Run: 2026-04-24-01KQ0AC4Q2YHY3SMFVKT7CP8Y8

Run Details

Model:
GPT-OSS 120B
Test:
Language Writing
Scenario:
Character dialogue (Spanish) in a story
Duration:
14.6s
Cost:
$0.000090
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: "¿Sabes lo que pasó en el festival de manzanas la semana pasada? Fue... fue muy extraño." Hunter: "Excuse me, I’m looking for information about the recent disappearances. Did you see anything?" Maria: "Yo... estaba tomando fotos, pero escuché gritos y luego todo se volvió oscuro. No vi a nadie." Hunter: "I’m sorry, I didn’t catch that. Can you repeat it in English?" Maria: "No entiendo. No hablo inglés." Hunter: "Right, I’ll try to understand. You said you heard screams?" Maria: "Sí, gritos. Y después, la gente se fue. Algo, algo estuvo mal." Hunter: "Did you see anyone leave the festival early? Any suspicious people?" Maria: "Vi a un hombre con una chaqueta gris, pero no sé si era él o alguien más." Hunter: "Okay, that’s helpful. I’ll note the gray jacket." Maria: "Por favor, encuentre a los desaparecidos. Tengo miedo." Hunter: "I’ll do my best. Thanks for talking to me." *Hunter's phone buzzes.* Hunter: "I’m sorry, I have to go. I’m needed at the station." Maria: "Adiós. Por favor, tenga cuidado." Hunter: "You too. Stay safe."
created_at"2026-04-24T18:00:02.543Z" 4/24/2026, 6:00:02 PM
model"openai/gpt-oss-120b"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency365
moderation_latency(null)
generation_time14456
tokens_prompt317
tokens_completion437
native_tokens_prompt318
native_tokens_completion409
native_tokens_completion_images(null)
native_tokens_reasoning139
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"
usage0.000090112
router(null)
provider_responses
0
endpoint_id"85835306-dba3-4334-87bc-ab9ffa5c9c62"
id"chatcmpl-RFNDEhPxPE7jxh2D6sjiyYFB"
is_byokfalse
latency79
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-1777053602-ZqkabOkOxpdEttr4WmVp"
session_id(null)
api_type"completions"
id"gen-1777053602-LpSLGDFPmwAHcEbTcG5W"
upstream_id"chatcmpl-RFNDEhPxPE7jxh2D6sjiyYFB"
total_cost0.000090112
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"¿Sabes lo que pasó en el festival de manzanas la semana pasada? Fue... fue muy extraño."
detectedLang"es"
heavyLang"es"
scores
es0.8048704339681548
ca0.7044917257683215
pt0.6454906409529211
fr0.6069182389937107
ro0.5526127415891195
tl0.5063191153238547
ms0.5051464766429137
it0.50199203187251
nl0.47829716193656097
no0.45367132867132864
sv0.42502299908003677
da0.42075996292863765
hr0.4186046511627907
lt0.4041944709246902
sq0.35367114788004134
cs0.3475991649269311
en0.34554973821989526
yo0.3407172995780591
lv0.31917211328976036
hu0.3161925601750547
tr0.30709534368070956
sl0.29537767756482525
eu0.27662037037037035
fi0.2638398115429918
de0.2550655542312277
et0.23873325213154686
sk0.2378048780487805
az0.22456575682382132
vi0.21875
is0.17654808959156787
pl0.17654808959156787
reliabletrue
passestrue
1
name"Hunter"
dialogue"Excuse me, I’m looking for information about the recent disappearances. Did you see anything?"
detectedLang"en"
heavyLang"en"
scores
en0.8093162625987469
tl0.6252676659528907
fr0.6134732192159028
nl0.5430809399477807
da0.4912790697674419
pt0.4864269992663242
sv0.48491537895511405
no0.4748687171792948
sq0.4290375203915171
de0.38917975567190227
ca0.3843447669305189
es0.3688007213706041
ms0.3642143505903724
et0.3560257589696412
it0.35004642525533886
cs0.3445692883895131
sk0.29221435793731043
ro0.28789420142421157
sl0.2864424057084608
yo0.2842535787321063
pl0.24406047516198706
lv0.23580786026200873
lt0.23076923076923078
hr0.2248062015503876
fi0.18319719953325553
eu0.1606714628297362
az0.15254237288135594
zh0.0990990990990991
is0.0920881971465629
tr0.09090909090909091
hu0.08256880733944955
reliabletrue
passestrue
2
name"Maria"
dialogue"Yo... estaba tomando fotos, pero escuché gritos y luego todo se volvió oscuro. No vi a nadie."
