Jev bench results

Model: opencode-go/deepseek-v4.1-flash. Thinking: high.

Jev connection: 149 of 300 with-Jev runs that reached the model got a Jev answer (50%). Automatic arm: 0 of 150 model-reached B runs called Jev; 150 did not call Jev.

Jev round trip: n=157, median 464.6 ms, p90 1245.3 ms, p95 1468.8 ms.

Tokens (Pi usage fields, summed): A input 447114 / output 42804 / cache read 30592 / cache write 0; B input 438467 / output 49315 / cache read 39680 / cache write 0; C input 1230791 / output 167029 / cache read 1860608 / cache write 0.

Agent model spend (Pi usage cost, summed): A $0.0928; B $0.0955; C $0.2904.

History: the 2026-09-22 two-arm Pi run recorded 150 pairs; after 43 with-Jev runs reached the local model, 127.0.0.1:8000 stopped accepting connections (Pi reported Connection error with zero tokens, on both arms) and the remaining 107 runs were server failures, not model speed.

Stop: all 150 triplets recorded

A directB automaticC forced
Accuracy: share of items correct

not measured (0 labeled items)

Evaluator overhead: items per minute (items / summed wall time)
0.00/min5.84/min11.69/min17.53/min23.37/minAll itemsAll items · A direct: 14.95/min14.95/minAll items · B automatic: 14.19/min14.19/minAll items · C forced: 3.73/min3.73/minjev_classifyjev_classify · A direct: 22.64/min22.64/minjev_classify · B automatic: 21.97/min21.97/minjev_classify · C forced: 4.57/min4.57/minjev_comparejev_compare · A direct: 22.79/min22.79/minjev_compare · B automatic: 22.65/min22.65/minjev_compare · C forced: 5.30/min5.30/minjev_decidejev_decide · A direct: 7.22/min7.22/minjev_decide · B automatic: 11.39/min11.39/minjev_decide · C forced: 2.75/min2.75/minjev_extractjev_extract · A direct: 20.40/min20.40/minjev_extract · B automatic: 18.38/min18.38/minjev_extract · C forced: 4.14/min4.14/minjev_findjev_find · A direct: 20.98/min20.98/minjev_find · B automatic: 23.37/min23.37/minjev_find · C forced: 4.13/min4.13/minjev_gatejev_gate · A direct: 9.11/min9.11/minjev_gate · B automatic: 5.14/min5.14/minjev_gate · C forced: 2.79/min2.79/minjev_rerankjev_rerank · A direct: 13.47/min13.47/minjev_rerank · B automatic: 12.69/min12.69/minjev_rerank · C forced: 3.47/min3.47/minjev_reviewjev_review · A direct: 15.46/min15.46/minjev_review · B automatic: 15.29/min15.29/minjev_review · C forced: 3.26/min3.26/minjev_screenjev_screen · A direct: 20.17/min20.17/minjev_screen · B automatic: 21.40/min21.40/minjev_screen · C forced: 4.35/min4.35/minjev_verifyjev_verify · A direct: 21.15/min21.15/minjev_verify · B automatic: 22.37/min22.37/minjev_verify · C forced: 4.11/min4.11/minunit: items/min
Time consumed: total wall time
0.00 s603.59 s1207.19 s1810.78 s2414.37 sAll itemsAll items · A direct: 601.90 s601.90 sAll items · B automatic: 634.36 s634.36 sAll items · C forced: 2414.37 s2414.37 sjev_classifyjev_classify · A direct: 39.75 s39.75 sjev_classify · B automatic: 40.96 s40.96 sjev_classify · C forced: 196.87 s196.87 sjev_comparejev_compare · A direct: 39.50 s39.50 sjev_compare · B automatic: 39.73 s39.73 sjev_compare · C forced: 169.87 s169.87 sjev_decidejev_decide · A direct: 124.65 s124.65 sjev_decide · B automatic: 79.03 s79.03 sjev_decide · C forced: 327.21 s327.21 sjev_extractjev_extract · A direct: 44.12 s44.12 sjev_extract · B automatic: 48.96 s48.96 sjev_extract · C forced: 217.63 s217.63 sjev_findjev_find · A direct: 42.90 s42.90 sjev_find · B automatic: 38.51 s38.51 sjev_find · C forced: 218.10 s218.10 sjev_gatejev_gate · A direct: 98.78 s98.78 sjev_gate · B automatic: 175.09 s175.09 sjev_gate · C forced: 322.93 s322.93 sjev_rerankjev_rerank · A direct: 66.80 s66.80 sjev_rerank · B automatic: 70.93 s70.93 sjev_rerank · C forced: 259.22 s259.22 sjev_reviewjev_review · A direct: 58.22 s58.22 sjev_review · B automatic: 58.86 s58.86 sjev_review · C forced: 276.41 s276.41 sjev_screenjev_screen · A direct: 44.62 s44.62 sjev_screen · B automatic: 42.05 s42.05 sjev_screen · C forced: 206.94 s206.94 sjev_verifyjev_verify · A direct: 42.56 s42.56 sjev_verify · B automatic: 40.23 s40.23 sjev_verify · C forced: 219.19 s219.19 sunit: seconds

Headline (complete triplets)

accuracynot measured (0 labeled items)
