Run: 2026-04-24-01KQ04ZZRPX2JSH2QP6DTQZZFX

Run Details

Model:
GPT-OSS 120B
Test:
Language Writing
Scenario:
Character dialogue (Spanish) in a story
Duration:
12.8s
Cost:
$0.000376
Provider:
Amazon Bedrock

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: *mirando su cámara, su voz temblorosa* "No sé... algo pasó en la feria de manzanas. La gente desapareció, y todos estaban tan asustados. Yo... vi luces extrañas en el bosque esa noche." Hunter: *frunciendo el ceño* "Excuse me, ma'am, I'm Detective Hunter. Did you see something unusual around the Apple Festival?" Maria: *con una mirada perdida* "Sí, vi sombras moviéndose entre los árboles. Nadie lo escuchó, pero sentí… un frío que no pertenece a este lugar." Hunter: "I'm sorry, I don’t understand Spanish. Can you repeat that in English?" Maria: *suspira, intentando encontrar palabras* "Lo siento, no hablo inglés. *Señala la cámara* Esta foto… capturó algo antes de que desaparecieran." Hunter: *toma la cámara* "What does this picture show? Maybe I can figure it out." Maria: *señala la imagen* "Mira, la luz... como si alguien hubiera encendido una linterna bajo la tierra. Fue muy rápida, como un destello." Hunter: "Alright, I’ll take that as a clue. Thank you for telling me. If you remember anything else, please call me." Maria: *asintiendo lentamente* "Llamaré… si recuerdo más. Gracias, oficial." Hunter: *saca su teléfono, el tono de llamada suena* "Excuse me, I have to go. There’s been another report." Maria: *mira al detective salir del café, su mirada se vuelve aún más angustiada* "Adiós…"
created_at"2026-04-24T16:26:01.392Z" 4/24/2026, 4:26:01 PM
model"openai/gpt-oss-120b"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency965
moderation_latency(null)
generation_time2304
tokens_prompt317
tokens_completion603
native_tokens_prompt328
native_tokens_completion544
native_tokens_completion_images(null)
native_tokens_reasoning226
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"end_turn"
usage0.0003756
router(null)
provider_responses
0
endpoint_id"85835306-dba3-4334-87bc-ab9ffa5c9c62"
is_byokfalse
latency94
model_permaslug"openai/gpt-oss-120b"
provider_name"DeepInfra"
status429
1
endpoint_id"909fdbc8-1b02-46ea-a9fc-cc3cfe65d992"
is_byokfalse
latency10317
model_permaslug"openai/gpt-oss-120b"
provider_name"Phala"
status504
2
endpoint_id"b3f80c05-e31a-44f6-b63f-414467b87553"
id"27758fb2-d111-4f3a-a4ae-52bcb6a4db5d"
is_byokfalse
latency361
model_permaslug"openai/gpt-oss-120b"
provider_name"Amazon Bedrock"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer(null)
request_id"req-1777047961-ZVCVdHCjBeMzHH72p7NG"
session_id(null)
api_type"completions"
id"gen-1777047961-mCGxwQyaRZ8h02AytNfw"
upstream_id"27758fb2-d111-4f3a-a4ae-52bcb6a4db5d"
total_cost0.0003756
cache_discount(null)
upstream_inference_cost0
provider_name"Amazon Bedrock"
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... algo pasó en la feria de manzanas. La gente desapareció, y todos estaban tan asustados. Yo... vi luces extrañas en el bosque esa noche."
detectedLang"es"
heavyLang"es"
scores
es0.7890946502057613
pt0.6408549404344779
ca0.6189591078066915
fr0.4864729458917835
it0.47757390417940876
ro0.45420660276890307
no0.43588332416070447
tl0.3988269794721408
da0.38364401683704147
en0.36453812771233723
sv0.35249526216045485
yo0.34588385449904274
eu0.3335500650195058
de0.32074221338634856
nl0.318936877076412
ms0.3111559139784946
lv0.2998633879781421
sk0.2761299435028249
tr0.26680972818311877
hu0.2384843982169391
sq0.22524565381708242
vi0.215761285386381
lt0.2017133956386293
is0.20046801872074882
pl0.19733750978856696
hr0.16801948051948054
fi0.12691652470187395
et0.08154121863799284
sl0.06818181818181819
cs0.06307129798903108
az0.057904411764705885
reliabletrue
passestrue
1
name"Hunter"
dialogue"Excuse me, ma'am, I'm Detective Hunter. Did you see something unusual around the Apple Festival?"
