Run: 2026-02-25-01KJBGJ26BWVC6MQY6FB9P9DWE

Run Details

Model:
Qwen 3.5 122B
Test:
Language Writing
Scenario:
Character dialogue (Hindi) in a story
Duration:
30.4s
Cost:
$0.009397
Provider:
Alibaba

Evaluation summary

Score Evaluator
Details Link
55.00% 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="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: (Startled, clutching her camera to her chest) "Kaun hai? Police? Kya hua?" Hunter: "Ma'am, please. I'm not here to hurt you. I'm Detective Hunter. Did you see anything strange near the orchard yesterday afternoon?" Selvi: (Eyes wide, voice trembling) "Maine dekha... woh... andhere mein. Koi tha." Hunter: "I don't speak Hindi, ma'am. Can you try English? Just a few words?" Selvi: (Shakes head frantically, pointing to her camera) "Nahi... English nahi aata. Camera. Dekho." Hunter: (Sighs, leaning in slightly) "Okay. You have a camera. Did you take a picture of something?" Selvi: (Nods, tapping the screen) "Haan! Woh... aadmi. Woh bhaag raha tha." Hunter: "A man? Running?" Selvi: "Haan. Darr raha tha. Kisi se." Hunter: (Stares at the screen, squinting) "Is that... is that the missing farmer? The one from the Miller place?" Selvi: (Nods vigorously, eyes filling with tears) "Haan. Woh... gayab." Hunter: (Rubbing his chin, processing) "Okay. Okay, that's... that's helpful. Even if I don't understand the rest." Selvi: "Kya... koi madad milegi?" Hunter: (Shrugs helplessly) "I don't know. I'll check this. Just... stay safe." Selvi: "Haan. Safe." Hunter: (Phone buzzes in his pocket, he glances at it) "Excuse me." Selvi: "Kya hua?" Hunter: "I have to go. I'll come back." Selvi: "Jaldi aana." Hunter: (Already walking away, phone to ear) "Yeah, I'm on my way. No, I found a lead."
created_at"2026-02-25T23:01:17.655Z" 2/25/2026, 11:01:17 PM
model"qwen/qwen3.5-122b-a10b-20260224"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency477
moderation_latency(null)
generation_time30277
tokens_prompt315
tokens_completion2959
native_tokens_prompt300
native_tokens_completion2899
native_tokens_completion_images(null)
native_tokens_reasoning2448
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"
usage0.0093968
router(null)
provider_responses
0
endpoint_id"33d466d1-d2f7-45ed-8ff3-fda7d2e32351"
id"chatcmpl-6457bd8e-ac44-97b8-95eb-4c2fec296a27"
is_byokfalse
latency477
model_permaslug"qwen/qwen3.5-122b-a10b-20260224"
provider_name"Alibaba"
status200
api_type"completions"
id"gen-1772060477-cpfTCJTnT5QT9WzPGpFf"
upstream_id"chatcmpl-6457bd8e-ac44-97b8-95eb-4c2fec296a27"
total_cost0.0093968
cache_discount(null)
upstream_inference_cost0
provider_name"Alibaba"

Evaluation details

Result Evaluator Details Meta Data
55.00% Parse dialogue n/a
dialogue
0
name"Selvi"
dialogue"Kaun hai? Police? Kya hua?"
detectedLang"it"
heavyLang"fi"
scores
it0.6394230769230769
cs0.5481927710843374
ro0.5398773006134969
en0.5356037151702787
hr0.5283018867924528
tl0.5253164556962026
fr0.5192307692307693
sl0.5192307692307693
sk0.511400651465798
vi0.511400651465798
eu0.38524590163934425
da0.375
et0.3723849372384937
lv0.3723849372384937
no0.3723849372384937
sv0.3723849372384937
pl0.3697478991596639
lt0.3670886075949367
nl0.3644067796610169
fi0.358974358974359
ms0.35344827586206895
sq0.35344827586206895
de0.34782608695652173
az0.3333333333333333
es0.3333333333333333
hu0.3333333333333333
ca0.32432432432432434
tr0.32432432432432434
pt0.3181818181818182
reliabletrue
passesfalse
1
name"Hunter"
dialogue"Ma'am, please. I'm not here to hurt you. I'm Detective Hunter. Did you see anything strange near the orchard yesterday afternoon?"