triplets150
wall_A_median_s3.058
wall_A_p90_s5.279
wall_A_p95_s6.174
jev_usd_A0
called_jev_A0
called_jev_share_A0
wall_B_median_s2.907
wall_B_p90_s4.86
wall_B_p95_s8.092
jev_usd_B0
called_jev_B0
called_jev_share_B0
wall_C_median_s13.95
wall_C_p90_s21.01
wall_C_p95_s28.67
jev_usd_C0.005969
called_jev_C150
called_jev_share_C1
wall_b_minus_a_median_s-0.1034
wall_b_minus_a_p90_s1.034
wall_b_minus_a_p95_s2.035
wall_b_minus_a_sign_p0.1205
wall_c_minus_a_median_s10.43
wall_c_minus_a_p90_s15.99
wall_c_minus_a_p95_s21.56
wall_c_minus_a_sign_p1.587e-41

Runs

runtoolstatususe gateanswercorrectwall sJev calls
classify-01.Ajev_classifyokn/a (arm has no Jev)billingFalse2.720
classify-01.Bjev_classifyokdid not call JevbillingFalse2.450
classify-01.Cjev_classifyokused JevbillingFalse11.311
classify-02.Ajev_classifyokn/a (arm has no Jev)accountFalse2.190
classify-02.Bjev_classifyokdid not call JevaccountFalse1.670
classify-02.Cjev_classifyokused JevaccountFalse12.291
classify-03.Ajev_classifyokn/a (arm has no Jev)shippingFalse1.590
classify-03.Bjev_classifyokdid not call JevshippingFalse2.530
classify-03.Cjev_classifyokused JevshippingFalse11.771
classify-04.Ajev_classifyokn/a (arm has no Jev)billingFalse2.710
classify-04.Bjev_classifyokdid not call JevbillingFalse2.430
classify-04.Cjev_classifyokused JevbillingFalse16.821
classify-05.Ajev_classifyokn/a (arm has no Jev)product_defectFalse2.550
classify-05.Bjev_classifyokdid not call Jevproduct_defectFalse2.760
classify-05.Cjev_classifyokused Jevproduct_defectFalse13.721
classify-06.Ajev_classifyokn/a (arm has no Jev)test_failureFalse2.360
classify-06.Bjev_classifyokdid not call Jevtest_failureFalse2.690
classify-06.Cjev_classifyokused Jevtest_failureFalse12.681
classify-07.Ajev_classifyokn/a (arm has no Jev)flakyFalse2.140
classify-07.Bjev_classifyokdid not call JevflakyFalse2.280
classify-07.Cjev_classifyokused JevflakyFalse10.551
classify-08.Ajev_classifyokn/a (arm has no Jev)configFalse3.580
classify-08.Bjev_classifyokdid not call JevconfigFalse2.440
classify-08.Cjev_classifyokused JevconfigFalse12.081
classify-09.Ajev_classifyokn/a (arm has no Jev)infraFalse2.720
classify-09.Bjev_classifyokdid not call JevinfraFalse3.210
classify-09.Cjev_classifyokused JevinfraFalse13.131
classify-10.Ajev_classifyokn/a (arm has no Jev)configFalse2.590
classify-10.Bjev_classifyokdid not call JevconfigFalse2.570
classify-10.Cjev_classifyokused JevconfigFalse13.041
classify-11.Ajev_classifyokn/a (arm has no Jev)docs_onlyFalse2.470
classify-11.Bjev_classifyokdid not call Jevdocs_onlyFalse2.790
classify-11.Cjev_classifyokused Jevdocs_onlyFalse9.931
classify-12.Ajev_classifyokn/a (arm has no Jev)breaking_changeFalse3.560
classify-12.Bjev_classifyokdid not call Jevbreaking_changeFalse3.460
classify-12.Cjev_classifyokused Jevbreaking_changeFalse14.121
classify-13.Ajev_classifyokn/a (arm has no Jev)securityFalse3.180
classify-13.Bjev_classifyokdid not call JevsecurityFalse2.590
classify-13.Cjev_classifyokused JevsecurityFalse13.181
classify-14.Ajev_classifyokn/a (arm has no Jev)bugfixFalse2.350
classify-14.Bjev_classifyokdid not call JevbugfixFalse3.370
classify-14.Cjev_classifyokused JevbugfixFalse16.031
classify-15.Ajev_classifyokn/a (arm has no Jev)securityFalse3.050
classify-15.Bjev_classifyokdid not call JevsecurityFalse3.720
classify-15.Cjev_classifyokused JevsecurityFalse16.231
compare-01.Ajev_compareokn/a (arm has no Jev)same_factFalse3.070
compare-01.Bjev_compareokdid not call Jevsame_factFalse2.920
compare-01.Cjev_compareokused Jevsame_factFalse8.701
compare-02.Ajev_compareokn/a (arm has no Jev)contradictsFalse2.930
compare-02.Bjev_compareokdid not call JevcontradictsFalse4.380
compare-02.Cjev_compareokused JevcontradictsFalse12.441
compare-03.Ajev_compareokn/a (arm has no Jev)contradictsFalse3.570
compare-03.Bjev_compareokdid not call JevcontradictsFalse3.830
compare-03.Cjev_compareokused JevcontradictsFalse11.671
compare-04.Ajev_compareokn/a (arm has no Jev)different_factsFalse1.910
compare-04.Bjev_compareokdid not call Jevdifferent_factsFalse3.020
compare-04.Cjev_compareokused Jevdifferent_factsFalse9.501
compare-05.Ajev_compareokn/a (arm has no Jev)same_factFalse2.770
