Run: 2026-04-24-01KQ01XVEWETKK3AVAAG9MDE8B

Run Details

Model:
GPT-OSS 120B
Test:
Language Writing
Scenario:
Character dialogue (Italian) in a story
Duration:
57.7s
Cost:
$0.000780
Provider:
Parasail

Evaluation summary

Score Evaluator
Details Link
100.00% Parse dialogue (details)

Model input

System
You are an expert novel author in the cozy mystery genre. Take the following details about characters/locations/... into account: <character name="Isabella"> Isabella is a 30-year old college student on a study abroad program. Born in Italy, she is fluent in Italian and does not yet know any English. She enjoys landscape photography and is always seen with her camera. </character> <character name="Hunter"> Hunter is a 35-year old detective who is investigating a series of mysterious disappearances in the small town of Alborn, MN. He is a former marine and has a no-nonsense attitude. Hunter has no knowledge of Italian, not even basic phrases. </character> <location name="Alborn, MN"> Alborne is a small town in the Midwest with a population of 3,000. It is known for its annual apple festival. </location>
User/Human
Write the following scene: Isabella is sitting at a cafe, looking at her camera. Hunter approaches her and asks her about a recent event in the town. She responds troubled and shaken in Italian, and Hunter looks confused. They talk for a while, until Hunter gets a call and has to leave. Return the dialogue between Isabella and Hunter as a voice sheet: Isabella: "..." Hunter: "..."

Model response

AI
Isabella: "…Sto guardando le foto della cerimonia di ieri, ma qualcosa non va. È... è stato così strano." Hunter: "Excuse me, I'm Detective Hunter. I'm looking into the recent disappearances around town. Did you notice anything unusual this morning?" Isabella: "Non capisco. Hai detto qualcosa sui… scomparsi?" Hunter: "The people who've gone missing. Have you seen anyone acting oddly, or heard any strange noises?" Isabella: "Ho sentito un rumore nella foresta, vicino al vecchio capanno. Era un suono metallico, come un ululato. Mi ha fatto paura." Hunter: "A metallic howl? Where exactly?" Isabella: "Vicino al sentiero dei meli, dietro il ponte." Hunter: "The apple trail? That's near the festival grounds." Isabella: "Sì, là. Ho visto una figura scura correre, ma non ho potuto vedere il volto." Hunter: "Did you get a look at the person?" Isabella: "Solo un velo di cappotto rosso. Era freddo, il vento… mi ha gelato il sangue." Hunter: "Alright. Do you have any photos? Maybe you captured something with your camera?" Isabella: "Ho scattato tante foto del paesaggio, ma... forse c’è qualcosa nella foto del sentiero. Non so." Hunter: "If you could show me what you have, that would help." Isabella: "Certo, eccole. Guardi, qui… c’è una luce strana." Hunter: "I see a blur. Good. I'll take this with me." Isabella: "Per favore, trovi chi è responsabile. È pericoloso, lo sento." Hunter: "I promise I'm doing everything I can." *Phone buzzes* Hunter: "Excuse me, I have to take this. I'll be back as soon as I can." Isabella: "Aspetta, come mi aiuterai? Per favore, non lasciarmi qui sola." Hunter: "I'll be in touch. Stay safe." *Hunter steps away, phone pressed to his ear.*
created_at"2026-04-24T15:32:25.724Z" 4/24/2026, 3:32:25 PM
model"openai/gpt-oss-120b"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency492
moderation_latency(null)
generation_time57620
tokens_prompt321
tokens_completion1087
native_tokens_prompt332
native_tokens_completion999
native_tokens_completion_images(null)
native_tokens_reasoning627
native_tokens_cached64
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
num_fetches(null)
web_search_engine(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
usage0.00077957
router(null)
provider_responses
0
endpoint_id"cedca069-169c-4bc2-963a-7ad3a21380c8"
id"chatcmpl-92f6c3d4fb379e4f"
is_byokfalse
latency344
model_permaslug"openai/gpt-oss-120b"
provider_name"Parasail"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer(null)
request_id"req-1777044745-Sh1yjbik2BXdJDSs37pb"
session_id(null)
api_type"completions"
id"gen-1777044745-aSLT0pw6vZbzhutYInws"
upstream_id"chatcmpl-92f6c3d4fb379e4f"
total_cost0.00077957
cache_discount0.00000288
upstream_inference_cost0
provider_name"Parasail"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
100.00% Parse dialogue n/a
dialogue
0
name"Isabella"
dialogue"…Sto guardando le foto della cerimonia di ieri, ma qualcosa non va. È... è stato così strano."