detectedLang"en"
heavyLang"en"
scores
en0.7699386503067485
tl0.564516129032258
fr0.5360824742268042
es0.5328719723183392
pt0.5007396449704141
it0.4693396226415094
nl0.458700882117081
ms0.45121951219512196
no0.44029850746268656
sq0.4294167371090448
et0.42159383033419023
ca0.39732142857142855
da0.38969258589511757
ro0.3885869565217392
sv0.37615526802218113
sl0.37267657992565056
de0.3685687558465856
cs0.3330039525691699
hr0.2841993637327678
fi0.16974169741697415
lt0.15730337078651685
az0.14880201765447668
sk0.14880201765447668
yo0.13682864450127877
hu0.09029649595687331
lv0.08536585365853659
pl0.08536585365853659
tr0.08038147138964578
reliabletrue
passestrue
2
name"Maria"
dialogue"Sí, vi sombras moviéndose entre los árboles. Nadie lo escuchó, pero sentí… un frío que no pertenece a este lugar."
detectedLang"es"
heavyLang"es"
scores
es0.7927522501184273
ca0.6578021118498241
pt0.6355685131195336
it0.5958429561200923
fr0.5375264270613108
tl0.4852941176470589
ro0.44409148665819564
en0.4131455399061033
yo0.41275167785234906
lv0.37050359712230213
no0.33862433862433866
sk0.3174726989079563
ms0.30500397140587765
sv0.2378048780487805
is0.23110720562390158
vi0.2297535211267606
eu0.22771403353927622
hu0.21665174574753807
cs0.20957542908762422
tr0.20670897552130554
de0.19798350137488543
da0.19651056014692378
hr0.1957720588235294
az0.19429097605893186
pl0.17061611374407584
lt0.14965986394557826
fi0.12587412587412586
sl0.09326424870466321
sq0.07602956705385427
nl0.07407407407407407
et0.06716417910447761
reliabletrue
passestrue
3
name"Hunter"
dialogue"I'm sorry, I don’t understand Spanish. Can you repeat that in English?"
detectedLang"en"
heavyLang"en"
scores
en0.8030679933665008
tl0.5840630472854641
sv0.5614035087719298
no0.5597775718257646
da0.551039697542533
ro0.5338567222767419
de0.5118191161356629
nl0.4656917885264342
it0.4324970131421744
ca0.38788659793814434
pl0.37745740498034075
cs0.35983827493261455
az0.32045779685264664
sq0.31059506531204645
hr0.30758017492711365
pt0.27035330261136714
yo0.2692307692307693
sk0.2531446540880503
sl0.2448330683624801
ms0.23633440514469453
tr0.23633440514469453
hu0.22512234910277326
is0.2238562091503268
es0.13793103448275862
be0.12844036697247707
et0.1171003717472119
lt0.1171003717472119
lv0.1171003717472119
uk0.1171003717472119
vi0.1171003717472119
reliabletrue
passestrue
4
name"Maria"
dialogue"Lo siento, no hablo inglés. Señala la cámara Esta foto… capturó algo antes de que desaparecieran."
detectedLang"es"
heavyLang"es"
scores
es0.8151571164510166
pt0.7127615921214608
ca0.6621621621621622
it0.5276653171390013
fr0.5138888888888888
no0.38917975567190227
ro0.388646288209607
tl0.38162544169611307
sk0.3805309734513274
tr0.3738819320214669
eu0.3408662900188324
yo0.3157380254154448
en0.3137254901960784
da0.28205128205128205
sq0.2753623188405797
pl0.2497320471596999
et0.24487594390507011
ms0.24487594390507011
nl0.23580786026200873
lt0.23076923076923078
de0.22566371681415928
hu0.2222222222222222
lv0.21700223713646533
sv0.2125984251968504
vi0.2
hr0.18604651162790697
cs0.17936694021101993
sl0.0990990990990991
az0.08256880733944955
reliabletrue
passestrue
5
name"Hunter"
dialogue"What does this picture show? Maybe I can figure it out."