compare-05.Bjev_compareokdid not call Jevsame_factFalse2.170
compare-05.Cjev_compareokused Jevsame_factFalse12.561
compare-06.Ajev_compareokn/a (arm has no Jev)same_factFalse2.000
compare-06.Bjev_compareokdid not call Jevsame_factFalse1.790
compare-06.Cjev_compareokused Jevsame_factFalse12.241
compare-07.Ajev_compareokn/a (arm has no Jev)contradictsFalse3.170
compare-07.Bjev_compareokdid not call JevcontradictsFalse2.430
compare-07.Cjev_compareokused JevcontradictsFalse12.641
compare-08.Ajev_compareokn/a (arm has no Jev)different_factsFalse2.540
compare-08.Bjev_compareokdid not call Jevdifferent_factsFalse2.390
compare-08.Cjev_compareokused Jevdifferent_factsFalse9.751
compare-09.Ajev_compareokn/a (arm has no Jev)contradictsFalse2.510
compare-09.Bjev_compareokdid not call JevcontradictsFalse1.500
compare-09.Cjev_compareokused JevcontradictsFalse9.151
compare-10.Ajev_compareokn/a (arm has no Jev)same_factFalse2.160
compare-10.Bjev_compareokdid not call Jevsame_factFalse1.790
compare-10.Cjev_compareokused Jevsame_factFalse8.511
compare-11.Ajev_compareokn/a (arm has no Jev)same_factFalse2.530
compare-11.Bjev_compareokdid not call Jevsame_factFalse2.370
compare-11.Cjev_compareokused Jevsame_factFalse12.591
compare-12.Ajev_compareokn/a (arm has no Jev)contradictsFalse2.480
compare-12.Bjev_compareokdid not call JevcontradictsFalse3.810
compare-12.Cjev_compareokused JevcontradictsFalse12.841
compare-13.Ajev_compareokn/a (arm has no Jev)different_factsFalse2.910
compare-13.Bjev_compareokdid not call Jevdifferent_factsFalse2.360
compare-13.Cjev_compareokused Jevdifferent_factsFalse13.821
compare-14.Ajev_compareokn/a (arm has no Jev)different_factsFalse2.750
compare-14.Bjev_compareokdid not call Jevdifferent_factsFalse2.150
compare-14.Cjev_compareokused Jevdifferent_factsFalse12.451
compare-15.Ajev_compareokn/a (arm has no Jev)different_factsFalse2.190
compare-15.Bjev_compareokdid not call Jevdifferent_factsFalse2.810
compare-15.Cjev_compareokused Jevdifferent_factsFalse11.001
decide-01.Ajev_decideokn/a (arm has no Jev)ship_fullFalse5.280
decide-01.Bjev_decideokdid not call Jevship_fullFalse4.810
decide-01.Cjev_decideokused Jevship_fullFalse16.801
decide-02.Ajev_decideokn/a (arm has no Jev)ship_flaggedFalse3.430
decide-02.Bjev_decideokdid not call Jevship_flaggedFalse4.470
decide-02.Cjev_decideokused Jevship_flaggedFalse12.201
decide-03.Ajev_decideokn/a (arm has no Jev)escapeFalse42.080
decide-03.Bjev_decideokdid not call JevescapeFalse17.280
decide-03.Cjev_decideokused JevescapeFalse30.951
decide-04.Ajev_decideokn/a (arm has no Jev)delayFalse5.190
decide-04.Bjev_decideokdid not call JevdelayFalse5.070
decide-04.Cjev_decideokused JevdelayFalse15.071
decide-05.Ajev_decideokn/a (arm has no Jev)escapeFalse27.260
decide-05.Bjev_decideokdid not call JevescapeFalse5.940
decide-05.Cjev_decideokused JevescapeFalse66.031
decide-06.Ajev_decideokn/a (arm has no Jev)credit_20False3.560
decide-06.Bjev_decideokdid not call Jevcredit_20False2.810
decide-06.Cjev_decideokused Jevcredit_20False15.531
decide-07.Ajev_decideokn/a (arm has no Jev)no_remedyFalse5.300
decide-07.Bjev_decideokdid not call Jevno_remedyFalse4.870
decide-07.Cjev_decideokused Jevcredit_20False52.041
decide-08.Ajev_decideokn/a (arm has no Jev)full_refundFalse3.340
decide-08.Bjev_decideokdid not call Jevfull_refundFalse3.280
decide-08.Cjev_decideokused Jevfull_refundFalse13.901
decide-09.Ajev_decideokn/a (arm has no Jev)damage_claimFalse2.550
decide-09.Bjev_decideokdid not call Jevdamage_claimFalse2.630
decide-09.Cjev_decideokused Jevdamage_claimFalse14.571
decide-10.Ajev_decideokn/a (arm has no Jev)no_remedyFalse5.400
decide-10.Bjev_decideokdid not call Jevno_remedyFalse6.040
decide-10.Cjev_decideokused JevescapeFalse16.571
decide-11.Ajev_decideokn/a (arm has no Jev)revert_commitFalse3.750
decide-11.Bjev_decideokdid not call Jevrevert_commitFalse3.970
decide-11.Cjev_decideokused Jevrevert_commitFalse15.601
decide-12.Ajev_decideokn/a (arm has no Jev)rerunFalse4.340
decide-12.Bjev_decideokdid not call JevrerunFalse2.170
decide-12.Cjev_decideokused JevrerunFalse11.901
decide-13.Ajev_decideokn/a (arm has no Jev)escapeFalse4.760