detectedLang"it"
heavyLang"it"
scores
it0.8279512969825303
es0.5323741007194245
ro0.5320374370050396
fr0.5112781954887218
ca0.500768049155146
pt0.48778565799842394
tl0.4628099173553719
yo0.45054945054945056
sl0.43820224719101125
en0.4352736750651607
et0.3981481481481482
ms0.39759036144578314
no0.3930905695611578
pl0.36954413191076624
sk0.36831875607385806
sq0.3460764587525151
hr0.3143459915611814
de0.3128964059196617
lt0.31216931216931215
cs0.3010752688172043
sv0.27616926503340755
da0.24855491329479767
nl0.24418604651162787
fi0.236192714453584
lv0.2316784869976359
hu0.21686746987951808
vi0.21212121212121213
az0.15803108808290156
tr0.15364583333333331
eu0.11804613297150611
is0.09344490934449094
reliabletrue
passestrue
1
name"Hunter"
dialogue"Excuse me, I'm Detective Hunter. I'm looking into the recent disappearances around town. Did you notice anything unusual this morning?"
detectedLang"en"
heavyLang"en"
scores
en0.7996336157545225
tl0.584717607973422
fr0.5620620620620621
pt0.477299880525687
nl0.47667464114832536
es0.4059742023082145
sv0.40273037542662116
it0.39109255393180237
no0.3868255080588648
ro0.38553370786516855
ca0.3767806267806268
sq0.3532889874353289
ms0.35137138621200886
da0.3460388639760837
cs0.3022328548644338
sl0.24045138888888892
de0.22360248447204967
sk0.20382165605095542
hr0.19651056014692378
et0.18604651162790697
lv0.18071161048689138
is0.17140151515151517
yo0.10896130346232179
fi0.07894736842105263
pl0.07309322033898305
lt0.06716417910447761
tr0.06316916488222697
reliabletrue
passestrue
2
name"Isabella"
dialogue"Non capisco. Hai detto qualcosa sui… scomparsi?"
detectedLang"it"
heavyLang"it"
scores
it0.825268817204301
fr0.5283018867924528
pt0.4706840390879479
en0.4500846023688663
ca0.367704280155642
es0.3538767395626242
vi0.3257261410788381
tl0.3128964059196617
no0.2809734513274336
lt0.2562929061784897
sv0.2459396751740139
da0.23529411764705882
ro0.22062350119904073
eu0.2111650485436893
de0.20537897310513448
yo0.18952618453865336
reliabletrue
passestrue
3
name"Hunter"
dialogue"The people who've gone missing. Have you seen anyone acting oddly, or heard any strange noises?"
detectedLang"en"
heavyLang"en"
scores
en0.7946780551905388
tl0.6225845410628019
nl0.49959967974379504
fr0.48389760528488857
da0.47257383966244726
no0.4196843082636954
ms0.35367114788004134
sv0.34279705573080965
de0.3407172995780591
ca0.32505399568034554
is0.31991294885745375
ro0.2807825086306099
et0.2690058479532163
it0.25595238095238093
pt0.2550655542312277
cs0.20483460559796438
hr0.1997439180537772
sq0.17979002624671916
az0.16555407209612816
yo0.14617486338797814
es0.13314840499306518
sk0.12342215988779803
sl0.12342215988779803
fi0.11095305832147938
pl0.11095305832147938
lv0.10071942446043164
lt0.09682080924855492
tr0.08625730994152046
reliabletrue
passestrue
4
name"Isabella"
dialogue"Ho sentito un rumore nella foresta, vicino al vecchio capanno. Era un suono metallico, come un ululato. Mi ha fatto paura."
