Run: 2026-02-25-01KJBJ9VFG1EQD6Y43YKJRYQF6

Run Details

Model:
Qwen 3.5 122B
Test:
Language Writing
Scenario:
Character dialogue (Hindi) in a story
Duration:
40.6s
Cost:
$0.012638
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: "(Speaking Hindi, voice trembling) I saw him... near the orchards. He was holding a bag, and he looked like he was in pain." Hunter: "Ma'am, I'm Detective Hunter. Do you understand me? I need to know if you saw anything unusual yesterday." Selvi: "(Speaking Hindi, clutching her camera) I tried to take a picture, but he ran away. He was wearing the same hat as the man who disappeared." Hunter: "I'm sorry, I don't speak that language. Can you write it down? Or find someone to translate?" Selvi: "(Speaking Hindi, eyes wide) No one understands me here. Please, you must help him. He is not safe." Hunter: "Look, I need a name or a location. I can't work with gestures alone." Selvi: "(Speaking Hindi, pointing at the photo on her camera screen) There. In the background. The old barn." Hunter: "I see the barn, but I don't know what you're saying. Did you see the man go inside?" Selvi: "(Speaking Hindi, shaking her head) No, he ran toward the woods. But he dropped this." Hunter: "You found something? A clue?" Selvi: "(Speaking Hindi, handing him a small object) Yes. A button. From his coat." Hunter: "Okay, okay, I get the picture. But I still don't know your name." Selvi: "(Speaking Hindi, softly) Selvi. My name is Selvi." Hunter: "Selvi. Right. I'll take a look at this... Selvi. I'll need to file a report." Selvi: "(Speaking Hindi, hopeful) You will come back?" Hunter: "I'm on the job, I'll be back. Just stay here." *(Hunter’s phone rings loudly. He answers, his demeanor shifting to professional urgency.)* Hunter: "Hunter here. ... What? On the north ridge? Okay, I'm on my way." *(Hunter looks back at Selvi, apologetic but distracted.)* Hunter: "I have to go. Stay safe." Selvi: "(Speaking Hindi, watching him leave) Please... be careful." Hunter: "Right. I'll be in touch." *(Hunter hurries away, leaving Selvi alone at the table.)*
created_at"2026-02-25T23:31:45.78Z" 2/25/2026, 11:31:45 PM
model"qwen/qwen3.5-122b-a10b-20260224"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency467
moderation_latency(null)
generation_time40540
tokens_prompt315
tokens_completion4103
native_tokens_prompt300
native_tokens_completion3912
native_tokens_completion_images(null)
native_tokens_reasoning3399
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"
usage0.0126384
router(null)
provider_responses
0
endpoint_id"33d466d1-d2f7-45ed-8ff3-fda7d2e32351"
id"chatcmpl-9288c9e1-bf4e-9555-833b-fb037518d344"
is_byokfalse
latency467
model_permaslug"qwen/qwen3.5-122b-a10b-20260224"
provider_name"Alibaba"
status200
api_type"completions"
id"gen-1772062305-B4VGCwhrfugIy9d3WNtm"
upstream_id"chatcmpl-9288c9e1-bf4e-9555-833b-fb037518d344"
total_cost0.0126384
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"I saw him... near the orchards. He was holding a bag, and he looked like he was in pain."
detectedLang"en"
heavyLang"en"
scores
en0.8134328358208955
tl0.6410624551328068
no0.5808885163453479
yo0.5794785534062238
da0.5759117896522477
nl0.5269631031220435
ms0.4553376906318083
de0.44933920704845814
it0.43630214205186024
sv0.43566591422121903
ro0.42594718714121704
ca0.42196531791907516
sk0.4110718492343934
pl0.38650306748466257
fr0.36386768447837153
sq0.36224489795918363
hr0.3342210386151798
sl0.32795698924731176
cs0.32157394843962006
hu0.3084370677731674
tr0.30747922437673125
az0.302649930264993
es0.30167597765363136
is0.29577464788732394
fi0.23547400611620795
lt0.2248062015503876
pt0.21875
lv0.21011058451816747
vi0.21011058451816747
et0.20127795527156547
be0.12280701754385964
eu0.12280701754385964
uk0.11190053285968028
reliabletrue
passesfalse
1
name"Hunter"
dialogue"Ma'am, I'm Detective Hunter. Do you understand me? I need to know if you saw anything unusual yesterday."