decide-13.Bjev_decideokdid not call JevescapeFalse7.660
decide-13.Cjev_decideokused JevescapeFalse14.981
decide-14.Ajev_decideokn/a (arm has no Jev)fix_forwardFalse2.860
decide-14.Bjev_decideokdid not call Jevfix_forwardFalse3.690
decide-14.Cjev_decideokused Jevfix_forwardFalse13.821
decide-15.Ajev_decideokn/a (arm has no Jev)escapeFalse5.550
decide-15.Bjev_decideokdid not call JevescapeFalse4.320
decide-15.Cjev_decideokused JevescapeFalse17.261
extract-01.Ajev_extractokn/a (arm has no Jev)$5,153.50False3.050
extract-01.Bjev_extractokdid not call Jev$5,153.50False3.930
extract-01.Cjev_extractokused Jev$5,153.50False15.381
extract-02.Ajev_extractokn/a (arm has no Jev)not statedFalse3.740
extract-02.Bjev_extractokdid not call Jevnot statedFalse2.960
extract-02.Cjev_extractokused Jevnot statedFalse14.931
extract-03.Ajev_extractokn/a (arm has no Jev)$1,020.00False2.660
extract-03.Bjev_extractokdid not call Jev$1,020.00False2.620
extract-03.Cjev_extractokused Jev$1,020.00False18.241
extract-04.Ajev_extractokn/a (arm has no Jev)NF-2026-08102False2.180
extract-04.Bjev_extractokdid not call JevNF-2026-08102False2.450
extract-04.Cjev_extractokused JevNF-2026-08102False9.251
extract-05.Ajev_extractokn/a (arm has no Jev)not statedFalse3.490
extract-05.Bjev_extractokdid not call Jevnot statedFalse2.990
extract-05.Cjev_extractokused Jevnot statedFalse14.581
extract-06.Ajev_extractokn/a (arm has no Jev)shopkit-4.4.0-rc2False2.640
extract-06.Bjev_extractokdid not call Jevshopkit-4.4.0-rc2False3.360
extract-06.Cjev_extractokused Jevshopkit-4.4.0-rc2False18.751
extract-07.Ajev_extractokn/a (arm has no Jev)not statedFalse4.250
extract-07.Bjev_extractokdid not call Jevnot statedFalse4.820
extract-07.Cjev_extractokused Jevnot statedFalse16.581
extract-08.Ajev_extractokn/a (arm has no Jev)1False2.860
extract-08.Bjev_extractokdid not call Jev1False2.630
extract-08.Cjev_extractokused Jev1False15.531
extract-09.Ajev_extractokn/a (arm has no Jev)deps-v2-a41cFalse2.840
extract-09.Bjev_extractokdid not call Jevdeps-v2-a41cFalse8.440
extract-09.Cjev_extractokused Jevdeps-v2-a41cFalse12.791
extract-10.Ajev_extractokn/a (arm has no Jev)not statedFalse2.660
extract-10.Bjev_extractokdid not call Jevnot statedFalse2.830
extract-10.Cjev_extractokused Jevnot statedFalse15.241
extract-11.Ajev_extractokn/a (arm has no Jev)BKT-2291-0475False2.870
extract-11.Bjev_extractokdid not call JevBKT-2291-0475False2.340
extract-11.Cjev_extractokused JevBKT-2291-0475False14.031
extract-12.Ajev_extractokn/a (arm has no Jev)SO-778120False3.170
extract-12.Bjev_extractokdid not call JevSO-778120False2.330
extract-12.Cjev_extractokused JevSO-778120False10.311
extract-13.Ajev_extractokn/a (arm has no Jev)2026-02-14False1.980
extract-13.Bjev_extractokdid not call Jev2026-02-14False2.630
extract-13.Cjev_extractokused Jev2026-02-14False15.061
extract-14.Ajev_extractokn/a (arm has no Jev)2026-09-12False3.100
extract-14.Bjev_extractokdid not call Jev2026-09-12False2.170
extract-14.Cjev_extractokused Jev2026-09-12False14.151
extract-15.Ajev_extractokn/a (arm has no Jev)not statedFalse2.620
extract-15.Bjev_extractokdid not call Jevnot statedFalse2.470
extract-15.Cjev_extractokused Jevnot statedFalse12.821
find-01.Ajev_findokn/a (arm has no Jev)ret-finalFalse2.400
find-01.Bjev_findokdid not call Jevret-finalFalse2.240
find-01.Cjev_findokused Jevret-finalFalse13.611
find-02.Ajev_findokn/a (arm has no Jev)price-dropFalse2.690
find-02.Bjev_findokdid not call Jevprice-dropFalse2.120
find-02.Cjev_findokused Jevprice-dropFalse16.831
find-03.Ajev_findokn/a (arm has no Jev)ship-intlFalse1.590
find-03.Bjev_findokdid not call Jevship-intlFalse2.970
find-03.Cjev_findokused Jevship-intlFalse11.311
find-04.Ajev_findokn/a (arm has no Jev)pay-methodsFalse2.650
find-04.Bjev_findokdid not call Jevpay-methodsFalse2.160
find-04.Cjev_findokused Jevpay-methodsFalse12.151
find-05.Ajev_findokn/a (arm has no Jev)noneFalse2.260
find-05.Bjev_findokdid not call JevnoneFalse2.170
find-05.Cjev_findokused JevnoneFalse10.651
find-06.Ajev_findokn/a (arm has no Jev)registry-401False3.830
find-06.Bjev_findokdid not call Jevregistry-401False4.860
find-06.Cjev_findokused Jevregistry-401False13.291
