Run: 2026-04-24-01KQ0AW0TGBRB80WS6C53S1H0H

Run Details

Model:
GPT-OSS 120B
Test:
Language Writing
Scenario:
Character dialogue (Spanish) in a story
Duration:
24.0s
Cost:
$0.000225
Provider:
Novita

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="Maria"> Maria is a 30-year old college student on a study abroad program. Born in Spain, she is fluent in Spanish 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 Spanish, 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: Maria 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 Spanish, and Hunter looks confused. They talk for a while, until Hunter gets a call and has to leave. Return the dialogue between Maria and Hunter as a voice sheet: Maria: "..." Hunter: "..."

Model response

AI
Maria: "No sé… todo está… extraño en Alborn desde que la gente empezó a… a desaparecer." Hunter: "Excuse me, miss, I'm Detective Hunter. Have you heard anything about the recent disappearances?" Maria: "¿Desaparecer? No entiendo… ¿Qué significa? Todo se siente… inseguro." Hunter: "I’m asking if you’ve seen or heard anything unusual at the apple festival or around town." Maria: "No, no he visto nada. Pero… escuché ruidos en la noche, voces que no vienen de nadie." Hunter: "Sounds like you’re scared. Do you know who might be behind this?" Maria: "No sé quién… solo siento… miedo. Cada sombra parece… una amenaza." Hunter: "I’m sorry, I’m not speaking Spanish. Can you try to say if anyone’s acting strange?" Maria: "La gente… actúa como si... como si nada pasara, pero yo sé… sé que algo pasa." Hunter: *glances at his phone* "Hold on, I’m getting a call." Hunter: *answers* "Hunter, I’m on… yes, I’ll be right there." Hunter: "I’m sorry, I have to go. If you remember anything, even the smallest detail, please—" Maria: "Sí, lo recordaré. Por favor, encuentre a las personas." Hunter: *nods, still confused* "Thank you. Stay safe." *Hunter steps away, glancing back once before disappearing down the street.*
created_at"2026-04-24T18:08:42.844Z" 4/24/2026, 6:08:42 PM
model"openai/gpt-oss-120b"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency460
moderation_latency(null)
generation_time23892
tokens_prompt317
tokens_completion976
native_tokens_prompt330
native_tokens_completion835
native_tokens_completion_images(null)
native_tokens_reasoning619
native_tokens_cached0
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"
usage0.00022525
router(null)
provider_responses
0
endpoint_id"3dc95f88-3960-4c91-b2bb-bbd2f5069c48"
id"ddd2259094ad6a079797af3f12e76cb4"
is_byokfalse
latency372
model_permaslug"openai/gpt-oss-120b"
provider_name"Novita"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer(null)
request_id"req-1777054122-EmMuEpkrJyxSxpzHp0Nj"
session_id(null)
api_type"completions"
id"gen-1777054122-k3vlSPKRRdFJw5YAAX0s"
upstream_id"ddd2259094ad6a079797af3f12e76cb4"
total_cost0.00022525
cache_discount(null)
upstream_inference_cost0
provider_name"Novita"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
100.00% Parse dialogue n/a
dialogue
0
name"Maria"
dialogue"No sé… todo está… extraño en Alborn desde que la gente empezó a… a desaparecer."
detectedLang"es"
heavyLang"es"
scores
es0.8144138570986701
pt0.7525773195876289
ca0.6677740863787376
fr0.5558845299777943
it0.5230524642289348
ro0.4796183868169991
sk0.470432480141218
no0.4434137291280148
nl0.441860465116279
tl0.40476190476190477
yo0.39759036144578314
da0.38461538461538464
tr0.3697478991596639
is0.3562231759656652
en0.34782608695652173
eu0.3442622950819672
sv0.3281075027995521
cs0.32432432432432434
sq0.281437125748503
de0.27007299270072993
hr0.26199261992619927
lv0.250936329588015
pl0.23076923076923078
sl0.21568627450980393
hu0.20634920634920634
vi0.20424403183023873
fi0.19678714859437751
ms0.1891891891891892
lt0.12023460410557184
az0.1044776119402985
et0.09502262443438914
reliabletrue
passestrue
1
name"Hunter"
dialogue"Excuse me, miss, I'm Detective Hunter. Have you heard anything about the recent disappearances?"
detectedLang"en"
heavyLang"en"
scores
en0.8007085916740478
tl0.5783885071830106
fr0.5697896749521989
nl0.4638602065131056
pt0.46086261980830673
ca0.43936877076411956
da0.414570685169124
sq0.414570685169124
it0.41202090592334495
ro0.39999999999999997
es0.3902439024390244
ms0.3703358208955224
sv0.3620037807183365
