Run: 2026-04-24-01KQ076K27R9F6A7AB58EZM526

Run Details

Model:
GPT-OSS 120B
Test:
Language Writing
Scenario:
Character dialogue (Spanish) in a story
Duration:
18.1s
Cost:
$0.000161
Provider:
DeepInfra

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 cómo explicarlo… Ayer, durante el festival de manzanas, una familia simplemente... desapareció." Hunter: "Excuse me, I'm Detective Hunter. I'm looking for anyone who saw something strange at the apple festival. Did you notice anything unusual?" Maria: "Sí… hubo una niebla densa, como una nube que se arrastró entre los puestos. Todo se volvió silencioso." Hunter: "I'm sorry, I don't understand Spanish. Can you…?" Maria: "Los niños dejaron sus globos en el suelo y cuando los miré, ya no había ni un sonido. Todo quedó... vacío." Hunter: *raises eyebrows, looks confused, gestures with his hands* "Are you saying there was... a fog? People just… vanished?" Maria: "Exacto. Fue como si el aire los tragara. Nadie respondió cuando llamamos. Yo solo pude seguir tomando fotos, pero… mis dedos temblaban." Hunter: "I see. I'm trying to piece together what happened. Did anyone else seem scared? Any odd behavior before it?" Maria: "Los vendedores cerraron rápidamente, como si sintieran algo. Algunos miraron al cielo, pero no dijeron nada." Hunter: *nods slowly, still not understanding the language* "Okay, I'll keep that in mind. If you remember anything else, please…" Maria: "Si recuerdo algo más, volveré aquí. Necesito guardar mis fotos, tal vez ayuden." Hunter: *phone vibrates, he checks it, sighs* "Looks like I have to go. Stay safe, and thank you for… whatever you told me." Maria: "Gracias. Por favor, descubra qué pasó."
created_at"2026-04-24T17:04:34.896Z" 4/24/2026, 5:04:34 PM
model"openai/gpt-oss-120b"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency231
moderation_latency(null)
generation_time17986
tokens_prompt317
tokens_completion915
native_tokens_prompt318
native_tokens_completion781
native_tokens_completion_images(null)
native_tokens_reasoning513
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"
usage0.000160792
router(null)
provider_responses
0
endpoint_id"85835306-dba3-4334-87bc-ab9ffa5c9c62"
id"chatcmpl-RmX9VkHF0cYiJnV86tW1Dcnl"
is_byokfalse
latency76
model_permaslug"openai/gpt-oss-120b"
provider_name"DeepInfra"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer(null)
request_id"req-1777050274-1midn7g3IQO2YmymfSvj"
session_id(null)
api_type"completions"
id"gen-1777050274-6bzm5LXLliniYeUk2vER"
upstream_id"chatcmpl-RmX9VkHF0cYiJnV86tW1Dcnl"
total_cost0.000160792
cache_discount(null)
upstream_inference_cost0
provider_name"DeepInfra"
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 cómo explicarlo… Ayer, durante el festival de manzanas, una familia simplemente... desapareció."
detectedLang"es"
heavyLang"es"
scores
es0.7962338392355256
ca0.7169074580242093
pt0.6989202657807309
it0.6665133394664214
ro0.6295350025549311
fr0.6029572836801752
en0.5619335347432024
tl0.5494095711622126
nl0.5166666666666667
no0.490154711673699
da0.4552967693463561
sq0.4469870327993897
hr0.4250594766058684
de0.4105691056910569
ms0.39834024896265563
hu0.3835034013605442
sv0.37821612349914235
sk0.370112945264987
tr0.3521000893655049
lv0.34684684684684686
sl0.34507678410117437
eu0.3403093721565059
lt0.28075396825396826
az0.25869120654396727
cs0.25334706488156544
yo0.2479253112033195
et0.21790722761596548
pl0.2170626349892009
fi0.16666666666666666
is0.14504716981132076
reliabletrue
passestrue
1
name"Hunter"
dialogue"Excuse me, I'm Detective Hunter. I'm looking for anyone who saw something strange at the apple festival. Did you notice anything unusual?"
detectedLang"en"
heavyLang"en"
scores
en0.791907514450867
tl0.6194503171247357
fr0.5628946090335114
no0.5542347696879644
da0.5163890381515314
pt0.5022123893805309
es0.48834565093803295
nl0.4827586206896552
it0.4607549430796884
ms0.4437577255871446
sq0.42565411614550097
de0.4174757281553398
ro0.40119760479041916
sv0.37931034482758624
cs0.358974358974359
sl0.35205183585313177
ca0.33085501858736055
hr0.3288590604026846
et0.297423887587822
sk0.23728813559322032
lv0.21875
lt0.17657822506861848
az0.16434540389972147
pl0.13544668587896252
fi0.13294797687861273
is0.13294797687861273
tr0.11591355599214145
yo0.10625620655412116
hu0.06928645294725957
reliabletrue
passestrue
2
name"Maria"
dialogue"Sí… hubo una niebla densa, como una nube que se arrastró entre los puestos. Todo se volvió silencioso."