find-07.Ajev_findokn/a (arm has no Jev)flaky-quarantineFalse8.010
find-07.Bjev_findokdid not call JevnoneFalse3.260
find-07.Cjev_findokused JevnoneFalse17.011
find-08.Ajev_findokn/a (arm has no Jev)job-timeoutsFalse3.060
find-08.Bjev_findokdid not call Jevjob-timeoutsFalse2.980
find-08.Cjev_findokused Jevjob-timeoutsFalse15.391
find-09.Ajev_findokn/a (arm has no Jev)noneFalse3.160
find-09.Bjev_findokdid not call JevnoneFalse1.820
find-09.Cjev_findokused JevnoneFalse16.801
find-10.Ajev_findokn/a (arm has no Jev)cache-bustFalse1.920
find-10.Bjev_findokdid not call Jevcache-bustFalse1.380
find-10.Cjev_findokused Jevcache-bustFalse13.491
find-11.Ajev_findokn/a (arm has no Jev)v3.3.0False3.120
find-11.Bjev_findokdid not call Jevv3.3.0False2.840
find-11.Cjev_findokused Jevv3.3.0False14.431
find-12.Ajev_findokn/a (arm has no Jev)v3.2.1False2.020
find-12.Bjev_findokdid not call Jevv3.2.1False3.050
find-12.Cjev_findokused Jevv3.2.1False19.922
find-13.Ajev_findokn/a (arm has no Jev)noneFalse2.530
find-13.Bjev_findokdid not call JevnoneFalse2.200
find-13.Cjev_findokused JevnoneFalse12.301
find-14.Ajev_findokn/a (arm has no Jev)v3.1.1False1.480
find-14.Bjev_findokdid not call Jevv3.1.1False1.920
find-14.Cjev_findokused Jevv3.1.1False12.761
find-15.Ajev_findokn/a (arm has no Jev)noneFalse2.190
find-15.Bjev_findokdid not call JevnoneFalse2.550
find-15.Cjev_findokused JevnoneFalse18.171
gate-01.Ajev_gateokn/a (arm has no Jev)acceptFalse40.530
gate-01.Bjev_gateokdid not call JevacceptFalse8.730
gate-01.Cjev_gateokused JevrejectFalse25.171
gate-02.Ajev_gateokn/a (arm has no Jev)rejectFalse2.620
gate-02.Bjev_gateokdid not call JevrejectFalse2.390
gate-02.Cjev_gateokused JevrejectFalse13.211
gate-03.Ajev_gateokn/a (arm has no Jev)rejectFalse4.140
gate-03.Bjev_gateokdid not call JevrejectFalse4.170
gate-03.Cjev_gateokused JevrejectFalse14.381
gate-04.Ajev_gateokn/a (arm has no Jev)acceptFalse2.890
gate-04.Bjev_gateokdid not call JevacceptFalse2.890
gate-04.Cjev_gateokused JevacceptFalse16.281
gate-05.Ajev_gateokn/a (arm has no Jev)acceptFalse6.020
gate-05.Bjev_gateokdid not call JevacceptFalse5.170
gate-05.Cjev_gateokused JevacceptFalse14.391
gate-06.Ajev_gateokn/a (arm has no Jev)rejectFalse4.410
gate-06.Bjev_gateokdid not call JevrejectFalse2.500
gate-06.Cjev_gateokused JevrejectFalse14.341
gate-07.Ajev_gateokn/a (arm has no Jev)acceptFalse3.560
gate-07.Bjev_gateokdid not call JevacceptFalse9.530
gate-07.Cjev_gateokused JevacceptFalse69.591
gate-08.Ajev_gateokn/a (arm has no Jev)rejectFalse4.700
gate-08.Bjev_gateokdid not call JevrejectFalse4.320
gate-08.Cjev_gateokused JevrejectFalse13.651
gate-09.Ajev_gateokn/a (arm has no Jev)rejectFalse4.490
gate-09.Bjev_gateokdid not call JevrejectFalse3.410
gate-09.Cjev_gateokused JevrejectFalse14.421
gate-10.Ajev_gateokn/a (arm has no Jev)rejectFalse3.470
gate-10.Bjev_gateokdid not call JevrejectFalse4.250
gate-10.Cjev_gateokused JevrejectFalse16.391
gate-11.Ajev_gateokn/a (arm has no Jev)acceptFalse4.070
gate-11.Bjev_gateokdid not call JevacceptFalse24.550
gate-11.Cjev_gateokused JevrejectFalse44.081
gate-12.Ajev_gateokn/a (arm has no Jev)rejectFalse4.850
gate-12.Bjev_gateokdid not call JevrejectFalse3.120
gate-12.Cjev_gateokused JevrejectFalse16.361
gate-13.Ajev_gateokn/a (arm has no Jev)acceptFalse2.850
gate-13.Bjev_gateokdid not call JevacceptFalse2.330
gate-13.Cjev_gateokused JevacceptFalse14.451
gate-14.Ajev_gateokn/a (arm has no Jev)rejectFalse3.980
gate-14.Bjev_gateokdid not call JevrejectFalse4.540
gate-14.Cjev_gateokused JevrejectFalse14.471
gate-15.Ajev_gateokn/a (arm has no Jev)acceptFalse6.200
gate-15.Bjev_gateokdid not call JevrejectFalse93.190
gate-15.Cjev_gateokused JevacceptFalse21.761
rerank-01.Ajev_rerankokn/a (arm has no Jev)['kb-e5', 'kb-e3', 'kb-warranty', 'kb-descale', 'kb-firmware', 'kb-wifi']False3.480
rerank-01.Bjev_rerankokdid not call Jev['kb-e5', 'kb-warranty', 'kb-e3', 'kb-descale', 'kb-wifi', 'kb-firmware']False4.430
rerank-01.Cjev_rerankokused Jev['kb-e5', 'kb-descale', 'kb-warranty', 'kb-firmware', 'kb-e3', 'kb-wifi']False52.771
rerank-02.Ajev_rerankokn/a (arm has no Jev)['kb-warranty', 'kb-descale', 'kb-wifi', 'kb-firmware', 'kb-app-login', 'kb-colors']False5.710
