| aegis2-noul-test-v1.json | 185 Bytes | | 193fcad5 |
| aqua-rat-choice-test-v1.json | 206 Bytes | | bf96d868 |
| arc-choice-test-v1.json | 196 Bytes | | 023c4e1c |
| arct-choice-test-v1.json | 198 Bytes | | bbc437f8 |
| argument-quality-choice-test-v1.json | 222 Bytes | | 1802a4af |
| argument-quality-noul-test-v1.json | 205 Bytes | | 4f425451 |
| babi-nli-noul-test-v1.json | 189 Bytes | | d4e6489b |
| banking77-choice-test-v1.json | 208 Bytes | | a6abfef8 |
| bbq-choice-test-v1.json | 196 Bytes | | 714becad |
| boardgameqa-choice-test-v1.json | 212 Bytes | | d7c5218c |
| canttalk-noul-test-v1.json | 189 Bytes | | 846df745 |
| civil-comments-noul-test-v1.json | 201 Bytes | | 0cbd1052 |
| cladder-noul-test-v1.json | 187 Bytes | | 5ae71093 |
| clinc-choice-test-v1.json | 200 Bytes | | 3055838e |
| contract-nli-choice-test-v1.json | 215 Bytes | | 0872b544 |
| corr2cause-choice-test-v1.json | 210 Bytes | | 99d85b1e |
| creak-noul-test-v1.json | 183 Bytes | | 819f003d |
| crows-pairs-choice-test-v1.json | 212 Bytes | | 42539bcc |
| dbpedia-choice-test-v1.json | 204 Bytes | | b56277e4 |
| defeasible-nli-choice-test-v1.json | 218 Bytes | | 2f833525 |
| esci-choice-test-v1.json | 198 Bytes | | 111c2c81 |
| ethics-choice-test-v1.json | 200 Bytes | | d66ff15e |
| ethics-noul-test-v1.json | 183 Bytes | | 3c63280c |
| ethos-noul-test-v1.json | 183 Bytes | | c79f2530 |
| few-nerd-choice-test-v1.json | 206 Bytes | | 83190812 |
| fol-nli-choice-test-v1.json | 204 Bytes | | a90545a0 |
| followir-core17-noul-test-v1.json | 203 Bytes | | 84d302f1 |
| followir-news21-noul-test-v1.json | 203 Bytes | | 46656123 |
| followir-robust04-noul-test-v1.json | 207 Bytes | | b5e72057 |
| go-emotions-noul-test-v1.json | 196 Bytes | | f61f8903 |
| gretel-pii-choice-test-v1.json | 210 Bytes | | 119e3af4 |
| gsm8k-choice-test-v1.json | 200 Bytes | | 17631188 |
| hans-noul-test-v1.json | 181 Bytes | | 8a599df8 |
| hatecheck-noul-test-v1.json | 191 Bytes | | e4697335 |
| hh-rlhf-choice-test-v1.json | 204 Bytes | | 7f3ccec4 |
| hwu64-choice-test-v1.json | 200 Bytes | | c20331f9 |
| impli-noul-test-v1.json | 183 Bytes | | ff250a05 |
| laya--ag-news-choice-test-v1.json | 216 Bytes | | 10b71bcd |
| laya--enron-spam-noul-test-v1.json | 205 Bytes | | 2e6efb14 |
| laya--typed-decisions-choice-test-v1.json | 232 Bytes | | 54816020 |
| laya--typed-decisions-noul-test-v1.json | 215 Bytes | | 41752679 |
| laya--typed-decisions-score-test-v1.json | 234 Bytes | | 6e9e2683 |
| lexcomp-noul-test-v1.json | 187 Bytes | | c1434a73 |
| logical-entailment-noul-test-v1.json | 209 Bytes | | 41fc0c79 |
| lonli-choice-test-v1.json | 200 Bytes | | 0ef35c95 |
| massive-choice-test-v1.json | 204 Bytes | | 07c7b519 |
| miqa-choice-test-v1.json | 198 Bytes | | cb3e5aec |
| mtop-choice-test-v1.json | 198 Bytes | | 3c7791d7 |
| nlsat-noul-test-v1.json | 183 Bytes | | 5b4d4c51 |
| open-jev--amount-extraction-control-v1-choice-test-v1.json | 264 Bytes | | 5ca43d7c |
| open-jev--amount-extraction-control-v1-noul-test-v1.json | 247 Bytes | | 22ded4fc |
| open-jev--browser-control-v1-choice-test-v1.json | 246 Bytes | | fb99767f |
| open-jev--citation-control-v1-choice-test-v1.json | 248 Bytes | | b91ce355 |
| open-jev--context-retention-control-v1-noul-test-v1.json | 249 Bytes | | 2868a560 |
| open-jev--customer-control-v1-choice-test-v1.json | 246 Bytes | | 1d54bd71 |
| open-jev--customer-control-v1-noul-test-v1.json | 229 Bytes | | e5a55df5 |
