Run: 2026-02-16-01KHK2KMYMJPRZBJS52MN5DTE3

Run Details

Model:
Qwen 3.5 397B A17B
Test:
Language Writing
Scenario:
Character dialogue (Hindi) in a story
Duration:
1m 49s
Cost:
$0.013212
Provider:
Alibaba

Evaluation summary

Score Evaluator
Details Link
50.00% 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: "[In Hindi] Main bas apni tasveerein dekh rahi thi. Kripya, mujhe pareshan na karein." (I was just looking at my pictures. Please, do not disturb me.) Hunter: "Detective Hunter, Alborn PD. I'm asking about the disappearances near the orchard. You were taking photos yesterday afternoon?" Selvi: "[In Hindi] Mujhe samajh nahi aa raha hai. Main angrezi nahi bolti." (I am not understanding. I do not speak English.) Hunter: "Ma'am, I need you to focus. Did you see a white van? Or anyone acting suspicious near the apple crates?" Selvi: "[In Hindi] Haan... maine ek gaadi dekhi thi. Kaali thi. Usme kuch galat tha." (Yes... I saw a car. It was black. There was something wrong with it.) Hunter: "You're shaking. Did you see the victims? Can you point to them in this sketch?" Selvi: "[In Hindi] Woh insaan... woh hila nahi tha. Mujhe dar lag raha hai." (That person... he was not moving. I am getting scared.) Hunter: "I can't help you if I don't know what you're saying. Do you have a number for a friend? Someone who translates?" Selvi: "[In Hindi] Koi nahi hai. Bas main hoon. Kripya, mujhe jaane dijiye." (There is no one. Just me. Please, let me go.) Hunter: "Look, this is about safety. If you saw something, you need to tell me. It's important for the town." Selvi: "[In Hindi] Mainne kaha na! Kuch galat tha! Par aap sun nahi rahe." (I told you! Something was wrong! But you are not listening.) Hunter: "[Phone Vibrates] Hold on. [Into Phone] Hunter. Yeah? You found the truck? Okay, I'm coming right now." Hunter: "[To Selvi] We're not done. Stay in town. I'll find someone who speaks... whatever that is." Selvi: "[In Hindi] Bhagwan ka shukr hai. Woh ja raha hai." (Thank God. He is leaving.)
created_at"2026-02-16T11:17:31.991175+00:00" 2/16/2026, 11:17:31 AM
model"qwen/qwen3.5-397b-a17b-20260216"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency790
moderation_latency(null)
generation_time108462
tokens_prompt315
tokens_completion3663
native_tokens_prompt300
native_tokens_completion3620
native_tokens_completion_images(null)
native_tokens_reasoning3109
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"
usage0.013212
router(null)
provider_responses
0
id"chatcmpl-9dbdd280-3739-9b1c-b507-ee1de4a9aec0"
status200
is_byokfalse
latency790
endpoint_id"180484a2-e24b-495a-ba41-b34b680d5a9f"
provider_name"Alibaba"
model_permaslug"qwen/qwen3.5-397b-a17b-20260216"
api_type"completions"
id"gen-1771240543-5tUrftdL5YHk4wN1emYN"
upstream_id"chatcmpl-9dbdd280-3739-9b1c-b507-ee1de4a9aec0"
total_cost0.013212
cache_discount(null)
upstream_inference_cost0
provider_name"Alibaba"