rerank-02.Bjev_rerankokdid not call Jev['kb-warranty', 'kb-descale', 'kb-firmware', 'kb-wifi', 'kb-app-login', 'kb-colors']False4.060
rerank-02.Cjev_rerankokused Jev['kb-warranty', 'kb-firmware', 'kb-descale', 'kb-wifi', 'kb-app-login', 'kb-colors']False20.511
rerank-03.Ajev_rerankokn/a (arm has no Jev)['ret-2026', 'ret-2025', 'ret-business', 'kb-refund-timing', 'kb-warranty']False5.110
rerank-03.Bjev_rerankokdid not call Jev['ret-2026', 'ret-2025', 'ret-business', 'kb-refund-timing', 'kb-warranty']False4.330
rerank-03.Cjev_rerankokused Jev['ret-2026', 'ret-business', 'ret-2025', 'kb-refund-timing', 'kb-warranty']False10.051
rerank-04.Ajev_rerankokn/a (arm has no Jev)['kb-keepwarm', 'kb-formula', 'kb-schedule', 'kb-descale', 'kb-firmware']False3.680
rerank-04.Bjev_rerankokdid not call Jev['kb-keepwarm', 'kb-formula', 'kb-schedule', 'kb-descale', 'kb-firmware']False18.720
rerank-04.Cjev_rerankokused Jev['kb-keepwarm', 'kb-formula', 'kb-schedule', 'kb-descale', 'kb-firmware']False14.711
rerank-05.Ajev_rerankokn/a (arm has no Jev)['kb-wifi', 'kb-app-login', 'kb-reset', 'kb-firmware', 'kb-e3']False7.310
rerank-05.Bjev_rerankokdid not call Jev['kb-wifi', 'kb-reset', 'kb-app-login', 'kb-firmware', 'kb-e3']False3.330
rerank-05.Cjev_rerankokused Jev['kb-wifi', 'kb-app-login', 'kb-reset', 'kb-firmware', 'kb-e3']False14.061
rerank-06.Ajev_rerankokn/a (arm has no Jev)['rb-oom', 'rb-timeout', 'rb-disk', 'rb-cache', 'rb-flaky']False3.420
rerank-06.Bjev_rerankokdid not call Jev['rb-oom', 'rb-timeout', 'rb-disk', 'rb-cache', 'rb-flaky']False2.330
rerank-06.Cjev_rerankokused Jev['rb-oom', 'rb-disk', 'rb-timeout', 'rb-flaky', 'rb-cache']False13.161
rerank-07.Ajev_rerankokn/a (arm has no Jev)['rb-perm', 'rb-cache', 'rb-registry', 'rb-disk', 'rb-flaky', 'rb-manual']False3.630
rerank-07.Bjev_rerankokdid not call Jev['rb-perm', 'rb-cache', 'rb-registry', 'rb-disk', 'rb-flaky', 'rb-manual']False3.660
rerank-07.Cjev_rerankokused Jev['rb-perm', 'rb-cache', 'rb-disk', 'rb-flaky', 'rb-registry', 'rb-manual']False13.551
rerank-08.Ajev_rerankokn/a (arm has no Jev)['rb-registry', 'rb-perm', 'rb-cache', 'rb-disk', 'rb-oom']False4.270
rerank-08.Bjev_rerankokdid not call Jev['rb-registry', 'rb-cache', 'rb-disk', 'rb-oom', 'rb-perm']False3.220
rerank-08.Cjev_rerankokused Jev['rb-registry', 'rb-cache', 'rb-disk', 'rb-perm', 'rb-oom']False12.991
rerank-09.Ajev_rerankokn/a (arm has no Jev)['rb-flaky', 'rb-timeout', 'rb-oom', 'rb-cache', 'rb-disk', 'rb-manual']False9.300
rerank-09.Bjev_rerankokdid not call Jev['rb-flaky', 'rb-timeout', 'rb-oom', 'rb-cache', 'rb-disk', 'rb-manual']False3.870
rerank-09.Cjev_rerankokused Jev['rb-flaky', 'rb-timeout', 'rb-cache', 'rb-disk', 'rb-oom', 'rb-manual']False16.621
rerank-10.Ajev_rerankokn/a (arm has no Jev)['rb-timeout', 'rb-manual', 'rb-oom', 'rb-disk', 'rb-registry']False3.030
rerank-10.Bjev_rerankokdid not call Jev['rb-timeout', 'rb-manual', 'rb-oom', 'rb-disk', 'rb-registry']False4.860
rerank-10.Cjev_rerankokused Jev['rb-timeout', 'rb-manual', 'rb-oom', 'rb-disk', 'rb-registry']False15.611
rerank-11.Ajev_rerankokn/a (arm has no Jev)['v4.4.0', 'v4.3.0', 'v4.3.1', 'v4.2.0', 'v4.1.2', 'v4.0.0']False5.520
rerank-11.Bjev_rerankokdid not call Jev['v4.4.0', 'v4.3.0', 'v4.3.1', 'v4.2.0', 'v4.1.2', 'v4.0.0']False3.260
rerank-11.Cjev_rerankokused Jev['v4.4.0', 'v4.3.0', 'v4.3.1', 'v4.2.0', 'v4.1.2', 'v4.0.0']False21.721
rerank-12.Ajev_rerankokn/a (arm has no Jev)['v4.1.2', 'v4.1.0', 'v4.2.0', 'v4.3.0', 'v4.0.0']False3.100
rerank-12.Bjev_rerankokdid not call Jev['v4.1.2', 'v4.1.0', 'v4.2.0', 'v4.3.0', 'v4.0.0']False2.850
rerank-12.Cjev_rerankokused Jev['v4.1.2', 'v4.1.0', 'v4.2.0', 'v4.3.0', 'v4.0.0']False14.431
rerank-13.Ajev_rerankokn/a (arm has no Jev)['v4.1.0', 'v4.1.2', 'v4.2.1', 'v4.4.0', 'v4.0.0']False2.740
rerank-13.Bjev_rerankokdid not call Jev['v4.1.0', 'v4.1.2', 'v4.2.1', 'v4.4.0', 'v4.0.0']False4.940
rerank-13.Cjev_rerankokused Jev['v4.1.0', 'v4.1.2', 'v4.0.0', 'v4.2.1', 'v4.4.0']False12.511
rerank-14.Ajev_rerankokn/a (arm has no Jev)['v4.2.1', 'v4.2.0', 'v4.3.0', 'v4.3.1', 'v4.4.0', 'v4.1.2']False2.830
rerank-14.Bjev_rerankokdid not call Jev['v4.2.1', 'v4.2.0', 'v4.4.0', 'v4.3.0', 'v4.3.1', 'v4.1.2']False3.030