detectedLang"en"
heavyLang"en"
scores
en0.7880794701986755
tl0.6252927400468384
no0.4715984147952444
da0.44521497919556174
nl0.43222143364088006
fr0.4152046783625731
sq0.37936384794414274
ro0.37791601866251945
de0.34318555008210183
cs0.3127147766323024
sl0.29515418502202645
it0.28507596067917784
pt0.27862939585211904
sk0.27007299270072993
sv0.2640294388224471
ms0.25788497217068646
hr0.2537313432835821
es0.2409867172675522
yo0.23371647509578544
ca0.2300288739172281
et0.22254616132167152
pl0.2102665350444225
tr0.19678714859437751
lv0.1935483870967742
lt0.17610710607621008
is0.07727797001153403
az0.06868451688009314
reliabletrue
passestrue
2
name"Selvi"
dialogue"Maine dekha... woh... andhere mein. Koi tha."
detectedLang"de"
heavyLang"da"
scores
de0.5833333333333334
en0.5421245421245421
fr0.4541484716157206
sq0.43820224719101125
et0.3946731234866829
fi0.3946731234866829
ro0.37027707808564225
lv0.26035502958579887
tl0.24698795180722888
reliabletrue
passesfalse
3
name"Hunter"
dialogue"I don't speak Hindi, ma'am. Can you try English? Just a few words?"
detectedLang"en"
heavyLang"en"
scores
en0.779275092936803
tl0.6001683501683501
ca0.5153061224489796
nl0.4656917885264342
sv0.4411764705882353
it0.4186046511627907
hr0.40476190476190477
et0.40401505646173147
cs0.39873417721518983
ro0.38788659793814434
no0.38471502590673573
sq0.3815104166666667
da0.37335092348284965
is0.3319268635724332
de0.3290960451977401
pl0.3271954674220963
tr0.32045779685264664
hu0.31948424068767906
az0.3065693430656934
yo0.302496328928047
sk0.2983751846381093
fr0.2899850523168909
lt0.23387096774193547
pt0.22764227642276424
ms0.22131147540983606
lv0.21875
vi0.21875
es0.21746293245469525
sl0.1592920353982301
hi0.1410488245931284
be0.12844036697247707
eu0.12844036697247707
fi0.1171003717472119
uk0.1171003717472119
reliabletrue
passestrue
4
name"Selvi"
dialogue"Nahi... English nahi aata. Camera. Dekho."
detectedLang"en"
heavyLang"tl"
scores
en0.591002044989775
ro0.5348837209302325
eu0.4520547945205479
it0.441340782122905
sv0.4350282485875706
de0.4186046511627907
ms0.4186046511627907
ca0.33774834437086093
es0.3311036789297659
no0.2907801418439716
fr0.2753623188405797
nl0.2753623188405797
da0.2647058823529412
hr0.2647058823529412
tl0.2647058823529412
reliabletrue
passesfalse
5
name"Hunter"
dialogue"Okay. You have a camera. Did you take a picture of something?"
detectedLang"en"
heavyLang"en"
scores
en0.8075865860362836
tl0.6888888888888888
ro0.5172413793103449
it0.513212795549374
es0.4688922610015175
fr0.46564885496183206
yo0.4640122511485452
de0.45567651632970446
nl0.4372990353697749
sl0.41471571906354515
ca0.40476190476190477
da0.3848857644991213
pt0.38380281690140844
ms0.3783303730017762
cs0.375
hr0.3613138686131387
is0.31906614785992216
no0.31906614785992216
hu0.308300395256917
sv0.29292929292929293
sq0.29006085192697767
sk0.27083333333333337
pl0.23076923076923078
lt0.1898148148148148
tr0.18032786885245902
az0.16666666666666666
eu0.16666666666666666
lv0.16666666666666666
vi0.16666666666666666
et0.15254237288135594
fi0.15254237288135594
reliabletrue
passestrue
6
name"Selvi"
dialogue"Haan! Woh... aadmi. Woh bhaag raha tha."
