Run: 2026-02-16-01KHK3A7RYBCWGNJB230AYYMSP

Run Details

Model:
Qwen 3.5 397B A17B
Test:
Language Writing
Scenario:
Character dialogue (Spanish) in a story
Duration:
2m 15s
Cost:
$0.015491
Provider:
Alibaba

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: "¿Quién es usted? ¿Qué quiere?" [Who are you? What do you want?] Hunter: "Detective Hunter. Alborn Police. I need to ask you a few questions." Maria: (Clutching her camera to her chest, eyes wide) "No hablo inglés. No entiendo." [I don't speak English. I don't understand.] Hunter: (Points to her camera, then to the orchard outside) "Did you take pictures? Near the trees? Yesterday?" Maria: (Shaking her head vigorously, voice trembling) "Sí, pero... vi algo. Algo malo." [Yes, but... I saw something. Something bad.] Hunter: (Frowns, leaning in slightly) "Bad? You saw someone? A person?" Maria: (Looking down at the table, hands shaking) "En el bosque. Estaba oscuro. Tenía mucho miedo." [In the woods. It was dark. I was very scared.] Hunter: (Sighs, rubbing the back of his neck) "Ma'am, I can't help you if I don't know what you're saying. Do you have anyone here who speaks English?" Maria: (Tears welling up, pushing the camera away slightly) "Por favor, déjeme sola. No quiero problemas." [Please, leave me alone. I don't want trouble.] Hunter: (Stares at her for a moment, realizing the barrier is too high) "Okay. Okay, stay put. Don't go anywhere." Maria: (Whispering to herself) "Dios mío... ¿qué hago?" [My God... what do I do?] Hunter: (Phone buzzes on the table; he glances at the screen) " Damn it. Hold on." (He stands up abruptly) "I have to take this. I'll be back." Maria: (Watches him walk away, hugging her camera tightly) "Por favor, que se vaya para siempre." [Please, let him go away forever.]
created_at"2026-02-16T11:30:18.58795+00:00" 2/16/2026, 11:30:18 AM
model"qwen/qwen3.5-397b-a17b-20260216"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency827
moderation_latency(null)
generation_time134950
tokens_prompt317
tokens_completion4577
native_tokens_prompt295
native_tokens_completion4254
native_tokens_completion_images(null)
native_tokens_reasoning3817
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
usage0.0154914
router(null)
provider_responses
0
id"chatcmpl-86addcbc-d95a-9de5-ba02-bc82024c72f7"
status200
is_byokfalse
latency827
endpoint_id"180484a2-e24b-495a-ba41-b34b680d5a9f"
provider_name"Alibaba"
model_permaslug"qwen/qwen3.5-397b-a17b-20260216"
api_type"completions"
id"gen-1771241283-ZCmWn7L8aZESCSsNMJyb"
upstream_id"chatcmpl-86addcbc-d95a-9de5-ba02-bc82024c72f7"
total_cost0.0154914
cache_discount(null)
upstream_inference_cost0
provider_name"Alibaba"

