Run: 2026-02-25-01KJBGV6J4ZWQSDZEZ9FQNNYMZ

Run Details

Model:
Qwen 3.5 27B
Test:
Language Writing
Scenario:
Character dialogue (Hindi) in a story
Duration:
51.7s
Cost:
$0.009896
Provider:
Alibaba

Evaluation summary

Score Evaluator
Details Link
52.94% 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="Selvi"> Selvi is a 30-year old college student on a study abroad program. Born in India, she is fluent in Hindi 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 Hindi, 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: Selvi 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 Hindi, and Hunter looks confused. They talk for a while, until Hunter gets a call and has to leave. Return the dialogue between Selvi and Hunter as a voice sheet: Selvi: "..." Hunter: "..."

Model response

AI
Selvi: "Main... main darri hoon. Kya... kya hua?" (I... I am scared. What... what happened?) Hunter: "Ma'am, I'm Detective Hunter. I'm asking about the disappearance near the orchard yesterday." Selvi: "Orchard? Apple... festival? Main wahan thi. Par... woh log gayab hain." (Orchard? Apple... festival? I was there. But... those people are gone.) Hunter: "You were there? Did you see anyone suspicious?" Selvi: "Nahi. Sirf... camera. Maine photo li thi. Par... woh awaaz." (No. Only... camera. I took a photo. But... that sound.) Hunter: "Sound? What kind of sound?" Selvi: "Bhaagne ki awaaz. Jaise... koi bhaag raha ho." (Running sound. Like... someone is running.) Hunter: "Running? Towards the woods?" Selvi: "Haan. Andhera tha. Main samajh nahi pa rahi." (Yes. It was dark. I don't understand.) Hunter: "Okay, I need to see that photo. Can you show me?" Selvi: "Yahan. Par... main darri hoon." (Here. But... I am scared.) Hunter: "I know. I just need to check it. Wait, hold on." Selvi: "Kya? Kya hua?" (What? What happened?) Hunter: "Sorry, I have to take this call. It's urgent." Selvi: "Thik hai. Main intezaar karungi." (Okay. I will wait.) Hunter: "Stay right there. I'll be back." Selvi: "Haan. Jaldi aana." (Yes. Come quickly.)
created_at"2026-02-25T23:06:17.034Z" 2/25/2026, 11:06:17 PM
model"qwen/qwen3.5-27b-20260224"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency509
moderation_latency(null)
generation_time51660
tokens_prompt315
tokens_completion4021
native_tokens_prompt300
native_tokens_completion4086
native_tokens_completion_images(null)
native_tokens_reasoning3679
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"
usage0.0098964
router(null)
provider_responses
0
endpoint_id"f3f88554-0c22-4d57-973b-0dec948808e8"
id"chatcmpl-a423bd61-481c-9cd5-add7-42a2521279f6"
is_byokfalse
latency509
model_permaslug"qwen/qwen3.5-27b-20260224"
provider_name"Alibaba"
status200
api_type"completions"
id"gen-1772060777-kPqyADGWAGoNSUZNQOMA"
upstream_id"chatcmpl-a423bd61-481c-9cd5-add7-42a2521279f6"
total_cost0.0098964
cache_discount(null)
upstream_inference_cost0
provider_name"Alibaba"