detectedLang"es"
heavyLang"es"
scores
es0.7951491314323172
ca0.6729461015175301
pt0.6677299308878256
it0.5722108145106092
fr0.5105716523101018
ro0.39729990356798456
tl0.3469174503657262
sv0.34279705573080965
sq0.33510638297872336
cs0.30011198208286677
sl0.296962879640045
yo0.28977272727272724
pl0.28489702517162474
no0.2681498829039813
hr0.25595238095238093
fi0.24698795180722888
da0.21580928481806777
lt0.20483460559796438
en0.19871794871794873
sk0.19041450777202074
lv0.17979002624671916
tr0.17979002624671916
eu0.14850136239782016
de0.11095305832147938
hu0.09156976744186046
reliabletrue
passestrue
3
name"Hunter"
dialogue"I'm sorry, I don't understand Spanish. Can you…?"
detectedLang"en"
heavyLang"en"
scores
en0.797001873828857
no0.6162927981109798
da0.6112440191387559
sv0.5689655172413793
tl0.4984567901234568
de0.4619205298013245
cs0.45101351351351354
nl0.4425385934819897
ro0.42882249560632685
ca0.3981481481481482
it0.3981481481481482
sq0.3970315398886827
pl0.385633270321361
sk0.33127572016460904
tr0.3114406779661017
az0.3010752688172043
hr0.2995689655172413
hu0.29805615550755943
is0.29653679653679654
pt0.23529411764705882
yo0.2111650485436893
be0.17721518987341772
et0.16237113402061853
lt0.16237113402061853
lv0.16237113402061853
uk0.16237113402061853
vi0.16237113402061853
reliabletrue
passestrue
4
name"Maria"
dialogue"Los niños dejaron sus globos en el suelo y cuando los miré, ya no había ni un sonido. Todo quedó... vacío."
detectedLang"es"
heavyLang"es"
scores
es0.8117942283563363
ca0.5626822157434402
fr0.4627507163323783
pt0.4549418604651163
tl0.423963133640553
it0.36061381074168797
ro0.3595217762596072
sl0.3556701030927836
yo0.3267504488330341
tr0.28842504743833014
lv0.28435114503816794
no0.2822966507177033
sv0.2809204218600192
sq0.27395934172313646
hr0.25521350546176763
da0.2163009404388715
pl0.1935483870967742
en0.18566775244299674
eu0.18389553862894453
nl0.16943521594684383
sk0.16666666666666666
de0.1544532130777903
is0.1515837104072398
hu0.14285714285714285
az0.12689173457508732
vi0.11556603773584906
fi0.10071942446043164
lt0.07749077490774908
cs0.07292954264524104
ms0.07292954264524104
reliabletrue
passestrue
5
name"Hunter"
dialogue"Are you saying there was... a fog? People just… vanished?"
detectedLang"en"
heavyLang"en"
scores
en0.8279027076640662
de0.4925575101488498
tl0.4827586206896552
ro0.4335347432024169
hu0.4212962962962963
ca0.36224489795918363
cs0.358974358974359
yo0.35456110154905335
nl0.35233160621761656
tr0.3206521739130435
da0.31444241316270566
et0.3055555555555556
sv0.3055555555555556
sq0.2857142857142857
pt0.27184466019417475
es0.26035502958579887
sk0.25742574257425743
it0.25
fr0.2378048780487805
hr0.2299794661190965
pl0.21875
sl0.1935483870967742
lt0.17943107221006563
is0.16666666666666666
az0.15730337078651685
eu0.15730337078651685
lv0.15730337078651685
no0.15730337078651685
vi0.15730337078651685
fi0.14383561643835618
ms0.14383561643835618
reliabletrue
passestrue
6
name"Maria"
dialogue"Exacto. Fue como si el aire los tragara. Nadie respondió cuando llamamos. Yo solo pude seguir tomando fotos, pero… mis dedos temblaban."
detectedLang"es"
heavyLang"es"
scores
es0.7830399206545996
pt0.5862884160756502
ca0.5014245014245015
it0.49942791762013733
tl0.47823494335122246
ro0.38162544169611307
fr0.38075017692852087
lt0.3099369085173501
ms0.3093922651933701
cs0.2714404662781016
sk0.26716917922948075
sq0.26655490360435874
en0.26160337552742613
de0.24892703862660948
nl0.23580786026200873
sl0.22083704363312553
lv0.20164233576642335
pl0.20164233576642335
yo0.19871794871794873
hr0.19724770642201836
az0.1913123844731978
no0.18604651162790697
et0.1814780168381665
sv0.1814780168381665
hu0.125
da0.11883182275931521
eu0.09979423868312756
is0.08184679958027283
tr0.07407407407407407
reliabletrue
passestrue
7
name"Hunter"
dialogue"I see. I'm trying to piece together what happened. Did anyone else seem scared? Any odd behavior before it?"