Evaluation details

Result Evaluator Details Meta Data
50.00% Parse dialogue n/a
dialogue
0
name"Selvi"
dialogue"Main bas apni tasveerein dekh rahi thi. Kripya, mujhe pareshan na karein."
detectedLang"tl"
heavyLang"vi"
scores
tl0.44717444717444715
fr0.3767313019390581
cs0.358974358974359
pt0.3283582089552239
nl0.3066255778120185
sq0.2879746835443038
lt0.27999999999999997
en0.2753623188405797
de0.25742574257425743
vi0.256198347107438
sk0.2549668874172185
pl0.2537313432835821
sl0.2524916943521595
hr0.25
ms0.1818181818181818
yo0.1818181818181818
is0.17279411764705882
lv0.16974169741697415
es0.16666666666666666
et0.16666666666666666
ca0.15413533834586465
fi0.15413533834586465
it0.13793103448275862
ro0.1262135922330097
sv0.1262135922330097
reliablefalse
passesfalse
1
name"Hunter"
dialogue"Detective Hunter, Alborn PD. I'm asking about the disappearances near the orchard. You were taking photos yesterday afternoon?"
detectedLang"en"
heavyLang"en"
scores
en0.7687780269058296
tl0.5875
fr0.5439469320066335
nl0.46636481241914624
pt0.4294605809128631
no0.3778280542986425
ca0.3584758942457232
it0.34523809523809523
es0.33894230769230765
ro0.3325242718446602
de0.32542927228127555
da0.2930591259640103
sq0.2673179396092362
sv0.25742574257425743
ms0.22169811320754715
sl0.19275929549902154
cs0.15384615384615385
sk0.15123456790123457
lv0.14948453608247422
tr0.14948453608247422
yo0.11480686695278969
pl0.11385606874328678
fi0.08839779005524862
lt0.08839779005524862
hi0.08536585365853659
et0.07924107142857142
is0.07924107142857142
hr0.07511210762331838
reliabletrue
passestrue
2
name"Selvi"
dialogue"Mujhe samajh nahi aa raha hai. Main angrezi nahi bolti."
detectedLang"no"
heavyLang"tl"
scores
no0.48899371069182396
is0.4857594936708861
et0.4298245614035088
it0.40909090909090906
da0.3486973947895792
eu0.336734693877551
vi0.3257261410788381
de0.32432432432432434
ro0.24418604651162787
fi0.24242424242424243
en0.23349056603773585
lv0.22985781990521328
tl0.22985781990521328
fr0.21307506053268765
sv0.19753086419753088
ms0.1792929292929293
reliablefalse
passesfalse
3
name"Hunter"
dialogue"Ma'am, I need you to focus. Did you see a white van? Or anyone acting suspicious near the apple crates?"
detectedLang"en"
heavyLang"en"
scores
en0.7928381177863273
tl0.6076233183856502
fr0.49348769898697536
ca0.47994056463595847
es0.46564885496183206
nl0.4631901840490798
de0.452697419859265
et0.4331983805668016
yo0.4266994266994267
no0.4181213632585204
ro0.40978077571669475
pt0.3902439024390244
cs0.38917975567190227
hu0.38325991189427316
hr0.38271604938271603
sv0.38217122683142096
da0.3595608417200366
it0.35779816513761464
pl0.3433395872420263
sk0.3230174081237911
ms0.3027888446215139
sq0.2886178861788618
lv0.2670157068062827
lt0.2623814541622761
is0.23329682365826945
sl0.23161361141602635
tr0.17355371900826447
az0.15966386554621848
vi0.15966386554621848
be0.09090909090909091
eu0.09090909090909091
fi0.08256880733944955
uk0.08256880733944955
reliabletrue
passestrue
4
name"Selvi"
dialogue"Haan... maine ek gaadi dekhi thi. Kaali thi. Usme kuch galat tha."
detectedLang"et"
heavyLang"vi"
scores
et0.5863495346432265
tl0.465954606141522
ro0.4269340974212034
fi0.4074074074074074
fr0.34210526315789475
tr0.3185689948892675
lv0.2907801418439716
en0.2895204262877442
vi0.27927927927927926
de0.2687385740402194
sq0.2263056092843327
nl0.2
es0.15966386554621848
ms0.15966386554621848
ca0.15789473684210525
sv0.15789473684210525
reliabletrue
passesfalse
5
name"Hunter"
dialogue"You're shaking. Did you see the victims? Can you point to them in this sketch?"
detectedLang"en"
heavyLang"en"
scores
en0.8137254901960784
tl0.6631205673758864
fr0.4848156182212581
da0.4808743169398907
nl0.4186046511627907
yo0.4114002478314746
sv0.4099378881987578
pl0.39567430025445294
no0.3790849673202614
ca0.3683510638297872
sl0.36666666666666664
ro0.3384401114206128
de0.3233618233618234
cs0.3055555555555556
et0.26356589147286824
az0.2531446540880503
ms0.24363057324840762
it0.23633440514469453
sk0.21746293245469525
lv0.20435510887772196
hr0.19627749576988157
lt0.17962003454231434
es0.14874551971326164
sq0.1410488245931284
tr0.1394927536231884
is0.13003663003663005
pt0.13003663003663005
reliabletrue
passestrue
6
name"Selvi"
dialogue"Woh insaan... woh hila nahi tha. Mujhe dar lag raha hai."
detectedLang"ms"
heavyLang"de"
scores
ms0.3877551020408163
sv0.3617021276595745
eu0.3548387096774194
vi0.3435448577680525
et0.3197278911564626
ro0.29906542056074764
lt0.29577464788732394
az0.2890995260663507
sq0.2805755395683453
tr0.2805755395683453
fi0.27007299270072993
it0.25