detectedLang"et"
heavyLang"de"
scores
et0.41348973607038125
sq0.36908517350157727
reliablefalse
passesfalse
7
name"Hunter"
dialogue"A man? Running?"
detectedLang"en"
heavyLang"is"
scores
en0.8204667863554758
tl0.7858672376873662
da0.76905311778291
sv0.7652582159624414
no0.7409326424870466
nl0.7375328083989501
is0.6491228070175439
de0.6466431095406361
lv0.6402877697841727
lt0.6376811594202898
hu0.609375
pt0.5833333333333334
ro0.5815899581589958
ca0.576271186440678
cs0.5689655172413793
es0.5689655172413793
sk0.5652173913043478
it0.5555555555555556
yo0.54337899543379
fr0.5391705069124424
hr0.5283018867924528
pl0.5121951219512195
sl0.47368421052631576
tr0.4350282485875706
sq0.4186046511627907
az0.4117647058823529
eu0.4117647058823529
vi0.4117647058823529
et0.38650306748466257
fi0.38650306748466257
ms0.38650306748466257
reliabletrue
passestrue
8
name"Selvi"
dialogue"Haan. Darr raha tha. Kisi se."
detectedLang"sq"
heavyLang"vi"
scores
sq0.604221635883905
et0.4845360824742268
cs0.4755244755244755
hr0.469964664310954
sl0.46808510638297873
es0.46428571428571425
ro0.4444444444444444
pt0.44237918215613387
fr0.42084942084942084
yo0.4163424124513619
fi0.40476190476190477
it0.39271255060728744
ca0.3902439024390244
da0.38016528925619836
sv0.3644067796610169
no0.3333333333333333
reliabletrue
passesfalse
9
name"Hunter"
dialogue"Is that... is that the missing farmer? The one from the Miller place?"
detectedLang"en"
heavyLang"en"
scores
en0.8255501878690283
tl0.6823069403714564
fr0.6531483457844184
da0.6440306681270538
nl0.6055825242718447
no0.5865139949109415
sv0.577922077922078
is0.5053272450532724
de0.5045731707317073
ca0.496124031007752
hu0.42781690140845074
yo0.411231884057971
cs0.4025735294117647
ro0.4025735294117647
pt0.3902439024390244
it0.38095238095238093
ms0.36647173489278756
tr0.34077079107505076
pl0.33537832310838445
et0.3340163934426229
hr0.33127572016460904
es0.3229166666666667
az0.32150313152400833
fi0.3200836820083682
sq0.1935483870967742
sk0.18546365914786966
reliabletrue
passestrue
10
name"Selvi"
dialogue"Haan. Woh... gayab."
detectedLang""
heavyLang"de"
scores
reliablefalse
passesfalse
11
name"Hunter"
dialogue"Okay. Okay, that's... that's helpful. Even if I don't understand the rest."
detectedLang"en"
heavyLang"en"
scores
en0.8029427220178665
nl0.6031746031746031
no0.5888157894736842
sv0.5842572062084257
da0.58006718924972
tl0.48559670781893005
sq0.4541484716157206
pl0.35233160621761656
yo0.3409490333919156
de0.3397887323943662
cs0.33510638297872336
ro0.3042671614100185
sk0.30037313432835816
hr0.2704280155642024
ca0.2690058479532163
is0.267578125
it0.23469387755102045
fi0.20886075949367086
fr0.17218543046357618
ms0.17218543046357618
be0.15730337078651685
tr0.15730337078651685
hu0.1515837104072398
az0.14383561643835618
et0.14383561643835618
lt0.14383561643835618
lv0.14383561643835618
uk0.14383561643835618
vi0.14383561643835618
reliabletrue
passestrue
12
name"Selvi"
dialogue"Kya... koi madad milegi?"