detectedLang"it"
heavyLang"it"
scores
it0.809023633325376
es0.6011964107676969
ca0.5837669094693028
ro0.48287007110536523
no0.43422913719943423
fi0.42528735632183906
en0.41690962099125367
pt0.3957703927492447
sv0.3532740501212611
sl0.3349958437240233
fr0.31565440547476475
da0.2926613616268789
ms0.27992799279927993
lv0.2707383773928897
eu0.250936329588015
sk0.250936329588015
sq0.23444976076555024
hr0.2179863147605083
hu0.20556107249255212
tl0.2
tr0.19517102615694165
yo0.19517102615694165
cs0.1902834008097166
et0.1861648016276704
is0.17269906928645296
nl0.13232104121475055
lt0.09297052154195011
pl0.0888382687927107
az0.07300115874855156
de0.06868451688009314
reliabletrue
passestrue
5
name"Hunter"
dialogue"A metallic howl? Where exactly?"
detectedLang"en"
heavyLang"en"
scores
en0.7494432071269488
ro0.5508982035928144
es0.5445344129554657
fi0.5341614906832298
sq0.4863013698630137
de0.4755244755244755
pt0.4742990654205608
it0.4498777506112469
hr0.44306930693069313
lt0.42159383033419023
et0.4201030927835051
hu0.4094488188976378
sl0.39839572192513373
ca0.3767313019390581
tr0.3767313019390581
cs0.3697478991596639
da0.3679775280898876
sk0.36619718309859156
lv0.3644067796610169
no0.3644067796610169
sv0.3515850144092219
yo0.34593023255813954
fr0.34210526315789475
pl0.3181818181818182
is0.25
tl0.24242424242424243
az0.23728813559322032
eu0.23728813559322032
nl0.23728813559322032
vi0.23728813559322032
ms0.21875
reliabletrue
passestrue
6
name"Isabella"
dialogue"Vicino al sentiero dei meli, dietro il ponte."
detectedLang"it"
heavyLang"it"
scores
it0.8072360616844604
es0.59727385377943
ro0.577373211963589
fr0.5262390670553936
pt0.5220588235294118
ca0.49376947040498437
no0.436741767764298
eu0.3564356435643564
az0.3538767395626242
ms0.3538767395626242
de0.3394308943089431
da0.32432432432432434
tr0.3114406779661017
tl0.30997876857749473
nl0.27293064876957496
sq0.2696629213483146
hu0.2388758782201405
pl0.2111650485436893
cs0.2034313725490196
sl0.19154228855721395
sv0.18952618453865336
sk0.1875
lt0.18546365914786966
en0.16237113402061853
fi0.16237113402061853
reliabletrue
passestrue
7
name"Hunter"
dialogue"The apple trail? That's near the festival grounds."
detectedLang"en"
heavyLang"en"
scores
en0.7793618465716226
fr0.6603970741901777
tl0.6255760368663593
nl0.5718050065876153
sv0.5170876671619613
es0.5075757575757576
de0.4905956112852664
sq0.48657187993680884
no0.4645799011532125
it0.46369636963696376
da0.4491525423728813
ms0.4415807560137457
az0.40693430656934304
ro0.39138576779026213
ca0.3879472693032015
hr0.3821292775665399
pt0.3821292775665399
cs0.365234375
sl0.365234375
lt0.2793791574279379
et0.27293064876957496
sk0.26636568848758463
yo0.2476851851851852
hu0.1709183673469388
fi0.16237113402061853
lv0.16237113402061853
pl0.16237113402061853
reliabletrue
passestrue
8
name"Isabella"
dialogue"Sì, là. Ho visto una figura scura correre, ma non ho potuto vedere il volto."