| open-jev--customer-control-v1-score-test-v1.json | 248 Bytes | | ec73b8dd |
| open-jev--drone-control-v1-choice-test-v1.json | 240 Bytes | | fe115a06 |
| open-jev--drone-control-v1-noul-test-v1.json | 223 Bytes | | d60ec836 |
| open-jev--drone-control-v1-score-test-v1.json | 242 Bytes | | 9c3c9af4 |
| open-jev--email-selection-control-v1-choice-test-v1.json | 260 Bytes | | a462ba17 |
| open-jev--email-selection-control-v1-noul-test-v1.json | 243 Bytes | | b30871a3 |
| open-jev--entity-alignment-control-v1-noul-test-v1.json | 245 Bytes | | c8d3023f |
| open-jev--entity-alignment-control-v1-score-test-v1.json | 264 Bytes | | 17109d25 |
| open-jev--ir-control-v1-choice-test-v1.json | 234 Bytes | | a5e426ac |
| open-jev--ir-control-v1-noul-test-v1.json | 217 Bytes | | bf8c63e7 |
| open-jev--ir-control-v1-score-test-v1.json | 236 Bytes | | 4477f118 |
| open-jev--mailroom-control-v1-choice-test-v1.json | 246 Bytes | | d26e986b |
| open-jev--mailroom-control-v1-noul-test-v1.json | 229 Bytes | | ea38e1a7 |
| open-jev--painting-geometry-v1-choice-test-v1.json | 248 Bytes | | c57ee462 |
| open-jev--painting-geometry-v1-noul-test-v1.json | 231 Bytes | | 670f489d |
| open-jev--painting-geometry-v1-score-test-v1.json | 250 Bytes | | 15c5714f |
| open-jev--phone-extraction-control-v1-choice-test-v1.json | 262 Bytes | | 02109af1 |
| open-jev--phone-extraction-control-v1-noul-test-v1.json | 245 Bytes | | 539dc03e |
| open-jev--reasoning-control-v1-choice-test-v1.json | 248 Bytes | | 977d7b9c |
| open-jev--reasoning-control-v1-noul-test-v1.json | 231 Bytes | | 310b1cb6 |
| open-jev--reasoning-control-v1-score-test-v1.json | 250 Bytes | | 7ffb2f38 |
| open-jev--silent-failure-control-v1-noul-test-v1.json | 243 Bytes | | 3a39be53 |
| open-jev--snake-v1-choice-test-v1.json | 224 Bytes | | fac06667 |
| open-jev--snake-v1-noul-test-v1.json | 207 Bytes | | 35f51f2e |
| open-jev--sponsor-segment-control-v1-choice-test-v1.json | 262 Bytes | | 772cb24a |
| open-jev--tic-tac-toe-v1-choice-test-v1.json | 238 Bytes | | bba2ad26 |
| open-jev--vizdoom-basic-v1-noul-test-v1.json | 223 Bytes | | 2757fd7d |
| open-jev--vizdoom-basic-v1-score-test-v1.json | 242 Bytes | | 983bd2ee |
| open-jev--workflow-controls-v1--agent-trace-observability-noul-test-v1.json | 287 Bytes | | 1f6fd2b9 |
| open-jev--workflow-controls-v1--customer-service-noul-test-v1.json | 269 Bytes | | 0e2c33de |
| open-jev--workflow-controls-v1--invoice-processing-noul-test-v1.json | 273 Bytes | | e7688772 |
| open-jev--workflow-controls-v1--security-incidents-noul-test-v1.json | 273 Bytes | | cd197bd2 |
| openbookqa-choice-test-v1.json | 210 Bytes | | e31bb9e1 |
| patent-similarity-score-test-v1.json | 226 Bytes | | acc5c0a8 |
| paws-noul-test-v1.json | 181 Bytes | | e3477ece |
| plane-noul-test-v1.json | 183 Bytes | | fd59697c |
| poem-sentiment-choice-test-v1.json | 218 Bytes | | ad65aca9 |
| qasper-noul-test-v1.json | 185 Bytes | | 6855d27a |
| quartz-choice-test-v1.json | 202 Bytes | | c1aee845 |
| robust-lr-choice-test-v1.json | 208 Bytes | | 2cbed27d |
| ruletaker-noul-test-v1.json | 191 Bytes | | 6e5f99bb |
| s1mb-generalization-contextual-choice-choice-test-v1.json | 264 Bytes | | 24cdc454 |
| s1mb-generalization-contextual-noul-noul-test-v1.json | 243 Bytes | | 0a5817ed |
| s1mb-generalization-contextual-score-score-test-v1.json | 264 Bytes | | 86b04c7f |
|