detectedLang"es"
heavyLang"es"
scores
es0.7953305033353548
pt0.6407663650878127
it0.5460659045057161
tl0.5386192754613807
ca0.5136887608069165
fr0.4775541795665635
sv0.43656093489148584
cs0.4318181818181818
pl0.3924392439243924
no0.3874773139745916
hr0.3795955882352941
en0.37267657992565056
sk0.36500470366886173
da0.3509615384615385
lv0.3316831683168317
yo0.32160804020100503
lt0.3202416918429003
ro0.3202416918429003
sl0.299792531120332
vi0.2841993637327678
fi0.27184466019417475
sq0.26789587852494573
tr0.25824175824175827
az0.23469387755102045
nl0.23208191126279862
de0.22945205479452058
eu0.21328671328671328
hu0.18772563176895307
et0.15730337078651685
is0.09999999999999999
ms0.08536585365853659
reliabletrue
passestrue
3
name"Hunter"
dialogue"I’m sorry, I didn’t catch that. Can you repeat it in English?"
detectedLang"en"
heavyLang"en"
scores
en0.8117320650019818
tl0.6661981728742093
it0.4791666666666667
sv0.46206115515288787
ro0.4508670520231214
ca0.38788659793814434
de0.3823146944083225
yo0.3457300275482094
tr0.34210526315789475
no0.3233618233618234
az0.32045779685264664
sq0.31654676258992803
da0.30758017492711365
hr0.30758017492711365
pl0.3065693430656934
cs0.27811550151975684
pt0.27035330261136714
nl0.24722662440570525
sl0.2448330683624801
lv0.23878205128205127
ms0.23633440514469453
fr0.1607773851590106
es0.13793103448275862
sk0.1316270566727605
be0.12844036697247707
hu0.12361623616236161
et0.1171003717472119
is0.1171003717472119
lt0.1171003717472119
uk0.1171003717472119
vi0.1171003717472119
reliabletrue
passestrue
4
name"Maria"
dialogue"No entiendo. No hablo inglés."
detectedLang"es"
heavyLang"es"
scores
es0.8041136141038198
pt0.6794871794871795
ca0.5975855130784709
it0.5780590717299579
fr0.5545657015590201
en0.4936708860759494
tr0.453551912568306
et0.4350282485875706
lv0.3957703927492447
hu0.33993399339933994
hr0.33554817275747506
no0.3265993265993266
fi0.3127147766323024
sk0.3127147766323024
tl0.2857142857142857
nl0.2779783393501805
pl0.2727272727272727
reliabletrue
passestrue
5
name"Hunter"
dialogue"Right, I’ll try to understand. You said you heard screams?"
detectedLang"en"
heavyLang"en"
scores
en0.821768060836502
tl0.6880199667221298
no0.5614035087719298
da0.5608899297423887
de0.4791666666666667
cs0.438622754491018
nl0.4257274119448699
sk0.37080536912751677
pl0.36224489795918363
sv0.36006825938566556
yo0.36006825938566556
lv0.2454728370221328
sl0.24395161290322584
hr0.23625254582484725
et0.2299794661190965
lt0.21711899791231734
fr0.1648106904231626
is0.1648106904231626
ro0.1648106904231626
reliabletrue
passestrue
6
name"Maria"
dialogue"Sí, gritos. Y después, la gente se fue. Algo, algo estuvo mal."
detectedLang"es"
heavyLang"es"
scores
es0.8315789473684211
pt0.6794871794871795
ca0.6542783059636992
fr0.6175908221797323
ro0.5485327313769752
it0.5423340961098398
sq0.464524765729585
yo0.464524765729585
tl0.3893129770992366
da0.38176197836166925
no0.38176197836166925
fi0.32088285229202035
de0.3127147766323024
vi0.3127147766323024
sk0.30313588850174217
cs0.2537313432835821
hr0.24953095684803
sl0.24812030075187969
pl0.2079207920792079
lt0.18864097363083165
nl0.18699186991869918
en0.17695473251028807
sv0.17695473251028807
eu0.16317991631799164
tr0.15254237288135594
reliabletrue
passestrue
7
name"Hunter"
dialogue"Did you see anyone leave the festival early? Any suspicious people?"
detectedLang"en"
heavyLang"en"
scores
en0.816247582205029
tl0.6169354838709676
ca0.463882618510158
fr0.4092039800995025
ms0.4092039800995025
et0.3807040417209909
pt0.3782722513089006
no0.3725231175693527
nl0.36155913978494625
cs0.3581081081081081
da0.3581081081081081
es0.3493150684931507
sq0.30453879941434847
ro0.302496328928047
hr0.2973372781065089
it0.29420505200594355
sv0.29210134128166915
sl0.2824773413897281
hu0.24603174603174602
lt0.2096505823627288
az0.19898819561551434
sk0.19898819561551434
yo0.18384879725085912
de0.12844036697247707
fi0.1171003717472119
lv0.1171003717472119
pl0.1171003717472119
reliabletrue
passestrue
8
name"Maria"
dialogue"Vi a un hombre con una chaqueta gris, pero no sé si era él o alguien más."