detectedLang"en"
heavyLang"en"
scores
en0.788391777509069
no0.5333333333333334
da0.5035460992907801
tl0.5
sq0.48186528497409326
cs0.4627782041442824
sv0.45567651632970446
pt0.44178628389154706
nl0.43820224719101125
pl0.4077834179357022
ro0.4042553191489362
sl0.3939393939393939
hr0.38704028021015763
it0.381078691423519
sk0.37777777777777777
et0.36479128856624315
ms0.36247723132969034
ca0.35004642525533886
de0.3427230046948357
es0.33774834437086093
fr0.3371212121212121
yo0.3013972055888224
lv0.20903954802259886
vi0.19908466819221968
lt0.19261822376009227
is0.16367980884109917
tr0.15560916767189384
fi0.0967741935483871
be0.09090909090909091
hu0.08735332464146023
az0.08256880733944955
uk0.08256880733944955
reliabletrue
passestrue
2
name"Selvi"
dialogue"I tried to take a picture, but he ran away. He was wearing the same hat as the man who disappeared."
detectedLang"en"
heavyLang"en"
scores
en0.8109497882637627
tl0.640598044853364
yo0.5930989583333334
no0.5377218934911242
da0.5070977917981072
nl0.49433656957928807
de0.48474855729596045
hr0.45934256055363326
sv0.4541484716157206
fr0.4302643573381951
sq0.4153414405986903
sk0.4098205854579792
ms0.40476190476190477
it0.3978805394990366
hu0.38665358194308147
sl0.37122736418511065
cs0.3705941591137966
pl0.3693239152371342
ca0.3686868686868687
lv0.36740890688259115
lt0.3543388429752066
ro0.3293991416309013
pt0.31015452538631344
tr0.2647058823529412
es0.2568370986920333
eu0.25059952038369304
fi0.19768934531450577
is0.18086500655307994
az0.17546174142480211
vi0.17546174142480211
et0.1677762982689747
be0.10071942446043164
uk0.09156976744186046
reliabletrue
passesfalse
3
name"Hunter"
dialogue"I'm sorry, I don't speak that language. Can you write it down? Or find someone to translate?"
detectedLang"en"
heavyLang"en"
scores
en0.8171589310829818
tl0.5822622107969152
ro0.4500846023688663
da0.4313210848643919
no0.4268077601410935
it0.3953488372093023
hr0.37679769894535
cs0.364613880742913
lt0.36211972522080466
yo0.35834155972359333
sk0.3493493493493494
lv0.34210526315789475
pl0.3374108053007136
fr0.3157894736842105
et0.30997876857749473
sq0.30997876857749473
ca0.30851063829787234
pt0.28414096916299564
sl0.2793791574279379
tr0.24418604651162787
az0.23439340400471145
sv0.23258559622195982
es0.19254658385093168
de0.19154228855721395
vi0.18851435705368288
nl0.1875
is0.18444165621079048
ms0.18341708542713567
eu0.18238993710691823
be0.09722222222222222
hu0.09344490934449094
uk0.08835904628330996
reliabletrue
passestrue
4
name"Selvi"
dialogue"No one understands me here. Please, you must help him. He is not safe."