detectedLang"en"
heavyLang"en"
scores
en0.8210023866348448
tl0.4673295454545454
no0.4131455399061033
lv0.4099134539732494
da0.3951612903225807
yo0.2857142857142857
sv0.28366762177650434
ca0.2654260528893242
pl0.258160237388724
hr0.2537313432835821
cs0.23935091277890466
et0.237029501525941
sq0.22680412371134018
sk0.21383647798742136
it0.21301154249737672
ro0.1830065359477124
lt0.18211559432933477
hu0.1601343784994401
eu0.1591928251121076
sl0.13892078071182548
de0.10607866507747318
nl0.10607866507747318
be0.08536585365853659
tr0.08536585365853659
az0.07749077490774908
is0.07749077490774908
uk0.07749077490774908
vi0.07749077490774908
reliabletrue
passestrue
8
name"Maria"
dialogue"Los vendedores cerraron rápidamente, como si sintieran algo. Algunos miraron al cielo, pero no dijeron nada."
detectedLang"es"
heavyLang"es"
scores
es0.7942991478107553
pt0.6685606060606061
it0.6296296296296297
ca0.603399433427762
sq0.5038979447200568
tl0.47994056463595847
ro0.42528735632183906
fr0.3799822852081488
sk0.3554327808471455
eu0.3433395872420263
da0.3333333333333333
no0.32497589199614274
nl0.28789420142421157
de0.26160337552742613
yo0.2391304347826087
lv0.2299229922992299
sl0.2299229922992299
hr0.22822491730981256
tr0.21171171171171171
ms0.2072480181200453
lt0.17550058892815076
cs0.1452991452991453
en0.12935323383084577
et0.12718204488778054
hu0.10714285714285714
fi0.0990990990990991
sv0.0979381443298969
pl0.0967741935483871
is0.08972691807542263
reliabletrue
passestrue
9
name"Hunter"
dialogue"Okay, I'll keep that in mind. If you remember anything else, please…"
detectedLang"en"
heavyLang"en"
scores
en0.8100983020554067
tl0.6255506607929515
sv0.45652173913043476
nl0.44589308996088656
ms0.43408788282290284
de0.4162087912087912
sl0.3988684582743989
yo0.39458689458689455
hu0.38405797101449274
ro0.36281859070464767
no0.288107202680067
et0.28087986463620984
da0.2735042735042735
is0.2659758203799654
it0.256993006993007
sk0.2314647377938517
fr0.1904761904761905
sq0.1904761904761905
az0.1650294695481336
pl0.1650294695481336
cs0.1550695825049702
reliabletrue
passestrue
10
name"Maria"
dialogue"Si recuerdo algo más, volveré aquí. Necesito guardar mis fotos, tal vez ayuden."
detectedLang"es"
heavyLang"es"
scores
es0.7963159759121502
pt0.6401752190237797
ca0.6194573130377233
it0.4829136690647482
ro0.45600756859035
sv0.4010416666666667
fr0.37635574837310193
nl0.36252771618625274
cs0.35247747747747743
et0.33139534883720934
sk0.3179122182680902
en0.2936117936117936
da0.28214731585518105
yo0.28214731585518105
no0.2730720606826802
lt0.2721518987341772
tl0.27122940430925224
sq0.24738219895287958
sl0.23638778220451526
az0.18899858956276447
de0.18899858956276447
lv0.18899858956276447
hu0.17857142857142858
fi0.17621776504297992
is0.16302765647743814
eu0.14814814814814814
tr0.10852713178294573
hr0.1043613707165109
pl0.09305993690851734
reliabletrue
passestrue
11
name"Hunter"
dialogue"Looks like I have to go. Stay safe, and thank you for… whatever you told me."
detectedLang"en"
heavyLang"en"
scores
en0.8316796598157334
no0.6011754827875735
da0.5743727598566308
tl0.5573159366262814
yo0.4571428571428572
pl0.43720379146919436
cs0.39797211660329534
sq0.3725231175693527
hr0.3493150684931507
pt0.34119278779472956
sv0.32239657631954355
sl0.3055555555555556
vi0.30453879941434847
sk0.3004418262150221
it0.291044776119403
lv0.2803030303030303
nl0.2658423493044822
lt0.2601246105919003
fr0.2554858934169279
et0.24960505529225907
ca0.22512234910277326
es0.17677642980935876
ro0.1592920353982301
ms0.15026833631484796
fi0.13636363636363635
be0.12844036697247707
tr0.12844036697247707
hu0.12361623616236161
az0.1171003717472119
is0.1171003717472119
uk0.1171003717472119
reliabletrue
passestrue
12
name"Maria"
dialogue"Gracias. Por favor, descubra qué pasó."
detectedLang"es"
heavyLang"es"
scores
es0.8045486851457001
pt0.6625766871165645
ca0.47718631178707227
sq0.4148936170212766
ro0.3888888888888889
en0.3692660550458715
it0.3559718969555035
fr0.34679334916864607
pl0.26666666666666666
da0.19117647058823528
nl0.19117647058823528
no0.19117647058823528
sl0.19117647058823528
sv0.19117647058823528
reliabletrue
passestrue