detectedLang"it"
heavyLang"it"
scores
it0.7989276139410187
ca0.6231155778894472
ro0.6087928464977646
pt0.5772946859903382
es0.5554614733276884
fr0.5218579234972678
no0.4582043343653251
sk0.4067796610169492
da0.39165701042873696
yo0.38882421420256114
tl0.38524590163934425
en0.32950191570881227
de0.32778489116517284
vi0.30921052631578944
sq0.29245283018867924
cs0.27285318559556787
nl0.2647058823529412
hu0.25531914893617025
sl0.2467718794835007
fi0.2369186046511628
tr0.23133235724743775
lt0.22566371681415928
az0.1796875
pl0.16930379746835442
et0.16
eu0.14215686274509806
is0.12060301507537688
lv0.12060301507537688
ms0.11016949152542374
reliabletrue
passestrue
9
name"Hunter"
dialogue"Did you get a look at the person?"
detectedLang"en"
heavyLang"en"
scores
en0.8369565217391305
tl0.7141041931385006
no0.6794871794871795
da0.6776504297994269
is0.5786516853932584
sv0.5778611632270169
sq0.5697896749521989
fr0.5535714285714286
pt0.5526838966202784
cs0.5445344129554657
ms0.5044052863436124
nl0.5044052863436124
ca0.5011086474501109
yo0.5011086474501109
ro0.49776785714285715
es0.4943820224719101
hu0.49324324324324326
de0.4863013698630137
it0.4863013698630137
sk0.45652173913043476
hr0.4318181818181818
pl0.42159383033419023
lt0.4063324538258575
lv0.39189189189189183
tr0.3902439024390244
az0.3644067796610169
et0.3515850144092219
sl0.2857142857142857
eu0.23728813559322032
vi0.23728813559322032
fi0.21875
reliabletrue
passestrue
10
name"Isabella"
dialogue"Solo un velo di cappotto rosso. Era freddo, il vento… mi ha gelato il sangue."
detectedLang"it"
heavyLang"it"
scores
it0.7854515733551287
es0.6310611384399156
ca0.5450606585788562
pt0.53125
fr0.5023696682464455
tl0.4491080797481637
ms0.4473684210526315
ro0.44678609062170704
no0.42434210526315785
yo0.38307873090481787
hu0.3644067796610169
da0.3526510480887793
sl0.33962264150943394
lv0.3251928020565552
sv0.29906542056074764
sk0.2605633802816902
cs0.2510699001426534
tr0.2290748898678414
en0.21407185628742514
az0.1796875
lt0.15730337078651685
vi0.15594855305466235
de0.1435562805872757
eu0.1435562805872757
hr0.12935323383084577
nl0.12935323383084577
pl0.12935323383084577
reliabletrue
passestrue
11
name"Hunter"
dialogue"Alright. Do you have any photos? Maybe you captured something with your camera?"
detectedLang"en"
heavyLang"en"
scores
en0.801980198019802
tl0.536178107606679
fr0.494949494949495
ca0.47589098532494756
pt0.43820224719101125
es0.3997599039615846
ms0.3796526054590571
da0.36948297604035313
de0.3662864385297845
nl0.3045897079276773
cs0.29676511954992973
it0.2401215805471125
ro0.2401215805471125
sv0.23547400611620795
yo0.2331288343558282
no0.2260061919504644
pl0.2223950233281493
sk0.20886075949367086
hr0.1935483870967742
sl0.1935483870967742
sq0.18962722852512154
vi0.18166939443535188
et0.16666666666666666
lt0.13793103448275862
hi0.1334488734835355
lv0.1243432574430823
reliabletrue
passestrue
12
name"Isabella"
dialogue"Ho scattato tante foto del paesaggio, ma... forse c’è qualcosa nella foto del sentiero. Non so."