detectedLang"en"
heavyLang"en"
scores
en0.8265895953757225
tl0.5579567779960707
no0.5486459378134404
nl0.5222929936305732
es0.47058823529411764
sv0.44581280788177335
pt0.4063324538258575
da0.39271255060728744
is0.3706293706293706
sq0.3553008595988539
de0.35344827586206895
pl0.34782608695652173
it0.34497816593886466
ca0.3343195266272189
yo0.33035714285714285
hr0.29467084639498436
sk0.2857142857142857
fr0.27768860353130015
fi0.2694805194805195
tr0.2694805194805195
cs0.2647058823529412
ms0.26350245499181674
hu0.2549668874172185
lv0.225473321858864
ro0.1818181818181818
et0.17431192660550457
sl0.16356877323420074
az0.13294797687861273
reliabletrue
passesfalse
5
name"Hunter"
dialogue"Look, I need a name or a location. I can't work with gestures alone."
detectedLang"en"
heavyLang"en"
scores
en0.8172217709179529
fr0.673202614379085
tl0.6359223300970874
ca0.5821727019498607
nl0.5481927710843374
de0.5445344129554657
it0.5283018867924528
da0.5253164556962026
ro0.5171673819742489
sv0.5166487647690655
yo0.4558645707376058
no0.44717444717444715
et0.44649446494464945
pt0.42675159235668786
pl0.4063324538258575
es0.40476190476190477
sq0.38016528925619836
hr0.3580599144079886
cs0.34497816593886466
hu0.33135215453194655
is0.3263473053892215
tr0.3253373313343328
lv0.32432432432432434
sk0.3098159509202454
fi0.24369747899159663
lt0.24369747899159663
ms0.23857868020304565
az0.22813036020583194
vi0.22813036020583194
sl0.16666666666666666
zh0.14611005692599618
be0.1346153846153846
eu0.1346153846153846
uk0.12280701754385964
reliabletrue
passestrue
6
name"Selvi"
dialogue"There. In the background. The old barn."
detectedLang"en"
heavyLang"en"
scores
en0.8332097850259451
tl0.6522411128284389
sv0.6394230769230769
de0.5909090909090909
nl0.5161290322580645
yo0.46428571428571425
no0.45520581113801456
da0.4230769230769231
sq0.4094488188976378
sl0.4063324538258575
ms0.40476190476190477
it0.3951612903225807
ro0.3869209809264305
az0.27184466019417475
pl0.27184466019417475
fr0.25742574257425743
is0.2549668874172185
reliabletrue
passesfalse
7
name"Hunter"
dialogue"I see the barn, but I don't know what you're saying. Did you see the man go inside?"
detectedLang"en"
heavyLang"en"
scores
en0.8194602812618776
tl0.594017094017094
da0.5177664974619289
no0.5148110316649642
sv0.4836956521739131
et0.4025157232704403
yo0.3632707774798928
fr0.33286516853932585
pl0.3300423131170663
sq0.30858806404657935
ca0.3055555555555556
it0.302496328928047
nl0.27921092564491656
cs0.27811550151975684
lv0.2647058823529412
tr0.26356589147286824
ro0.2531446540880503
lt0.24841772151898736
ms0.23878205128205127
is0.22764227642276424
hr0.2263843648208469
de0.19627749576988157
sk0.1316270566727605
es0.13003663003663005
pt0.13003663003663005
be0.12844036697247707
hu0.12361623616236161
az0.1171003717472119
uk0.1171003717472119
vi0.1171003717472119
reliabletrue
passestrue
8
name"Selvi"
dialogue"No, he ran toward the woods. But he dropped this."
detectedLang"en"
heavyLang"en"
scores
en0.8324958123953099
tl0.6749729144095342
yo0.569583931133429
no0.471830985915493
ca0.4296577946768061
es0.42418426103646834
pl0.3839835728952772
fr0.3562231759656652
nl0.34782608695652173
pt0.3150684931506849
lv0.30394431554524365
hr0.2518703241895262
fi0.23273657289002556
sk0.23273657289002556
tr0.22680412371134018
it0.21052631578947367
da0.20634920634920634
ms0.20634920634920634
sq0.20634920634920634
sv0.20634920634920634
reliabletrue
passesfalse
9
name"Hunter"
dialogue"You found something? A clue?"
