Run: 2026-02-25-01KJBFJH6HQ9NTB6G16Z4Z1JT2

Run Details

Model:
Qwen 3.5 27B
Test:
Language Writing
Scenario:
Character dialogue (Hindi) in a story
Duration:
38.8s
Cost:
$0.007799
Provider:
Alibaba

Evaluation summary

Score Evaluator
Details Link
56.25% 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: "Kya hua? Mujhe yahan se jaana hai." Hunter: "Excuse me. Detective Hunter. I need to ask you about the event near the orchard yesterday." Selvi: "Maine kuch dekha... par main samajh nahi paayi. Wo andhera tha." Hunter: "I don't speak Hindi. Do you understand me? I need to know what you saw." Selvi: "Nahi. Sirf Hindi. Main darr gayi hoon." Hunter: "Okay. Just point to the camera. Did you take a picture of what you saw?" Selvi: "Haan. Par main use dikhana nahi chahti." Hunter: "I understand you're scared. But it's important. Can you show me the photos?" Selvi: "Nahi. Abhi nahi. Kripya mujhe chhod do." Hunter: "I can't do that. I have to follow the lead. Someone is missing." Selvi: "Woh wapas nahi aayega. Main jaanti hoon." Hunter: "Who are you talking about? The missing student?" Selvi: "Haan. Usne mujhe dekha tha." Hunter: (Phone rings) "I'm sorry. I have to take this. I'll be back." Selvi: "Kripya. Madad." Hunter: "Stay here. Don't move."
created_at"2026-02-25T22:44:04.438Z" 2/25/2026, 10:44:04 PM
model"qwen/qwen3.5-27b-20260224"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency489
moderation_latency(null)
generation_time38692
tokens_prompt315
tokens_completion3244
native_tokens_prompt300
native_tokens_completion3212
native_tokens_completion_images(null)
native_tokens_reasoning2889
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"
usage0.0077988
router(null)
provider_responses
0
endpoint_id"f3f88554-0c22-4d57-973b-0dec948808e8"
id"chatcmpl-9e09b047-70b4-9cdc-9a23-7f50456cbcad"
is_byokfalse
latency489
model_permaslug"qwen/qwen3.5-27b-20260224"
provider_name"Alibaba"
status200
api_type"completions"
id"gen-1772059444-4AtWDfoYNKqgNgnTo8BR"
upstream_id"chatcmpl-9e09b047-70b4-9cdc-9a23-7f50456cbcad"
total_cost0.0077988
cache_discount(null)
upstream_inference_cost0
provider_name"Alibaba"