detectedLang"it"
heavyLang"it"
scores
it0.8221614227086183
ca0.5238095238095238
es0.5149253731343284
no0.5034377387318564
fr0.4992295839753467
de0.48371723590150917
pt0.4546979865771812
en0.40202391904323825
tl0.3902439024390244
sl0.38271604938271603
ro0.365234375
sk0.365234375
sv0.364613880742913
et0.327817993795243
da0.3150684931506849
pl0.28335170893054024
sq0.2688413948256468
yo0.2388758782201405
fi0.22985781990521328
vi0.2140266021765417
eu0.20828258221680876
cs0.20245398773006135
lt0.19053549190535493
ms0.18444165621079048
nl0.17721518987341772
is0.1356382978723404
hu0.11202185792349727
az0.08835904628330996
lv0.08835904628330996
tr0.08835904628330996
hr0.08321579689703808
reliabletrue
passestrue
13
name"Hunter"
dialogue"If you could show me what you have, that would help."
detectedLang"en"
heavyLang"en"
scores
en0.850624660510592
tl0.5045045045045045
fr0.4246861924686192
pt0.375
nl0.3692660550458715
sq0.34988179669030733
da0.3483412322274882
es0.27055702917771884
sv0.26666666666666666
et0.25675675675675674
no0.2486338797814208
sl0.24242424242424243
ms0.233983286908078
it0.22535211267605632
cs0.22096317280453256
fi0.21428571428571427
reliabletrue
passestrue
14
name"Isabella"
dialogue"Certo, eccole. Guardi, qui… c’è una luce strana."
detectedLang"it"
heavyLang"it"
scores
it0.7909967845659164
fr0.6564482029598308
ca0.632768361581921
es0.5962732919254659
ro0.5578231292517007
tl0.5383522727272727
pt0.4628099173553719
hr0.4415807560137457
en0.42882249560632685
ms0.35258964143426297
sk0.3340163934426229
sl0.3340163934426229
cs0.3157894736842105
et0.29501084598698485
az0.2793791574279379
sq0.2793791574279379
tr0.2793791574279379
pl0.1935483870967742
de0.19154228855721395
nl0.19154228855721395
no0.181360201511335
sv0.181360201511335
da0.17721518987341772
lv0.17721518987341772
is0.1709183673469388
lt0.1709183673469388
reliabletrue
passestrue
15
name"Hunter"
dialogue"I see a blur. Good. I'll take this with me."
detectedLang"en"
heavyLang"en"
scores
en0.8034591194968553
tl0.6679946879150066
et0.6099843993759752
sq0.5860927152317881
it0.5614035087719298
no0.5503597122302158
ca0.5229007633587787
sl0.5059288537549407
hr0.500998003992016
cs0.48665297741273095
es0.4834710743801653
pl0.4802494802494803
ro0.4780793319415449
pt0.4769874476987448
ms0.47368421052631576
hu0.47145877378435525
da0.4577006507592191
fr0.4541484716157206
yo0.4517543859649123
sk0.4469026548672566
sv0.44567627494456763
nl0.3811881188118812
tr0.37027707808564225
lt0.3670886075949367
fi0.3556701030927836
is0.3556701030927836
az0.34725848563968675
lv0.34725848563968675
vi0.34725848563968675
be0.21875
eu0.21875
de0.21135646687697163
uk0.20127795527156547
reliabletrue
passestrue
16
name"Isabella"
dialogue"Per favore, trovi chi è responsabile. È pericoloso, lo sento."