detectedLang"en"
heavyLang"en"
scores
en0.8186763372620127
tl0.7416020671834626
pt0.5215311004784688
cs0.5121951219512195
es0.5121951219512195
hu0.43820224719101125
ms0.41348973607038125
ro0.41002949852507375
ca0.40476190476190477
sk0.3939393939393939
it0.38461538461538464
yo0.3730407523510972
fr0.36908517350157727
hr0.358974358974359
pl0.3442622950819672
sl0.3103448275862069
lt0.2907801418439716
tr0.2779783393501805
is0.2727272727272727
da0.2647058823529412
sq0.2647058823529412
az0.25925925925925924
eu0.25925925925925924
lv0.25925925925925924
nl0.25925925925925924
no0.25925925925925924
vi0.25925925925925924
de0.250936329588015
et0.23954372623574144
fi0.23954372623574144
sv0.23954372623574144
reliabletrue
passestrue
10
name"Selvi"
dialogue"Yes. A button. From his coat."
detectedLang"en"
heavyLang"en"
scores
en0.8124330117899251
tl0.6085011185682326
it0.5370370370370371
hu0.4712990936555891
de0.453125
pt0.4444444444444444
ro0.44267515923566875
ca0.4372990353697749
cs0.4299674267100977
es0.4299674267100977
sk0.42622950819672134
yo0.40476190476190477
fr0.4006849315068493
hr0.3902439024390244
pl0.375
sl0.33962264150943394
lt0.31906614785992216
tr0.3055555555555556
is0.3
da0.29149797570850206
sq0.29149797570850206
az0.2857142857142857
eu0.2857142857142857
lv0.2857142857142857
nl0.2857142857142857
no0.2857142857142857
vi0.2857142857142857
et0.2647058823529412
fi0.2647058823529412
ms0.2647058823529412
sv0.2647058823529412
reliabletrue
passesfalse
11
name"Hunter"
dialogue"Okay, okay, I get the picture. But I still don't know your name."
detectedLang"en"
heavyLang"en"
scores
en0.8129342597541421
tl0.630801687763713
sv0.5077355836849508
sq0.5056497175141244
no0.48377581120943947
is0.46808510638297873
da0.46564885496183206
hr0.45482866043613707
fr0.44267515923566875
it0.4336569579288026
yo0.4308943089430894
nl0.3955094991364421
de0.38162544169611307
ro0.32432432432432434
ms0.308300395256917
ca0.2827868852459016
lt0.27083333333333337
lv0.27083333333333337
pl0.2647058823529412
cs0.23076923076923078
sl0.18604651162790697
sk0.17061611374407584
be0.16666666666666666
tr0.16666666666666666
hu0.1606714628297362
az0.15254237288135594
et0.15254237288135594
uk0.15254237288135594
vi0.15254237288135594
reliabletrue
passestrue
12
name"Selvi"
dialogue"Selvi. My name is Selvi."
detectedLang"en"
heavyLang"af"
scores
en0.7443762781186094
nl0.654696132596685
hu0.5519713261648745
yo0.4897959183673469
da0.47257383966244726
fi0.46808510638297873
no0.42660550458715596
is0.423963133640553
pl0.423963133640553
cs0.4075829383886255
sk0.4075829383886255
de0.3842364532019704
ca0.3811881188118812
tl0.37810945273631835
reliabletrue
passesfalse
13
name"Hunter"
dialogue"Selvi. Right. I'll take a look at this... Selvi. I'll need to file a report."
detectedLang"en"
heavyLang"en"
scores
en0.8024236037934668
tl0.6980676328502415
da0.6153846153846154
no0.6002132196162047
cs0.5123537061118335
fr0.4813278008298755
sl0.4813278008298755
yo0.46808510638297873
sk0.46120689655172414
pl0.45014662756598234
ca0.43438914027149317
hr0.4335347432024169
ro0.42835365853658536
et0.410377358490566
hu0.37290969899665555
es0.36332767402376914
pt0.36115843270868825
de0.3567753001715266
sv0.35008665511265163
it0.34210526315789475
lv0.33862433862433866
lt0.3315508021390375
fi0.31569343065693434
nl0.27184466019417475
sq0.258893280632411
ms0.251497005988024
tr0.17035398230088497
is0.16666666666666666
az0.15730337078651685
eu0.15730337078651685
vi0.15730337078651685
reliabletrue
passestrue
14
name"Selvi"
dialogue"You will come back?"