detectedLang"et"
heavyLang"tl"
scores
et0.5844875346260388
tl0.469964664310954
sv0.4117647058823529
ca0.34210526315789475
en0.34210526315789475
es0.34210526315789475
hu0.34210526315789475
ro0.34210526315789475
reliabletrue
passesfalse
13
name"Hunter"
dialogue"I don't know. I'll check this. Just... stay safe."
detectedLang"en"
heavyLang"en"
scores
en0.8116438356164383
tl0.5
sv0.46601941747572817
ca0.4387755102040817
et0.375
no0.34523809523809523
da0.3357487922705314
hr0.3357487922705314
sq0.3276283618581907
pl0.314214463840399
it0.2948717948717949
cs0.2763157894736842
ro0.24657534246575344
yo0.2403314917127072
sk0.207492795389049
be0.20289855072463767
tr0.20289855072463767
hu0.19590643274853803
az0.1863905325443787
is0.1863905325443787
lt0.1863905325443787
lv0.1863905325443787
uk0.1863905325443787
vi0.1863905325443787
reliabletrue
passestrue
14
name"Selvi"
dialogue"Haan. Safe."
detectedLang"en"
heavyLang"fi"
scores
en0.6774193548387096
reliablefalse
passestrue
15
name"Hunter"
dialogue"Excuse me."
detectedLang"sq"
heavyLang"es"
scores
sq0.663677130044843
es0.576271186440678
et0.5588235294117647
fr0.5481927710843374
no0.5481927710843374
en0.5398773006134969
pt0.5398773006134969
sl0.5398773006134969
ms0.5283018867924528
nl0.5283018867924528
it0.5161290322580645
fi0.5
reliabletrue
passesfalse
16
name"Selvi"
dialogue"Kya hua?"
detectedLang""
heavyLang"tl"
scores
reliablefalse
passestrue
17
name"Hunter"
dialogue"I have to go. I'll come back."
detectedLang"en"
heavyLang"en"
scores
en0.8159831756046267
da0.6902654867256637
pl0.6783088235294117
tl0.6601941747572816
yo0.6323529411764706
it0.6128318584070797
hr0.5930232558139535
no0.5920745920745921
cs0.5742092457420924
sk0.5382585751978892
lv0.5138888888888888
lt0.4883040935672514
ca0.44089456869009586
sv0.44089456869009586
sq0.4336569579288026
sl0.40878378378378377
ro0.33962264150943394
be0.2857142857142857
tr0.2857142857142857
hu0.2768595041322314
az0.2647058823529412
et0.2647058823529412
is0.2647058823529412
uk0.2647058823529412
vi0.2647058823529412
reliabletrue
passestrue
18
name"Selvi"
dialogue"Jaldi aana."
detectedLang"eu"
heavyLang"is"
scores
eu0.5856353591160222
is0.5562130177514794
et0.5098039215686274
reliabletrue
passesfalse
19
name"Hunter"
dialogue"Yeah, I'm on my way. No, I found a lead."
detectedLang"en"
heavyLang"en"
scores
en0.8169107856191743
tl0.7213779128672746
ca0.648786717752235
pl0.6367239101717306
sk0.6227709190672153
hr0.6153846153846154
cs0.5913818722139673
it0.5378151260504201
no0.5315161839863715
yo0.5053956834532374
et0.5045045045045045
pt0.5027124773960217
es0.494485294117647
lv0.4897959183673469
tr0.4607843137254902
ro0.45436507936507936
fr0.4510978043912176
hu0.44779116465863456
fi0.4364754098360656
da0.434156378600823
sq0.42827442827442824
sv0.4222689075630252
lt0.34523809523809523
is0.3341404358353511
az0.32598039215686275
vi0.32598039215686275
sl0.24657534246575344
hi0.233983286908078
be0.20289855072463767
eu0.20289855072463767
nl0.20289855072463767
de0.19590643274853803
ms0.1863905325443787
uk0.1863905325443787
reliabletrue
passestrue