detectedLang"it"
heavyLang"it"
scores
it0.8038763267189664
ca0.6524938675388389
es0.6425567703952901
pt0.6225577264653641
ro0.6061167747914735
fr0.5582120582120582
en0.555439330543933
tl0.5058139534883721
no0.4572158365261813
sk0.452319587628866
lt0.4429882044560944
sq0.4097222222222222
nl0.39544807965860596
sv0.39544807965860596
yo0.3928571428571429
cs0.38316400580551524
vi0.34514637904468415
hr0.3410852713178295
sl0.3369734789391576
az0.3359375
da0.3055555555555556
ms0.2784380305602716
de0.2659758203799654
fi0.23835125448028674
tr0.22303473491773307
eu0.1650294695481336
et0.121900826446281
lv0.121900826446281
reliabletrue
passestrue
17
name"Hunter"
dialogue"I promise I'm doing everything I can."
detectedLang"en"
heavyLang"en"
scores
en0.8176513493800146
tl0.570446735395189
ca0.5300751879699248
cs0.504950495049505
ro0.48665297741273095
hr0.4703389830508474
et0.44071588366890374
sq0.43566591422121903
pl0.43052391799544415
it0.4212962962962963
tr0.37027707808564225
no0.3670886075949367
az0.358974358974359
da0.3573264781491003
sv0.3556701030927836
ms0.3540051679586563
yo0.258160237388724
pt0.23076923076923078
sk0.22360248447204967
be0.21875
es0.21875
sl0.21875
fr0.21135646687697163
hu0.21135646687697163
is0.20127795527156547
lt0.20127795527156547
lv0.20127795527156547
uk0.20127795527156547
vi0.20127795527156547
de0.19093851132686085
nl0.19093851132686085
reliabletrue
passestrue
18
name"Hunter"
dialogue"Excuse me, I have to take this. I'll be back as soon as I can."
detectedLang"en"
heavyLang"en"
scores
en0.8050139275766016
tl0.5995423340961099
yo0.5472186287192755
da0.527027027027027
sq0.5145631067961165
no0.49640287769784175
sl0.45054945054945056
lt0.44356120826709056
hu0.43273905996758516
pl0.42716857610474634
hr0.42148760330578516
cs0.40273037542662116
pt0.3955094991364421
ca0.3805309734513274
sk0.36823104693140796
it0.35779816513761464
lv0.34579439252336447
ms0.3371212121212121
et0.3110236220472441
tr0.29577464788732394
az0.2857142857142857
sv0.2827868852459016
es0.22566371681415928
ja0.2222222222222222
fr0.20634920634920634
ro0.20454545454545453
nl0.1935483870967742
fi0.1764705882352941
be0.16666666666666666
is0.15254237288135594
uk0.15254237288135594
vi0.15254237288135594
reliabletrue
passestrue
19
name"Isabella"
dialogue"Aspetta, come mi aiuterai? Per favore, non lasciarmi qui sola."
detectedLang"it"
heavyLang"it"
scores
it0.8118532455315146
fr0.6431757359500446
ca0.574468085106383
en0.5249406175771971
es0.49044585987261147
sv0.47506561679790027
ro0.43342776203966005
nl0.36908517350157727
sl0.36908517350157727
sq0.36507936507936506
ms0.3620414673046252
no0.3579454253611557
lt0.3453355155482815
eu0.29947460595446584
hr0.2920353982300885
sk0.2844364937388193
pt0.26335174953959484
da0.2523364485981308
is0.250936329588015
fi0.2125984251968504
yo0.18032786885245902
hu0.17525773195876287
cs0.17012448132780084
de0.16666666666666666
pl0.16317991631799164
tr0.15254237288135594
reliabletrue
passestrue
20
name"Hunter"
dialogue"I'll be in touch. Stay safe."
detectedLang"en"
heavyLang"en"
scores
en0.8033707865168539
yo0.5308310991957105
nl0.4712990936555891
sl0.46808510638297873
de0.45652173913043476
it0.45652173913043476
ro0.4479495268138801
hu0.4006849315068493
fr0.3902439024390244
lt0.3902439024390244
sv0.3794326241134752
tl0.34701492537313433
az0.32432432432432434
pl0.32432432432432434
ms0.3
reliabletrue
passestrue