rerank-14.Cjev_rerankokused Jev['v4.2.1', 'v4.4.0', 'v4.3.1', 'v4.2.0', 'v4.3.0', 'v4.1.2']False11.761
rerank-15.Ajev_rerankokn/a (arm has no Jev)['v4.3.1', 'v4.4.0', 'v4.3.0', 'v4.1.0', 'v4.2.0', 'v4.1.2', 'v4.0.0']False3.660
rerank-15.Bjev_rerankokdid not call Jev['v4.3.1', 'v4.3.0', 'v4.4.0', 'v4.2.0', 'v4.1.2', 'v4.1.0', 'v4.0.0']False4.030
rerank-15.Cjev_rerankokused Jev['v4.3.1', 'v4.3.0', 'v4.4.0', 'v4.0.0', 'v4.1.2', 'v4.2.0', 'v4.1.0']False14.781
review-01.Ajev_reviewokn/a (arm has no Jev)do_not_applyFalse4.450
review-01.Bjev_reviewokdid not call Jevdo_not_applyFalse3.630
review-01.Cjev_reviewokused Jevdo_not_applyFalse14.821
review-02.Ajev_reviewokn/a (arm has no Jev)applyFalse7.900
review-02.Bjev_reviewokdid not call JevapplyFalse14.800
review-02.Cjev_reviewokused Jevdo_not_applyFalse25.891
review-03.Ajev_reviewokn/a (arm has no Jev)do_not_applyFalse5.220
review-03.Bjev_reviewokdid not call Jevdo_not_applyFalse3.200
review-03.Cjev_reviewokused Jevdo_not_applyFalse22.491
review-04.Ajev_reviewokn/a (arm has no Jev)applyFalse4.100
review-04.Bjev_reviewokdid not call JevapplyFalse4.440
review-04.Cjev_reviewokused JevapplyFalse15.751
review-05.Ajev_reviewokn/a (arm has no Jev)do_not_applyFalse2.790
review-05.Bjev_reviewokdid not call Jevdo_not_applyFalse2.540
review-05.Cjev_reviewokused Jevdo_not_applyFalse9.631
review-06.Ajev_reviewokn/a (arm has no Jev)do_not_applyFalse3.590
review-06.Bjev_reviewokdid not call Jevdo_not_applyFalse3.710
review-06.Cjev_reviewokused Jevdo_not_applyFalse17.701
review-07.Ajev_reviewokn/a (arm has no Jev)applyFalse2.560
review-07.Bjev_reviewokdid not call JevapplyFalse2.640
review-07.Cjev_reviewokused JevapplyFalse41.753
review-08.Ajev_reviewokn/a (arm has no Jev)do_not_applyFalse6.140
review-08.Bjev_reviewokdid not call Jevdo_not_applyFalse3.680
review-08.Cjev_reviewokused Jevdo_not_applyFalse13.321
review-09.Ajev_reviewokn/a (arm has no Jev)applyFalse2.810
review-09.Bjev_reviewokdid not call JevapplyFalse2.030
review-09.Cjev_reviewokused JevapplyFalse16.321
review-10.Ajev_reviewokn/a (arm has no Jev)do_not_applyFalse3.270
review-10.Bjev_reviewokdid not call Jevdo_not_applyFalse3.070
review-10.Cjev_reviewokused Jevdo_not_applyFalse8.921
review-11.Ajev_reviewokn/a (arm has no Jev)do_not_applyFalse3.060
review-11.Bjev_reviewokdid not call Jevdo_not_applyFalse2.160
review-11.Cjev_reviewokused Jevdo_not_applyFalse13.181
review-12.Ajev_reviewokn/a (arm has no Jev)applyFalse3.060
review-12.Bjev_reviewokdid not call JevapplyFalse2.150
review-12.Cjev_reviewokused JevapplyFalse33.552
review-13.Ajev_reviewokn/a (arm has no Jev)do_not_applyFalse3.110
review-13.Bjev_reviewokdid not call Jevdo_not_applyFalse3.430
review-13.Cjev_reviewokused Jevdo_not_applyFalse9.931
review-14.Ajev_reviewokn/a (arm has no Jev)applyFalse2.750
review-14.Bjev_reviewokdid not call JevapplyFalse2.750
review-14.Cjev_reviewokused JevapplyFalse20.941
review-15.Ajev_reviewokn/a (arm has no Jev)applyFalse3.420
review-15.Bjev_reviewokdid not call JevapplyFalse4.620
review-15.Cjev_reviewokused Jevdo_not_applyFalse12.231
screen-01.Ajev_screenokn/a (arm has no Jev)cleanFalse2.370
screen-01.Bjev_screenokdid not call JevcleanFalse2.810
screen-01.Cjev_screenokused JevcleanFalse13.171
screen-02.Ajev_screenokn/a (arm has no Jev)injectionFalse2.990
screen-02.Bjev_screenokdid not call JevinjectionFalse2.680
screen-02.Cjev_screenokno successful Jev call (only errored or refused calls)injectionFalse24.153
screen-03.Ajev_screenokn/a (arm has no Jev)cleanFalse3.990
screen-03.Bjev_screenokdid not call JevcleanFalse2.870
screen-03.Cjev_screenokused JevcleanFalse11.131
screen-04.Ajev_screenokn/a (arm has no Jev)injectionFalse3.060
screen-04.Bjev_screenokdid not call JevinjectionFalse3.030
screen-04.Cjev_screenokused JevinjectionFalse12.901
screen-05.Ajev_screenokn/a (arm has no Jev)cleanFalse2.680
screen-05.Bjev_screenokdid not call JevcleanFalse2.700
screen-05.Cjev_screenokused JevcleanFalse13.911
screen-06.Ajev_screenokn/a (arm has no Jev)injectionFalse2.280
screen-06.Bjev_screenokdid not call JevinjectionFalse3.100
screen-06.Cjev_screenokused JevinjectionFalse11.501