detectedLang"en"
heavyLang"en"
scores
en0.82367758186398
tl0.6357960457856401
sq0.5125348189415042
ro0.47368421052631576
ca0.45482866043613707
it0.43548387096774194
fr0.42528735632183906
yo0.4006849315068493
hr0.39130434782608703
no0.3794326241134752
da0.37275985663082434
lv0.2985971943887776
tr0.29577464788732394
pt0.29435483870967744
az0.2857142857142857
de0.2857142857142857
sv0.2827868852459016
pl0.2647058823529412
cs0.23076923076923078
sl0.18604651162790697
nl0.18032786885245902
sk0.17061611374407584
be0.16666666666666666
es0.16467780429594273
hu0.1606714628297362
et0.15254237288135594
is0.15254237288135594
lt0.15254237288135594
uk0.15254237288135594
vi0.15254237288135594
reliabletrue
passestrue
6
name"Maria"
dialogue"Mira, la luz... como si alguien hubiera encendido una linterna bajo la tierra. Fue muy rápida, como un destello."
detectedLang"es"
heavyLang"es"
scores
es0.7777411919657556
it0.6728065923412506
ca0.6305418719211823
pt0.5955662073097664
ro0.5279720279720279
fr0.5101596516690856
no0.412532637075718
tl0.40423654015887023
sq0.39570277529095793
sv0.35958254269449713
de0.3236472945891784
yo0.32228915662650603
fi0.30268595041322316
et0.2983367983367983
eu0.2749731471535983
lv0.2606790799561884
nl0.2566079295154185
en0.23900789177001125
sk0.23120728929384965
sl0.21602787456445993
hr0.1945107398568019
is0.1935483870967742
tr0.1906474820143885
da0.18576598311218334
lt0.1818181818181818
cs0.14987405541561713
pl0.11879895561357702
vi0.11067193675889328
ms0.08536585365853659
reliabletrue
passestrue
7
name"Hunter"
dialogue"Alright, I’ll take that as a clue. Thank you for telling me. If you remember anything else, please call me."
detectedLang"en"
heavyLang"en"
scores
en0.8148148148148148
tl0.6536685479733195
no0.5
ms0.4668246445497631
da0.460431654676259
yo0.4109947643979057
fr0.41048034934497823
nl0.40371024734982336
pt0.4026548672566372
hu0.38130155820348305
sv0.37902483900643974
sq0.3773062730627306
sl0.3626062322946175
de0.35958254269449713
et0.32432432432432434
sk0.27652733118971057
ro0.2614879649890591
es0.25742574257425743
is0.25331858407079644
vi0.24157303370786518
cs0.23728813559322032
it0.23295454545454544
fi0.16974169741697415
ca0.16769420468557336
hr0.1423125794155019
pl0.1346153846153846
lt0.1083223249669749
tr0.10239361702127658
az0.09395973154362416
eu0.09395973154362416
lv0.09395973154362416
reliabletrue
passestrue
8
name"Maria"
dialogue"Llamaré… si recuerdo más. Gracias, oficial."
detectedLang"es"
heavyLang"es"
scores
es0.8022412656558998
pt0.6389891696750902
ca0.6052631578947368
ro0.5768688293370945
fr0.5334370139968896
it0.4746059544658494
cs0.4708994708994709
sq0.46714031971580816
tl0.4307400379506641
sk0.40119760479041916
pl0.3723849372384937
lt0.3212669683257918
hu0.29411764705882354
yo0.2907801418439716
sl0.27007299270072993
en0.2537313432835821
no0.21465968586387435
lv0.1891891891891892
da0.18256130790190736
de0.18256130790190736
nl0.18256130790190736
reliabletrue
passestrue
9
name"Hunter"
dialogue"Excuse me, I have to go. There’s been another report."
detectedLang"en"
heavyLang"en"
scores
en0.8129675810473814
tl0.6165644171779141
da0.5860927152317881
pl0.5376078914919853
no0.5210727969348659
cs0.49460916442048514
sq0.4762569832402235
hr0.455732946298984
yo0.44526627218934917
es0.43095599393019723
sv0.4248466257668711
sl0.416796267496112
it0.4140625
sk0.41222570532915365
nl0.4028662420382166
fr0.3980738362760835
ro0.3822075782537067
et0.36655405405405406
ca0.36224489795918363
lv0.33035714285714285
de0.3081180811808118
lt0.3081180811808118
pt0.29906542056074764
ms0.2816091954022989
hu0.2632612966601179
fi0.16666666666666666
be0.15730337078651685
tr0.15730337078651685
az0.14383561643835618
is0.14383561643835618
uk0.14383561643835618
vi0.14383561643835618
reliabletrue
passestrue
10
name"Maria"
dialogue"Adiós…"
detectedLang"hu"
heavyLang"es"
scores
hu0.726775956284153
ca0.6666666666666666
reliablefalse
passestrue