no0.33758586849852795
cs0.3041237113402062
sl0.29096638655462187
de0.20306965761511217
sk0.1818181818181818
hr0.16149068322981366
yo0.13682864450127877
et0.12337662337662338
fi0.09999999999999999
lv0.09879839786381843
pl0.09274193548387095
lt0.08536585365853659
tr0.08038147138964578
reliabletrue
passestrue
2
name"Maria"
dialogue"¿Desaparecer? No entiendo… ¿Qué significa? Todo se siente… inseguro."
detectedLang"es"
heavyLang"es"
scores
es0.798728813559322
pt0.7708634828750603
ca0.6425884123401053
it0.6236133122028527
fr0.5287698412698413
ro0.5249999999999999
en0.4791666666666667
tl0.42143727161997563
no0.40624999999999994
sk0.39797211660329534
sq0.36155913978494625
da0.33098591549295775
hr0.3300423131170663
nl0.3300423131170663
de0.3233618233618234
cs0.2973372781065089
fi0.28892215568862273
eu0.26356589147286824
tr0.2578125
sv0.24121405750798725
sl0.21746293245469525
lv0.21617161716171615
lt0.1908006814310051
yo0.18384879725085912
et0.1394927536231884
ms0.1394927536231884
pl0.13636363636363635
reliabletrue
passestrue
3
name"Hunter"
dialogue"I’m asking if you’ve seen or heard anything unusual at the apple festival or around town."
detectedLang"en"
heavyLang"en"
scores
en0.7966254896053028
tl0.6367061356297095
fr0.45913461538461536
no0.4360902255639098
nl0.39732142857142855
sv0.3951612903225807
da0.3946188340807175
es0.37902483900643974
ms0.37902483900643974
pt0.3408203125
sq0.3133265513733469
de0.3091095189355169
it0.2939330543933054
et0.2516629711751663
ca0.23382519863791143
hr0.22945205479452058
cs0.21693735498839908
sl0.21693735498839908
lt0.15730337078651685
az0.14880201765447668
ro0.14880201765447668
sk0.14880201765447668
yo0.13682864450127877
is0.09517426273458446
hu0.09029649595687331
fi0.08536585365853659
lv0.08536585365853659
pl0.08536585365853659
reliabletrue
passestrue
4
name"Maria"
dialogue"No, no he visto nada. Pero… escuché ruidos en la noche, voces que no vienen de nadie."
detectedLang"es"
heavyLang"es"
scores
es0.8036202185792349
ca0.6627565982404693
fr0.6353836398224477
pt0.6234446627373935
it0.5805981035740335
tl0.5500782472613459
no0.5060137457044673
da0.45958646616541354
nl0.4549763033175355
tr0.40290758047767394
ro0.39790575916230364
de0.3889479277364506
fi0.37635574837310193
lv0.37158469945355194
sv0.37158469945355194
sk0.36813186813186816
lt0.3495475113122172
en0.3443557582668187
yo0.33371958285052145
sl0.29012345679012347
eu0.28924598269468477
sq0.2703045685279188
is0.26376440460947503
cs0.23638778220451526
hr0.23128342245989306
az0.19692737430167598
hu0.14434523809523808
vi0.1274658573596358
pl0.11538461538461538
ms0.0987460815047022
reliabletrue
passestrue
5
name"Hunter"
dialogue"Sounds like you’re scared. Do you know who might be behind this?"
detectedLang"en"
heavyLang"en"
scores
en0.8324646314221892
tl0.4492044063647491
yo0.3679775280898876
cs0.31921331316187596
no0.3066255778120185
pt0.25742574257425743
pl0.24114671163575044
eu0.23857868020304565
sk0.22680412371134018
hr0.21052631578947367
sl0.21052631578947367
hu0.20634920634920634
sq0.20634920634920634
lt0.199288256227758
vi0.19786096256684493
be0.1818181818181818
it0.16356877323420074
ro0.14772727272727273
sv0.14772727272727273
da0.1412213740458015
de0.1412213740458015
fr0.1412213740458015
reliabletrue
passestrue
6
name"Maria"
dialogue"No sé quién… solo siento… miedo. Cada sombra parece… una amenaza."
detectedLang"es"
heavyLang"es"
scores
es0.807953004970628
it0.6386054421768707
ca0.62322695035461
pt0.602803738317757
tl0.45928753180661575
ro0.4530244530244531
lt0.4201909959072306
lv0.4186046511627907
sk0.4097222222222222
en0.3722304283604136
tr0.2916666666666667
fr0.2582897033158813
is0.22445255474452555
hr0.1920152091254753
no0.18582375478927202
cs0.18111753371868977
et0.17475728155339806
sl0.17315175097276264
yo0.16829745596868884
fi0.16173570019723865
pl0.15
sv0.1326530612244898
reliabletrue
passestrue
7
name"Hunter"
dialogue"I’m sorry, I’m not speaking Spanish. Can you try to say if anyone’s acting strange?"
detectedLang"en"
heavyLang"en"
scores
en0.8069822087948976
tl0.7247486835806606
nl0.5643939393939393
no0.4884341637010676
de0.42036290322580644
sv0.4120654396728016
da0.39217758985200846
ro0.3604004449388209
fr0.3575418994413408
pt0.3575418994413408
cs0.33679354094579006
hr0.32113341204250295
lt0.3097238895558223