Evaluation details

Result Evaluator Details Meta Data
100.00% Parse dialogue n/a
dialogue
0
name"Maria"
dialogue"¿Quién es usted? ¿Qué quiere?"
detectedLang"es"
heavyLang"es"
scores
es0.8319327731092437
de0.5359628770301624
da0.4520547945205479
no0.4428969359331476
ca0.42363112391930835
eu0.3993993993993994
lv0.375
en0.3548387096774194
it0.34210526315789475
hu0.33774834437086093
ro0.3150684931506849
lt0.3127147766323024
nl0.2647058823529412
sk0.2647058823529412
reliabletrue
passestrue
1
name"Hunter"
dialogue"Detective Hunter. Alborn Police. I need to ask you a few questions."
detectedLang"en"
heavyLang"en"
scores
en0.7983870967741935
fr0.6525237746891002
tl0.6491875923190545
it0.6471025260029718
ca0.6048252911813644
ro0.6011754827875735
cs0.5957446808510638
pt0.565018315018315
hr0.5589600742804085
da0.5458891013384322
no0.5458891013384322
sl0.5123203285420944
sk0.5082815734989649
es0.49252136752136755
pl0.488697524219591
sq0.4808743169398907
sv0.47339246119733924
nl0.45776255707762553
et0.42702050663449936
lv0.42002442002442
yo0.4193154034229829
lt0.41430332922318125
de0.40176322418136023
hu0.38551099611901685
tr0.36918990703851257
az0.30453879941434847
ms0.3004418262150221
eu0.2566510172143975
fi0.23633440514469453
is0.22512234910277326
vi0.21875
be0.12844036697247707
uk0.1171003717472119
reliabletrue
passestrue
2
name"Maria"
dialogue"No hablo inglés. No entiendo."
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
3
name"Hunter"
dialogue"Did you take pictures? Near the trees? Yesterday?"
detectedLang"en"
heavyLang"en"
scores
en0.8080330773774365
tl0.5590230664857531
nl0.47580645161290325
ca0.453781512605042
fr0.453781512605042
et0.37858508604206503
no0.3394308943089431
ro0.3186582809224318
da0.3157894736842105
sv0.3157894736842105
yo0.2476851851851852
lv0.2034313725490196
cs0.1935483870967742
ms0.1935483870967742
sl0.1935483870967742
sq0.1935483870967742
de0.181360201511335
reliabletrue
passestrue
4
name"Maria"
dialogue"Sí, pero... vi algo. Algo malo."
detectedLang"es"
heavyLang"es"
scores
es0.7553816046966731
tl0.5644599303135889
yo0.5421245421245421
da0.5318352059925093
sv0.5265151515151516
no0.50199203187251
pt0.47257383966244726
vi0.4444444444444444
ca0.44196428571428575
sl0.4292237442922375
it0.423963133640553
hr0.4131455399061033
sk0.4131455399061033
reliabletrue
passestrue
5
name"Hunter"
dialogue"Bad? You saw someone? A person?"
detectedLang"en"
heavyLang"en"
scores
en0.8084291187739464
pt0.6402877697841727
de0.6101364522417154
es0.5983935742971888
tl0.5901639344262295
cs0.5735607675906184
ms0.5565410199556541
sv0.5348837209302325
no0.5327102803738317
ca0.5305164319248826
ro0.5271867612293144
da0.5238095238095238
sq0.5238095238095238
hu0.522673031026253
it0.5157384987893463
is0.511002444987775
fr0.5012468827930174
sk0.48586118251928023
hr0.4609164420485175
pl0.45054945054945056
lt0.4350282485875706
lv0.42028985507246375
nl0.42028985507246375
tr0.4186046511627907
az0.39209726443769
et0.37888198757763975
yo0.3730407523510972
sl0.3103448275862069
eu0.25925925925925924
vi0.25925925925925924
fi0.23954372623574144
reliabletrue
passestrue
6
name"Maria"
dialogue"En el bosque. Estaba oscuro. Tenía mucho miedo."
detectedLang"es"
heavyLang"es"
scores
es0.796156086196855
ca0.5673671199011124
fr0.4479495268138801
eu0.34944237918215615
nl0.30417495029821073
da0.29718875502008035
sv0.29718875502008035
no0.2842535787321063
pt0.2813141683778234
is0.2768595041322314
hu0.2631578947368421
ro0.24892703862660948
tr0.2391304347826087
it0.23076923076923078
sk0.2222222222222222
en0.2081447963800905
fi0.1935483870967742
sl0.1764705882352941
reliabletrue
passestrue
7
name"Hunter"
dialogue"Ma'am, I can't help you if I don't know what you're saying. Do you have anyone here who speaks English?"
detectedLang"en"
heavyLang"en"
scores
en0.8169014084507041
tl0.421193232413179
da0.3551587301587301
sq0.35064935064935066
hr0.3374108053007136
cs0.3271221532091097
sv0.3229166666666667
pl0.2927094668117519
no0.2588369441277081
sk0.2388758782201405
et0.23708920187793428
vi0.2111650485436893
tr0.2073170731707317
yo0.20245398773006135
ro0.19950738916256158
pt0.1935483870967742
ca0.1751269035532995
sl0.15584415584415584
it0.15032679738562094
de0.09972299168975068
ms0.09972299168975068
be0.09722222222222222
hu0.09344490934449094
az0.08835904628330996
is0.08835904628330996
lt0.08835904628330996
lv0.08835904628330996
uk0.08835904628330996
reliabletrue
passestrue
8
name"Maria"
dialogue"Por favor, déjeme sola. No quiero problemas."
detectedLang"es"
heavyLang"es"
scores
es0.7586484312148029
pt0.6916752312435765
it0.6235884567126726
ca0.5873452544704264
hr0.5398773006134969
fr0.5297805642633229
sq0.52
sk0.5121951219512195
en0.511400651465798
pl0.5008319467554077
no0.49324324324324326
lv0.4915254237288135
sl0.471830985915493
cs0.4392523364485981
ro0.4360902255639098
tl0.4307400379506641
lt0.4174757281553398
tr0.4163424124513619
da0.40828402366863903
nl0.40357852882703776
sv0.39999999999999997
et0.3576017130620985
az0.33774834437086093
de0.3103448275862069
ms0.2
hu0.17355371900826447
reliabletrue
passestrue
9
name"Hunter"
dialogue"Okay. Okay, stay put. Don't go anywhere."
detectedLang"en"
heavyLang"en"
scores
en0.7783251231527093
tl0.5562130177514794
hr0.3571428571428572
pl0.32432432432432434
de0.25742574257425743
sq0.25742574257425743
yo0.2549668874172185
reliabletrue
passestrue
10
name"Maria"
dialogue"Dios mío... ¿qué hago?"
detectedLang"es"
heavyLang"es"
scores
es0.7109826589595376
reliabletrue
passestrue
11
name"Hunter"
dialogue"I have to take this. I'll be back."
detectedLang"en"
heavyLang"en"
scores
en0.8312236286919831
tl0.6879875195007801
da0.6610169491525424
yo0.6254681647940075
lt0.5824634655532359
pl0.5661605206073753
hr0.5604395604395604
no0.5594713656387665
cs0.5412844036697247
sk0.504950495049505
sl0.49874686716791977
lv0.4805194805194805
hu0.4791666666666667
ca0.40828402366863903
sv0.40828402366863903
sq0.40119760479041916
it0.36507936507936506
ro0.3103448275862069
be0.25925925925925924
tr0.25925925925925924
az0.23954372623574144
et0.23954372623574144
is0.23954372623574144
uk0.23954372623574144
vi0.23954372623574144
reliabletrue
passestrue
12
name"Maria"
dialogue"Por favor, que se vaya para siempre."
detectedLang"es"
heavyLang"es"
scores
es0.8319641523525019
pt0.7903075489282386
ca0.6995994659546061
sq0.6489859594383774
fr0.5945945945945946
it0.5596868884540117
tl0.5011086474501109
sl0.4668246445497631
ro0.460431654676259
da0.4109947643979057
sv0.4015957446808511
no0.3835616438356164
cs0.3767313019390581
hr0.3715083798882682
yo0.32228915662650603
fi0.3119266055045872
ms0.296875
tr0.27184466019417475
en0.24242424242424243
nl0.22413793103448276
reliabletrue
passestrue