)
  on-02                        yes    -> yes                                 30.90s
  on-14                        yes    -> yes                                 36.20s
  on-29                        yes    -> REFUSED: overlong                       — (61727 tokens)
  on-33                        yes    -> yes                                 34.45s
  on-34                        yes    -> yes                                 18.39s
  on-40                        yes    -> yes                                 21.55s
  off-04                       no     -> REFUSED: overlong                       — (80515 tokens)
  off-14                       no     -> REFUSED: overlong                       — (61727 tokens)
  off-18                       no     -> no                                  36.21s
{"n": 10, "n_reached": 6, "n_labelled": 6, "refused": 4, "refused_by_reason": {"overlong": 4}, "correct": 6, "errors": 0, "brier": 0.005207814586873897, "reliability": [{"lo": 0.0, "hi": 0.1, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.1, "hi": 0.2, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.2, "hi": 0.3, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.3, "hi": 0.4, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"l
ANNOUNCE  box benchbox · cards GPU-46890836-d8f, GPU-7aa0be10-974 · arm openjev-fp8-readout-32k · task blong · start 2026-09-21T21:21:21Z · expect ~5 min
census (arm 9, num_ctx 32768): longest page 80515 tokens, 2 pages still overlong: the-open-call, three-new-voices-at-the-narrators-chair
  on-01                        -      -> REFUSED: overlong                       — (80515 tokens)
  on-02                        -      -> head-to-head                        30.83s
  on-14                        -      -> the-sound-is-made-on-your-device    36.36s
  on-29                        -      -> REFUSED: overlong                       — (61727 tokens)
  on-33                        -      -> top                                 34.74s
  on-34                        -      -> top                                 18.70s
  on-40                        -      -> top                                 22.04s
{"n": 7, "n_reached": 5, "n_labelled": 0, "refused": 2, "refused_by_reason": {"overlong": 2}, "correct": 0, "errors": 0, "brier": null, "reliability": [{"lo": 0.0, "hi": 0.1, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.1, "hi": 0.2, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.2, "hi": 0.3, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.3, "hi": 0.4, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.4, "hi": 0.
ANNOUNCE  box benchbox · cards GPU-46890836-d8f, GPU-7aa0be10-974 · arm openjev-fp8-generate-32k · task along · start 2026-09-21T21:28:44Z · expect ~6 min
census (arm 9, num_ctx 32768): longest page 80515 tokens, 2 pages still overlong: the-open-call, three-new-voices-at-the-narrators-chair
  on-01                        yes    -> REFUSED: overlong                       — (80515 tokens)
  on-02                        yes    -> yes                                 30.55s
  on-14                        yes    -> yes                                 36.24s
  on-29                        yes    -> REFUSED: overlong                       — (61727 tokens)
  on-33                        yes    -> yes                                 34.48s
  on-34                        yes    -> yes                                 18.40s
  on-40                        yes    -> yes                                 21.55s
  off-04                       no     -> REFUSED: overlong                       — (80515 tokens)
  off-14                       no     -> REFUSED: overlong                       — (61727 tokens)
  off-18                       no     -> no                                  36.23s
{"n": 10, "n_reached": 6, "n_labelled": 6, "refused": 4, "refused_by_reason": {"overlong": 4}, "correct": 6, "errors": 0, "brier": 8.349285404259891e-05, "reliability": [{"lo": 0.0, "hi": 0.1, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.1, "hi": 0.2, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.2, "hi": 0.3, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.3, "hi": 0.4, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"
ANNOUNCE  box benchbox · cards GPU-46890836-d8f, GPU-7aa0be10-974 · arm openjev-fp8-generate-32k · task blong · start 2026-09-21T21:38:56Z · expect ~5 min
census (arm 9, num_ctx 32768): longest page 80515 tokens, 2 pages still overlong: the-open-call, three-new-voices-at-the-narrators-chair
  on-01                        -      -> REFUSED: overlong                       — (80515 tokens)
  on-02                        -      -> head-to-head                        30.84s
  on-14                        -      -> the-sound-is-made-on-your-device    36.36s
  on-29                        -      -> REFUSED: overlong                       — (61727 tokens)
  on-33                        -      -> top                                 34.78s
  on-34                        -      -> top                                 18.72s
  on-40                        -      -> top                                 22.08s
{"n": 7, "n_reached": 5, "n_labelled": 0, "refused": 2, "refused_by_reason": {"overlong": 2}, "correct": 0, "errors": 0, "brier": null, "reliability": [{"lo": 0.0, "hi": 0.1, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.1, "hi": 0.2, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.2, "hi": 0.3, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.3, "hi": 0.4, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.4, "hi": 0.