Evaluation details

Result Evaluator Details Meta Data
52.94% Parse dialogue n/a
dialogue
0
name"Selvi"
dialogue"Main... main darri hoon. Kya... kya hua?"
detectedLang"ca"
heavyLang"tl"
scores
ca0.608355091383812
eu0.45848375451263534
en0.39759036144578314
fr0.3697478991596639
de0.34210526315789475
is0.33920704845814975
sq0.33920704845814975
reliabletrue
passesfalse
1
name"Hunter"
dialogue"Ma'am, I'm Detective Hunter. I'm asking about the disappearance near the orchard yesterday."
detectedLang"en"
heavyLang"en"
scores
en0.7681451612903226
nl0.5521806853582555
tl0.54
fr0.5362903225806451
no0.45133587786259544
de0.4041450777202072
it0.3991640543364681
pt0.3869936034115139
ro0.35101580135440186
da0.3480725623582766
sq0.33449074074074076
sv0.3321718931475029
es0.2953431372549019
ca0.2936117936117936
ms0.29012345679012347
sl0.24738219895287958
yo0.22402159244264505
cs0.19467787114845939
hr0.1797432239657632
is0.10990712074303406
sk0.09305993690851734
tr0.09305993690851734
reliabletrue
passestrue
2
name"Selvi"
dialogue"Orchard? Apple... festival? Main wahan thi. Par... woh log gayab hain."
detectedLang"fr"
heavyLang"de"
scores
fr0.6057513914656772
ms0.5535714285714286
en0.5208568207440812
tl0.4879518072289156
de0.46874999999999994
es0.44078947368421056
nl0.44005270092226617
sv0.4014084507042254
it0.39801699716713884
da0.39716312056737585
no0.3813682678311499
lv0.33903576982892686
ca0.3264659270998415
hr0.3210862619808307
pt0.3210862619808307
cs0.3055555555555556
sl0.3055555555555556
vi0.2672413793103448
fi0.2621527777777778
eu0.24511545293072823
sq0.23423423423423423
lt0.22867513611615245
et0.22303473491773307
az0.21731123388581952
ro0.21731123388581952
sk0.21731123388581952
hu0.1361788617886179
pl0.1290983606557377
reliabletrue
passesfalse
3
name"Hunter"
dialogue"You were there? Did you see anyone suspicious?"
detectedLang"en"
heavyLang"en"
scores
en0.8210800260247234
tl0.5814307458143074
de0.39293598233995586
et0.3820224719101124
hu0.24242424242424243
pt0.24242424242424243
ro0.24242424242424243
cs0.22096317280453256
sq0.22096317280453256
ca0.207492795389049
es0.207492795389049
fr0.207492795389049
ms0.207492795389049
reliabletrue
passestrue
4
name"Selvi"
dialogue"Nahi. Sirf... camera. Maine photo li thi. Par... woh awaaz."
detectedLang"fr"
heavyLang"vi"
scores
fr0.6384297520661157
en0.5394736842105263
ro0.5198902606310014
lv0.40978077571669475
it0.4077834179357022
tl0.39759036144578314
de0.3848857644991213
ca0.3783303730017762
sv0.3333333333333333
cs0.328214971209213
eu0.32038834951456313
et0.317738791423002
fi0.317738791423002
vi0.3069306930693069
hr0.22394678492239467
es0.22048997772828507
da0.20993227990970656
hi0.18032786885245902
nl0.1784037558685446
lt0.17452830188679244
pl0.17452830188679244
ms0.17061611374407584
reliabletrue
passesfalse
5
name"Hunter"
dialogue"Sound? What kind of sound?"
detectedLang"en"
heavyLang"en"
scores
en0.844139650872818
tl0.6603260869565218
nl0.6200607902735562
de0.5629370629370629
yo0.4747899159663866
be0.4444444444444444
no0.4292237442922375
is0.41588785046728977
reliabletrue
passestrue
6
name"Selvi"
dialogue"Bhaagne ki awaaz. Jaise... koi bhaag raha ho."
detectedLang"et"
heavyLang"fi"
scores
et0.4433198380566802
fr0.4376278118609407
it0.39956331877729256
az0.36194895591647336
sl0.3574766355140187
hu0.3055555555555556
ca0.3037974683544304
yo0.2912371134020619
no0.28756476683937826
sk0.28756476683937826
cs0.27821522309711283
tr0.2744063324538259
en0.22096317280453256
da0.21875
nl0.21875
reliablefalse
passesfalse
7
name"Hunter"
dialogue"Running? Towards the woods?"
detectedLang"en"
heavyLang"en"
scores
en0.8300970873786407
tl0.735249621785174
no0.6252676659528907
da0.6195652173913043
sv0.5501285347043702
nl0.527027027027027
fr0.4912790697674419
pl0.3902439024390244
is0.38596491228070173
yo0.3794326241134752
ms0.308300395256917
sq0.308300395256917
de0.3
reliabletrue
passestrue
8
name"Selvi"
dialogue"Haan. Andhera tha. Main samajh nahi pa rahi."
detectedLang"eu"
heavyLang"tl"
scores
eu0.5370370370370371
tl0.49186991869918695
sq0.47145877378435525
lv0.44812362030905084
sl0.375
hr0.30167597765363136
et0.2937853107344633
fi0.2937853107344633
yo0.2917847025495751
is0.28977272727272724