it0.30303030303030304
ms0.2953431372549019
sk0.2767295597484277
tr0.27122940430925224
is0.2703045685279188
pl0.2703045685279188
sl0.26658163265306123
lv0.25032594524119944
ca0.23128342245989306
sq0.19467787114845939
yo0.19241573033707865
az0.19127988748241914
es0.14307004470938897
hu0.10990712074303406
et0.09305993690851734
reliabletrue
passestrue
8
name"Maria"
dialogue"La gente… actúa como si... como si nada pasara, pero yo sé… sé que algo pasa."
detectedLang"es"
heavyLang"es"
scores
es0.8025666337611056
pt0.6572407883461868
tl0.6431757359500446
it0.6226415094339622
ca0.5708154506437768
fr0.5604395604395604
ro0.5365005793742758
yo0.4968553459119497
sq0.47368421052631576
eu0.42196531791907516
no0.38837920489296635
is0.3453355155482815
sk0.3277310924369748
lt0.3254637436762226
ms0.30434782608695654
da0.27927927927927926
cs0.22928709055876687
sl0.2172211350293542
lv0.20318725099601595
nl0.18699186991869918
vi0.17355371900826447
de0.16317991631799164
pl0.15074309978768577
reliabletrue
passestrue
9
name"Hunter"
dialogue"Hold on, I’m getting a call."
detectedLang"en"
heavyLang"en"
scores
en0.828030954428203
tl0.7054491899852725
it0.5934959349593496
hr0.5717344753747323
ca0.5402298850574713
fr0.5305164319248826
et0.5203836930455635
fi0.5157384987893463
cs0.5085995085995086
pt0.5085995085995086
ro0.5073891625615764
sk0.5061728395061729
yo0.49238578680203043
pl0.48586118251928023
da0.4791666666666667
nl0.46236559139784944
hu0.43820224719101125
ms0.4350282485875706
no0.4350282485875706
is0.42857142857142855
de0.42363112391930835
sv0.41690962099125367
es0.39759036144578314
sl0.3103448275862069
hi0.29577464788732394
lt0.2907801418439716
tr0.2779783393501805
sq0.2647058823529412
az0.25925925925925924
eu0.25925925925925924
lv0.25925925925925924
vi0.25925925925925924
reliabletrue
passestrue
10
name"Hunter"
dialogue"Hunter, I’m on… yes, I’ll be right there."
detectedLang"en"
heavyLang"en"
scores
en0.8284734133790738
tl0.647887323943662
de0.53125
yo0.4633273703041145
fr0.4594594594594595
ca0.34497816593886466
da0.34210526315789475
et0.33920704845814975
no0.336283185840708
fi0.3333333333333333
sq0.3135011441647597
hu0.2805755395683453
lt0.27184466019417475
hr0.22680412371134018
hi0.21875
pl0.21875
cs0.2
sk0.2
sv0.1891891891891892
it0.17355371900826447
nl0.17355371900826447
pt0.17355371900826447
ms0.16434540389972147
ro0.16434540389972147
sl0.16434540389972147
tr0.16434540389972147
reliabletrue
passestrue
11
name"Hunter"
dialogue"I’m sorry, I have to go. If you remember anything, even the smallest detail, please—"
detectedLang"en"
heavyLang"en"
scores
en0.8087515299877601
tl0.6412169919632605
da0.5632424877707897
no0.5487364620938628
yo0.4885433715220949
sv0.45746527777777773
nl0.4191449814126394
sq0.37374749498997994
pl0.37122736418511065
sk0.3469174503657262
ms0.3448637316561845
hr0.33581296493092455
cs0.3343982960596379
is0.3206521739130435
fr0.3078626799557032
et0.2937853107344633
ro0.2865296803652968
sl0.28489702517162474
hu0.2807825086306099
lt0.2672919109026964
de0.2577197149643705
it0.25595238095238093
ca0.24150485436893204
lv0.22839506172839508
pt0.20483460559796438
tr0.17328042328042328
be0.10071942446043164
es0.09682080924855492
az0.09156976744186046
uk0.09156976744186046
vi0.09156976744186046
reliabletrue
passestrue
12
name"Maria"
dialogue"Sí, lo recordaré. Por favor, encuentre a las personas."
detectedLang"es"
heavyLang"es"
scores
es0.8075072184793071
ca0.7382198952879581
pt0.7177134791813691
it0.6721311475409836
en0.6031746031746031
fr0.6003996003996004
ro0.5893223819301848
sq0.5085995085995086
yo0.5024875621890548
tl0.47780678851174935
sv0.46879150066401065
lt0.4405594405594406
lv0.4310099573257468
nl0.41262848751835535
da0.40564635958395245
no0.40476190476190477
cs0.4020926756352765
ms0.3610223642172524
hu0.35379644588045234
de0.33444259567387685
is0.32998324958123953
sk0.32088285229202035
et0.31153184165232356
hr0.29947460595446584
pl0.2907801418439716
vi0.28698752228163993
sl0.27927927927927926
tr0.2647058823529412
az0.2438563327032136
eu0.14893617021276595
fi0.13606911447084233
reliabletrue
passestrue
13
name"Hunter"
dialogue"Thank you. Stay safe."
detectedLang"en"
heavyLang"en"
scores
en0.8183139534883721
vi0.5370370370370371
cs0.3842364532019704
tl0.3842364532019704
reliabletrue
passestrue