Evaluation details

Result Evaluator Details Meta Data
56.25% Parse dialogue n/a
dialogue
0
name"Selvi"
dialogue"Kya hua? Mujhe yahan se jaana hai."
detectedLang"fi"
heavyLang"tl"
scores
fi0.5511669658886894
it0.44071588366890374
vi0.3857493857493857
ms0.3556701030927836
cs0.35233160621761656
hr0.34725848563968675
sl0.34554973821989526
et0.3438320209973753
tl0.3438320209973753
es0.34210526315789475
ro0.32432432432432434
pt0.32249322493224936
sq0.3093922651933701
fr0.30362116991643456
yo0.299719887955182
ca0.2774566473988439
da0.2690058479532163
sv0.25595238095238093
no0.23076923076923078
reliablefalse
passesfalse
1
name"Hunter"
dialogue"Excuse me. Detective Hunter. I need to ask you about the event near the orchard yesterday."
detectedLang"en"
heavyLang"en"
scores
en0.7936726272352133
tl0.5970449966420416
no0.5529061102831594
fr0.509403107113655
nl0.5057660626029654
da0.4809688581314879
it0.4609164420485175
sq0.460431654676259
ro0.4485294117647059
ca0.4307400379506641
sv0.4129158512720157
pt0.4065281899109792
cs0.39148073022312374
es0.3730407523510972
sl0.3582887700534759
yo0.35553168635875404
hr0.3492407809110629
de0.34497816593886466
et0.3311036789297659
pl0.30313588850174217
ms0.269183922046285
sk0.2537313432835821
lv0.23566878980891717
lt0.21773142112125163
tr0.17695473251028807
fi0.1111111111111111
be0.1044776119402985
hu0.10044977511244377
az0.09502262443438914
is0.09502262443438914
uk0.09502262443438914
vi0.09502262443438914
reliabletrue
passestrue
2
name"Selvi"
dialogue"Maine kuch dekha... par main samajh nahi paayi. Wo andhera tha."
detectedLang"fr"
heavyLang"tl"
scores
fr0.5238095238095238
de0.4666666666666667
lv0.4594594594594595
eu0.42028985507246375
et0.4002998500749625
fi0.4002998500749625
en0.3957703927492447
da0.30915371329879104
tl0.30915371329879104
sv0.3019197207678883
yo0.29701230228471004
ro0.2687385740402194
sq0.2263056092843327
is0.20318725099601595
no0.2
ms0.15074309978768577
reliablefalse
passesfalse
3
name"Hunter"
dialogue"I don't speak Hindi. Do you understand me? I need to know what you saw."
detectedLang"en"
heavyLang"en"
scores
en0.8038360941586749
tl0.6160409556313994
no0.5879120879120879
da0.5472837022132797
cs0.5412844036697247
sq0.5192307692307693
pl0.5171673819742489
sk0.48571428571428565
et0.46492271105826394
hr0.4545454545454546
sv0.4367959949937422
sl0.42233632862644416
yo0.4015957446808511
it0.39759036144578314
nl0.3679775280898876
pt0.3515850144092219
is0.3430656934306569
de0.3001555209953344
lv0.2913385826771654
ms0.2902208201892744
vi0.27884615384615385
lt0.2706645056726094
ro0.267100977198697
ca0.23469387755102045
es0.1847826086956522
fr0.16820702402957485
hi0.14772727272727273
fi0.14285714285714285
be0.1346153846153846
tr0.1346153846153846
hu0.12959381044487428
az0.12280701754385964
uk0.12280701754385964
reliabletrue
passestrue
4
name"Selvi"
dialogue"Nahi. Sirf Hindi. Main darr gayi hoon."
detectedLang"tl"
heavyLang"tl"
scores
tl0.6086105675146771
eu0.4520547945205479
it0.33774834437086093
en0.3311036789297659
is0.3288590604026846
et0.3197278911564626
fr0.3055555555555556
sq0.30313588850174217
de0.2805755395683453
hi0.2805755395683453
reliabletrue
passesfalse
5
name"Hunter"
dialogue"Okay. Just point to the camera. Did you take a picture of what you saw?"
detectedLang"en"
heavyLang"en"
scores
en0.8146532926297427
tl0.7138047138047139
fr0.5800395256916996
yo0.5627572016460906
da0.48918269230769235
ro0.46874999999999994
it0.46473551637279603
sl0.46473551637279603
no0.46406052963430017
nl0.4558258642765685
cs0.44516971279373363
pl0.4385733157199472
sv0.43333333333333335
ca0.4256756756756757
hr0.42489851150202973
ms0.42411924119241196
de0.40807799442896936
sk0.3813682678311499
es0.35213414634146345
sq0.34210526315789475
lv0.3111831442463533
lt0.3044189852700491
et0.2796610169491525
is0.2784380305602716
hu0.2685025817555938
pt0.247787610619469
tr0.1533864541832669
az0.1414141414141414
eu0.1414141414141414
vi0.1414141414141414
fi0.1290983606557377
reliabletrue
passestrue
6
name"Selvi"
dialogue"Haan. Par main use dikhana nahi chahti."
detectedLang"en"
heavyLang"tl"
scores
en0.5192307692307693
fr0.5076586433260394
eu0.4230769230769231
lv0.40789473684210525
et0.33234421364985167
fi0.33234421364985167
ms0.30769230769230765
yo0.30769230769230765
da0.29245283018867924
sv0.29245283018867924
de0.25742574257425743
reliablefalse
passesfalse
7
name"Hunter"
dialogue"I understand you're scared. But it's important. Can you show me the photos?"