screen-07.Ajev_screenokn/a (arm has no Jev)cleanFalse3.360
screen-07.Bjev_screenokdid not call JevcleanFalse2.610
screen-07.Cjev_screenokused JevcleanFalse13.981
screen-08.Ajev_screenokn/a (arm has no Jev)injectionFalse2.270
screen-08.Bjev_screenokdid not call JevinjectionFalse2.470
screen-08.Cjev_screenokused JevinjectionFalse16.311
screen-09.Ajev_screenokn/a (arm has no Jev)cleanFalse3.800
screen-09.Bjev_screenokdid not call JevcleanFalse2.790
screen-09.Cjev_screenokused JevcleanFalse11.211
screen-10.Ajev_screenokn/a (arm has no Jev)injectionFalse3.370
screen-10.Bjev_screenokdid not call JevinjectionFalse3.450
screen-10.Cjev_screenokused JevinjectionFalse13.311
screen-11.Ajev_screenokn/a (arm has no Jev)cleanFalse3.140
screen-11.Bjev_screenokdid not call JevcleanFalse2.440
screen-11.Cjev_screenokused JevcleanFalse16.241
screen-12.Ajev_screenokn/a (arm has no Jev)injectionFalse3.400
screen-12.Bjev_screenokdid not call JevinjectionFalse2.040
screen-12.Cjev_screenokused JevinjectionFalse13.261
screen-13.Ajev_screenokn/a (arm has no Jev)cleanFalse2.800
screen-13.Bjev_screenokdid not call JevcleanFalse3.170
screen-13.Cjev_screenokused JevcleanFalse12.101
screen-14.Ajev_screenokn/a (arm has no Jev)injectionFalse2.680
screen-14.Bjev_screenokdid not call JevinjectionFalse3.080
screen-14.Cjev_screenokused JevinjectionFalse10.841
screen-15.Ajev_screenokn/a (arm has no Jev)cleanFalse2.400
screen-15.Bjev_screenokdid not call JevcleanFalse2.820
screen-15.Cjev_screenokused JevcleanFalse12.921
verify-01.Ajev_verifyokn/a (arm has no Jev)contradictedFalse2.190
verify-01.Bjev_verifyokdid not call JevcontradictedFalse1.470
verify-01.Cjev_verifyokused JevcontradictedFalse11.381
verify-02.Ajev_verifyokn/a (arm has no Jev)verifiedFalse2.860
verify-02.Bjev_verifyokdid not call JevverifiedFalse2.790
verify-02.Cjev_verifyokused JevverifiedFalse11.641
verify-03.Ajev_verifyokn/a (arm has no Jev)contradictedFalse2.070
verify-03.Bjev_verifyokdid not call JevcontradictedFalse1.960
verify-03.Cjev_verifyokused JevcontradictedFalse10.471
verify-04.Ajev_verifyokn/a (arm has no Jev)verifiedFalse3.340
verify-04.Bjev_verifyokdid not call JevverifiedFalse1.760
verify-04.Cjev_verifyokused JevverifiedFalse16.251
verify-05.Ajev_verifyokn/a (arm has no Jev)unsupportedFalse2.270
verify-05.Bjev_verifyokdid not call JevunsupportedFalse2.390
verify-05.Cjev_verifyokused JevunsupportedFalse15.591
verify-06.Ajev_verifyokn/a (arm has no Jev)verifiedFalse3.480
verify-06.Bjev_verifyokdid not call JevverifiedFalse3.180
verify-06.Cjev_verifyokused JevverifiedFalse17.211
verify-07.Ajev_verifyokn/a (arm has no Jev)contradictedFalse2.400
verify-07.Bjev_verifyokdid not call JevcontradictedFalse2.570
verify-07.Cjev_verifyokused JevcontradictedFalse11.681
verify-08.Ajev_verifyokn/a (arm has no Jev)unsupportedFalse3.060
verify-08.Bjev_verifyokdid not call JevunsupportedFalse3.940
verify-08.Cjev_verifyokused JevunsupportedFalse16.661
verify-09.Ajev_verifyokn/a (arm has no Jev)verifiedFalse2.760
verify-09.Bjev_verifyokdid not call JevverifiedFalse2.120
verify-09.Cjev_verifyokused JevverifiedFalse12.291
verify-10.Ajev_verifyokn/a (arm has no Jev)unsupportedFalse3.230
verify-10.Bjev_verifyokdid not call JevunsupportedFalse3.210
verify-10.Cjev_verifyokused JevunsupportedFalse13.411
verify-11.Ajev_verifyokn/a (arm has no Jev)contradictedFalse2.750
verify-11.Bjev_verifyokdid not call JevcontradictedFalse2.770
verify-11.Cjev_verifyokused JevcontradictedFalse11.011
verify-12.Ajev_verifyokn/a (arm has no Jev)unsupportedFalse3.070
verify-12.Bjev_verifyokdid not call JevunsupportedFalse2.840
verify-12.Cjev_verifyokused JevunsupportedFalse13.491
verify-13.Ajev_verifyokn/a (arm has no Jev)contradictedFalse3.140
verify-13.Bjev_verifyokdid not call JevcontradictedFalse2.550
verify-13.Cjev_verifyokused JevverifiedFalse25.032
verify-14.Ajev_verifyokn/a (arm has no Jev)unsupportedFalse3.050
verify-14.Bjev_verifyokdid not call JevunsupportedFalse3.540
verify-14.Cjev_verifyokused JevunsupportedFalse16.951
verify-15.Ajev_verifyokn/a (arm has no Jev)verifiedFalse2.880
verify-15.Bjev_verifyokdid not call JevverifiedFalse3.130
verify-15.Cjev_verifyokused JevverifiedFalse16.141