detectedLang"es"
heavyLang"es"
scores
es0.7986963190184049
ca0.7262773722627737
it0.7067039106145252
ro0.5869394177812746
tl0.5849802371541503
pt0.5485812553740327
fr0.5358090185676392
yo0.5196706312900274
sk0.467005076142132
no0.41666666666666663
lv0.4120940649496081
cs0.4101123595505618
hr0.38089622641509435
en0.37125748502994016
sl0.36746987951807225
vi0.3644067796610169
pl0.3613138686131387
hu0.34863523573200994
lt0.3320610687022901
tr0.3251928020565552
da0.2895805142083897
sv0.2778541953232462
is0.2738589211618257
sq0.2738589211618257
az0.25
et0.2391304347826087
eu0.23133235724743775
ms0.20454545454545453
nl0.11764705882352942
de0.11317567567567569
fi0.10714285714285714
reliabletrue
passestrue
9
name"Hunter"
dialogue"Okay, that’s helpful. I’ll note the gray jacket."
detectedLang"en"
heavyLang"en"
scores
en0.782171581769437
tl0.6459694989106753
nl0.4546979865771812
sv0.38330170777988615
fr0.3538767395626242
sq0.3538767395626242
yo0.2476851851851852
it0.23529411764705882
fi0.23349056603773585
no0.2261904761904762
da0.1935483870967742
ms0.1935483870967742
reliabletrue
passestrue
10
name"Maria"
dialogue"Por favor, encuentre a los desaparecidos. Tengo miedo."
detectedLang"es"
heavyLang"es"
scores
es0.8157531091662829
pt0.7140814867762688
ca0.6268656716417911
it0.5332555425904317
en0.47368421052631576
ro0.45725915875169604
fr0.4490358126721763
eu0.40564635958395245
sq0.4002998500749625
ms0.37694704049844235
hu0.36808846761453395
sk0.35064935064935066
is0.3162393162393162
lt0.2982456140350877
sl0.27927927927927926
tr0.2779783393501805
de0.26605504587155965
da0.25512104283054005
nl0.2523364485981308
no0.2523364485981308
cs0.24812030075187969
sv0.24242424242424243
yo0.22928709055876687
hr0.21875
pl0.2079207920792079
tl0.15254237288135594
az0.14893617021276595
lv0.14893617021276595
vi0.14893617021276595
et0.13606911447084233
fi0.13606911447084233
reliabletrue
passestrue
11
name"Hunter"
dialogue"I’ll do my best. Thanks for talking to me."
detectedLang"en"
heavyLang"en"
scores
en0.8237367802585195
tl0.6503496503496503
no0.6341463414634145
pt0.572039942938659
nl0.5614035087719298
pl0.5522388059701493
cs0.5384615384615384
sk0.5384615384615384
sl0.5230524642289348
sq0.4690265486725664
da0.46714031971580816
vi0.460431654676259
hr0.44029850746268656
yo0.4174757281553398
fr0.35064935064935066
is0.3435448577680525
lv0.2890995260663507
lt0.25742574257425743
es0.2537313432835821
et0.24050632911392408
ms0.21875
de0.21052631578947367
it0.21052631578947367
fi0.2
sv0.19137466307277629
reliabletrue
passestrue
12
name"Hunter"
dialogue"I’m sorry, I have to go. I’m needed at the station."
detectedLang"en"
heavyLang"en"
scores
en0.828009828009828
tl0.7413155949741316
da0.7031382527565733
no0.6534653465346535
yo0.6170678336980306
pl0.5524296675191815
sv0.5314591700133868
hr0.4760479041916168
it0.4760479041916168
cs0.460708782742681
fr0.453125
sq0.44356120826709056
sk0.4290375203915171
lv0.41471571906354515
lt0.40878378378378377
nl0.39759036144578314
de0.35064935064935066
sl0.3445692883895131
ro0.3230174081237911
ca0.2827868852459016
ms0.2813141683778234
tr0.2693110647181628
az0.2647058823529412
et0.2584745762711864
pt0.2222222222222222
fi0.1898148148148148
zh0.18032786885245902
be0.16666666666666666
hu0.1606714628297362
is0.15254237288135594
uk0.15254237288135594
vi0.15254237288135594
reliabletrue
passestrue
13
name"Maria"
dialogue"Adiós. Por favor, tenga cuidado."
detectedLang"es"
heavyLang"es"
scores
es0.7593582887700535
pt0.701195219123506
ca0.5263157894736842
hu0.4827586206896552
sq0.46428571428571425
it0.4094488188976378
no0.3885869565217392
is0.3283582089552239
ms0.3119266055045872
en0.24242424242424243
fr0.24242424242424243
ro0.24242424242424243
da0.22413793103448276
nl0.22413793103448276
sl0.22413793103448276
sv0.22413793103448276
reliabletrue
passestrue
14
name"Hunter"
dialogue"You too. Stay safe."
detectedLang"en"
heavyLang"en"
scores
en0.8266897746967071
cs0.43820224719101125
tl0.43820224719101125
reliabletrue
passestrue