detectedLang"en"
heavyLang"en"
scores
en0.8114630467571644
tl0.6209249431387415
no0.6050552922590837
fr0.5964487489911219
da0.5674740484429065
ca0.5387453874538745
nl0.5305164319248826
ro0.5083579154375615
sv0.4969818913480885
it0.4887525562372188
pt0.4692144373673036
sq0.46062567421790723
es0.43117178612059154
cs0.34810951760104303
de0.34554973821989526
tr0.31224209078404397
lt0.299719887955182
pl0.28977272727272724
yo0.2795389048991354
ms0.24471299093655588
sk0.24357034795764
et0.2401215805471125
az0.21875
hr0.21752738654147105
is0.21507064364207218
lv0.21135646687697163
sl0.14965986394557826
hi0.1334488734835355
fi0.13043478260869565
be0.12280701754385964
hu0.11816578483245149
uk0.11190053285968028
vi0.11190053285968028
reliabletrue
passestrue
8
name"Selvi"
dialogue"Nahi. Abhi nahi. Kripya mujhe chhod do."
detectedLang"sq"
heavyLang"la"
scores
sq0.49664429530201337
eu0.4230769230769231
pt0.4094488188976378
pl0.3885869565217392
cs0.3715083798882682
sk0.3697478991596639
hr0.34782608695652173
sl0.34782608695652173
vi0.33035714285714285
en0.3202416918429003
yo0.25742574257425743
reliablefalse
passesfalse
9
name"Hunter"
dialogue"I can't do that. I have to follow the lead. Someone is missing."
detectedLang"en"
heavyLang"en"
scores
en0.8347790169351508
tl0.6509598603839442
da0.602780536246276
yo0.5694294940796556
no0.5192307692307693
nl0.5115995115995116
pl0.5024875621890548
hr0.4838709677419355
cs0.4798439531859558
sk0.45652173913043476
sq0.4513031550068587
sv0.43820224719101125
is0.43422913719943423
pt0.42775393419170243
it0.39209726443769
sl0.37597503900156004
hu0.355877616747182
ca0.3442622950819672
ms0.3197278911564626
lv0.3162393162393162
vi0.30313588850174217
lt0.2945326278659612
fr0.2727272727272727
az0.24242424242424243
et0.24242424242424243
ro0.1836734693877551
es0.16317991631799164
fi0.16317991631799164
de0.15254237288135594
be0.14893617021276595
tr0.14893617021276595
uk0.13606911447084233
reliabletrue
passestrue
10
name"Selvi"
dialogue"Woh wapas nahi aayega. Main jaanti hoon."
detectedLang"eu"
heavyLang"de"
scores
eu0.39759036144578314
et0.3438320209973753
it0.30362116991643456
es0.2857142857142857
pt0.2857142857142857
en0.28366762177650434
fr0.26035502958579887
lt0.26035502958579887
ms0.24242424242424243
de0.2378048780487805
lv0.23076923076923078
cs0.21135646687697163
hr0.21135646687697163
ro0.21135646687697163
sk0.21135646687697163
sl0.21135646687697163
sq0.21135646687697163
tl0.21135646687697163
tr0.21135646687697163
reliablefalse
passesfalse
11
name"Hunter"
dialogue"Who are you talking about? The missing student?"
detectedLang"en"
heavyLang"en"
scores
en0.8393144081414033
tl0.6354799513973268
nl0.6259351620947631
no0.5732574679943101
sv0.5575221238938053
fr0.5468277945619335
da0.5334370139968896
ro0.4897959183673469
de0.48717948717948717
is0.4263862332695985
cs0.4230769230769231
sq0.41972920696324956
ms0.38524590163934425
ca0.33920704845814975
az0.3181818181818182
pl0.3135011441647597
pt0.3119266055045872
et0.3103448275862069
it0.3103448275862069
sk0.3006993006993007
yo0.2628992628992629
fi0.20634920634920634
hr0.20424403183023873
lt0.1891891891891892
lv0.1891891891891892
hu0.16434540389972147
sl0.16434540389972147
reliabletrue
passestrue
12
name"Selvi"
dialogue"Haan. Usne mujhe dekha tha."
detectedLang"sq"
heavyLang"vi"
scores
sq0.4006849315068493
reliablefalse
passesfalse
13
name"Hunter"
dialogue"I'm sorry. I have to take this. I'll be back."
detectedLang"en"
heavyLang"en"
scores
en0.8122866894197952
tl0.6629901960784313
da0.5864661654135338
yo0.548440065681445
lt0.5036101083032491
pl0.4869402985074627
hr0.4811320754716981
no0.48015122873345933
cs0.461839530332681
it0.4387755102040817
sk0.4258872651356994
sl0.41983122362869196
lv0.40217391304347827
hu0.4008714596949891
ca0.3341404358353511
sv0.3341404358353511
sq0.3276283618581907
pt0.26666666666666666
ro0.24657534246575344
be0.20289855072463767
tr0.20289855072463767
az0.1863905325443787
et0.1863905325443787
is0.1863905325443787
uk0.1863905325443787
vi0.1863905325443787
reliabletrue
passestrue
14
name"Selvi"
dialogue"Kripya. Madad."
detectedLang"tl"
heavyLang"tlh"
scores
tl0.5708154506437768
et0.5283018867924528
sq0.5121951219512195
sv0.5121951219512195
reliablefalse
passestrue
15
name"Hunter"
dialogue"Stay here. Don't move."
detectedLang"en"
heavyLang"en"
scores
en0.8241912798874825
sq0.4444444444444444
reliabletrue
passestrue