no0.24623115577889448
es0.2366412213740458
pt0.2366412213740458
tl0.20634920634920634
de0.20424403183023873
nl0.20424403183023873
reliablefalse
passesfalse
7
name"Hunter"
dialogue"I can't help you if I don't know what you're saying. Do you have a number for a friend? Someone who translates?"
detectedLang"en"
heavyLang"en"
scores
en0.8252184769038703
tl0.5635910224438903
da0.48604992657856094
pt0.46605644546147984
no0.42763695829926407
cs0.42004971002485497
sk0.396551724137931
yo0.39130434782608703
pl0.38811188811188807
et0.38650306748466257
sv0.3848857644991213
hr0.38271604938271603
ca0.375
nl0.3710691823899371
sq0.3607305936073059
de0.35125115848007415
es0.3383742911153119
sl0.3217054263565891
vi0.3217054263565891
hu0.308300395256917
ro0.308300395256917
tr0.3069306930693069
it0.3020937188434696
fr0.2768595041322314
is0.2391304347826087
ms0.23329682365826945
lt0.2324561403508772
lv0.2222222222222222
az0.21524663677130043
eu0.16367980884109917
be0.09090909090909091
fi0.08256880733944955
uk0.08256880733944955
reliabletrue
passestrue
8
name"Selvi"
dialogue"Koi nahi hai. Bas main hoon. Kripya, mujhe jaane dijiye."
detectedLang"fr"
heavyLang"tl"
scores
fr0.36363636363636365
eu0.32038834951456313
vi0.30966469428007887
et0.2723492723492723
sq0.23076923076923078
it0.2222222222222222
ms0.2222222222222222
en0.22048997772828507
de0.1822429906542056
reliablefalse
passesfalse
9
name"Hunter"
dialogue"Look, this is about safety. If you saw something, you need to tell me. It's important for the town."
detectedLang"en"
heavyLang"en"
scores
en0.8380566801619433
tl0.5702005730659025
no0.49622166246851385
da0.4439295644114921
fr0.43872778297474274
pt0.4280266920877026
nl0.39879759519038077
es0.3858751279426817
yo0.3775933609958506
ms0.3617021276595745
ca0.33184855233853006
sq0.3281075027995521
it0.3142857142857143
ro0.3142857142857143
sv0.28994082840236685
et0.2805755395683453
cs0.2583436341161928
sl0.2583436341161928
lt0.22580645161290325
hu0.20424403183023873
pl0.1836734693877551
sk0.18032786885245902
lv0.16897506925207756
hr0.16201117318435754
is0.13294797687861273
tr0.11764705882352942
fi0.1111111111111111
reliabletrue
passestrue
10
name"Selvi"
dialogue"Mainne kaha na! Kuch galat tha! Par aap sun nahi rahe."
detectedLang"tl"
heavyLang"tl"
scores
tl0.5655080213903744
lv0.4953416149068323
sv0.4298245614035088
fr0.4206773618538324
ro0.40693430656934304
yo0.39478584729981375
sq0.3737957610789981
en0.36647173489278756
fi0.35000000000000003
eu0.336734693877551
sk0.32150313152400833
pl0.3200836820083682
cs0.3186582809224318
sl0.3186582809224318
hr0.3157894736842105
de0.3143459915611814
et0.3114406779661017
pt0.29805615550755943
nl0.2545871559633027
no0.24418604651162787
da0.22248803827751198
lt0.19154228855721395
es0.18952618453865336
ms0.18952618453865336
ca0.1875
tr0.1875
reliablefalse
passesfalse
11
name"Hunter"
dialogue"Hold on. Hunter. Yeah? You found the truck? Okay, I'm coming right now."
detectedLang"en"
heavyLang"en"
scores
en0.8060344827586207
tl0.7164461247637052
fr0.5258166491043204
da0.48805460750853247
ca0.4230769230769231
de0.4230769230769231
no0.4163424124513619
yo0.3626062322946175
nl0.3487698986975398
it0.25864909390444807
pt0.25864909390444807
ro0.25864909390444807
et0.2549668874172185
cs0.2537313432835821
fi0.25
sv0.2474916387959866
ms0.23339011925042585
sq0.23339011925042585
es0.18330308529945552
hr0.16356877323420074
hi0.15730337078651685
pl0.15730337078651685
sk0.14285714285714285
sl0.11591355599214145
tr0.11591355599214145
reliabletrue
passestrue
12
name"Hunter"
dialogue"We're not done. Stay in town. I'll find someone who speaks... whatever that is."
detectedLang"en"
heavyLang"en"
scores
en0.8237476808905381
tl0.4825708061002179
nl0.45899772209567197
yo0.30453879941434847
sv0.291044776119403
da0.28785607196401797
hu0.2448330683624801
sl0.2448330683624801
pt0.24000000000000002
de0.23633440514469453
it0.23633440514469453
ro0.23014586709886548
et0.2263843648208469
is0.16225749559082892
no0.15630550621669628
az0.15026833631484796
pl0.15026833631484796
es0.1410488245931284
tr0.1410488245931284
ms0.13636363636363635
fr0.1316270566727605
reliabletrue
passestrue
13
name"Selvi"
dialogue"Bhagwan ka shukr hai. Woh ja raha hai."
detectedLang"et"
heavyLang"cs"
scores
et0.660633484162896
lv0.5445344129554657
sq0.49209932279909707
yo0.44717444717444715
pl0.42159383033419023
vi0.4109947643979057
fi0.40476190476190477
tl0.3343195266272189
ca0.3263473053892215
it0.30769230769230765
de0.281150159744409
sk0.27184466019417475
da0.26229508196721313
sl0.26229508196721313
sv0.25
reliabletrue
passesfalse