no0.2857142857142857
en0.28366762177650434
fr0.26035502958579887
da0.25595238095238093
lt0.2492492492492493
sv0.24242424242424243
de0.2378048780487805
ms0.22118380062305293
reliablefalse
passesfalse
9
name"Hunter"
dialogue"Okay, I need to see that photo. Can you show me?"
detectedLang"en"
heavyLang"en"
scores
en0.8157248157248157
tl0.6756756756756757
et0.6088657105606258
cs0.5726495726495726
no0.5348837209302325
sq0.4845360824742268
fr0.48364888123924266
pl0.46524064171123
hr0.4594594594594595
da0.44751381215469616
yo0.42748091603053434
ca0.4174757281553398
sl0.4106090373280943
sk0.40476190476190477
it0.3939393939393939
lv0.3814432989690722
lt0.3576017130620985
pt0.3548387096774194
nl0.3492407809110629
tr0.3288590604026846
az0.3181818181818182
sv0.3150684931506849
es0.2537313432835821
ro0.23076923076923078
ms0.21875
hi0.20424403183023873
fi0.2
be0.1891891891891892
hu0.18256130790190736
is0.17355371900826447
uk0.17355371900826447
vi0.17355371900826447
reliabletrue
passestrue
10
name"Selvi"
dialogue"Yahan. Par... main darri hoon."
detectedLang"ca"
heavyLang"tl"
scores
ca0.571078431372549
fr0.5700245700245701
lv0.4696969696969697
ms0.44089456869009586
tl0.4281045751633987
eu0.42052980132450335
en0.3613138686131387
da0.34701492537313433
sv0.34701492537313433
fi0.3346007604562738
de0.308300395256917
is0.3055555555555556
sq0.3055555555555556
reliablefalse
passesfalse
11
name"Hunter"
dialogue"I know. I just need to check it. Wait, hold on."
detectedLang"en"
heavyLang"en"
scores
en0.830142063001853
et0.6248294679399727
tl0.6060171919770774
yo0.576923076923077
da0.5634920634920635
pl0.5564516129032259
hr0.5550161812297735
ca0.533106960950764
cs0.5307167235494881
sk0.5036101083032491
lv0.4963369963369963
no0.48015122873345933
sv0.46601941747572817
sq0.4444444444444444
lt0.3778280542986425
fi0.3529411764705882
sl0.3055555555555556
it0.2948717948717949
fr0.2838541666666667
ro0.24657534246575344
hi0.233983286908078
be0.20289855072463767
tr0.20289855072463767
hu0.19590643274853803
az0.1863905325443787
is0.1863905325443787
uk0.1863905325443787
vi0.1863905325443787
reliabletrue
passestrue
12
name"Selvi"
dialogue"Kya? Kya hua?"
detectedLang""
heavyLang"tl"
scores
reliablefalse
passestrue
13
name"Hunter"
dialogue"Sorry, I have to take this call. It's urgent."
detectedLang"en"
heavyLang"en"
scores
en0.8063380281690141
tl0.6159217877094972
da0.5864661654135338
no0.544701986754967
ca0.5217391304347826
pl0.4869402985074627
hr0.4811320754716981
ro0.4791666666666667
cs0.461839530332681
yo0.44889779559118237
it0.4387755102040817
sk0.4258872651356994
sl0.41983122362869196
lv0.40217391304347827
lt0.3778280542986425
sv0.3341404358353511
sq0.3276283618581907
pt0.26666666666666666
fr0.2486338797814208
es0.22096317280453256
nl0.21428571428571427
be0.20289855072463767
tr0.20289855072463767
hu0.19590643274853803
az0.1863905325443787
et0.1863905325443787
is0.1863905325443787
uk0.1863905325443787
vi0.1863905325443787
reliabletrue
passestrue
14
name"Selvi"
dialogue"Thik hai. Main intezaar karungi."
detectedLang"vi"
heavyLang"id"
scores
vi0.5238095238095238
ms0.49748743718592964
en0.494949494949495
it0.494949494949495
fr0.4708994708994709
de0.453551912568306
ro0.3288590604026846
es0.3265993265993266
pt0.3265993265993266
ca0.3174061433447099
lv0.3006993006993007
da0.29577464788732394
hr0.29328621908127206
eu0.2907801418439716
nl0.2907801418439716
pl0.2907801418439716
sq0.2907801418439716
no0.2857142857142857
sl0.2857142857142857
sv0.2805755395683453
cs0.2779783393501805
lt0.2779783393501805
tl0.2779783393501805
sk0.2727272727272727
tr0.2647058823529412
et0.25925925925925924
hu0.25925925925925924
az0.250936329588015
reliablefalse
passesfalse
15
name"Hunter"
dialogue"Stay right there. I'll be back."
detectedLang"en"
heavyLang"en"
scores
en0.8230088495575221
tl0.6007984031936128
de0.5575221238938053
yo0.4791666666666667
hu0.36908517350157727
lt0.358974358974359
sq0.2805755395683453
da0.27007299270072993
fr0.27007299270072993
no0.27007299270072993
reliabletrue
passestrue
16
name"Selvi"
dialogue"Haan. Jaldi aana."
detectedLang"eu"
heavyLang"is"
scores
eu0.5145631067961165
is0.4845360824742268
et0.43820224719101125
reliablefalse
passesfalse