detectedLang"en"
heavyLang"en"
scores
en0.8394863563402889
tl0.7191011235955056
it0.6183206106870229
de0.5145631067961165
cs0.43820224719101125
reliabletrue
passesfalse
15
name"Hunter"
dialogue"I'm on the job, I'll be back. Just stay here."
detectedLang"en"
heavyLang"en"
scores
en0.819364161849711
yo0.5387453874538745
tl0.5353159851301116
et0.5059288537549407
fr0.4279176201372997
sv0.4186046511627907
sq0.41588785046728977
ca0.4131455399061033
da0.39903846153846156
fi0.375
hu0.31880108991825606
lt0.3093922651933701
no0.2753623188405797
hr0.26035502958579887
hi0.251497005988024
nl0.251497005988024
pl0.251497005988024
de0.2378048780487805
ms0.2378048780487805
cs0.23076923076923078
sk0.23076923076923078
reliabletrue
passestrue
16
name"Hunter"
dialogue"Hunter here. ... What? On the north ridge? Okay, I'm on my way."
detectedLang"en"
heavyLang"en"
scores
en0.8077979132344867
tl0.6399176954732511
fr0.42528735632183906
no0.41569282136894825
sq0.40374787052810895
yo0.34210526315789475
pl0.3346007604562738
cs0.3150684931506849
sk0.3150684931506849
da0.3137254901960784
ca0.3110236220472441
et0.3055555555555556
fi0.3
pt0.2985971943887776
sv0.29718875502008035
nl0.29577464788732394
ms0.2813141683778234
de0.2009132420091324
hr0.2009132420091324
es0.19724770642201836
hi0.1935483870967742
it0.15254237288135594
ro0.14425427872860636
sl0.14425427872860636
tr0.14425427872860636
reliabletrue
passestrue
17
name"Hunter"
dialogue"I have to go. Stay safe."
detectedLang"en"
heavyLang"en"
scores
en0.8306997742663657
da0.7222222222222222
pl0.7109826589595376
yo0.6674057649667406
hr0.6296296296296297
no0.6287128712871286
tl0.6153846153846154
cs0.6113989637305699
sk0.576271186440678
lv0.5522388059701493
lt0.526813880126183
ca0.4791666666666667
sv0.4791666666666667
sq0.471830985915493
sl0.44649446494464945
it0.43396226415094336
ro0.375
be0.3181818181818182
tr0.3181818181818182
hu0.3087557603686636
az0.29577464788732394
et0.29577464788732394
is0.29577464788732394
uk0.29577464788732394
vi0.29577464788732394
reliabletrue
passestrue
18
name"Selvi"
dialogue"Please... be careful."
detectedLang"en"
heavyLang"en"
scores
en0.8266296809986131
ro0.6973365617433415
tl0.5980707395498392
hu0.4834710743801653
lt0.47257383966244726
yo0.46808510638297873
es0.37810945273631835
fr0.37810945273631835
reliabletrue
passesfalse
19
name"Hunter"
dialogue"Right. I'll be in touch."
detectedLang"en"
heavyLang"en"
scores
en0.8134328358208955
tl0.6268656716417911
yo0.6085011185682326
de0.5580808080808082
fr0.515235457063712
nl0.4712990936555891
sl0.46808510638297873
it0.45652173913043476
ro0.4479495268138801
hu0.4006849315068493
lt0.3902439024390244
sv0.3794326241134752
az0.32432432432432434
pl0.32432432432432434
ms0.3
da0.29718875502008035
no0.29718875502008035
reliabletrue
passestrue