Run: 2026-09-03-01M1KBYMBSDMF2NXHTMWYKVEW0

Run Details

Model:
DeepSeek V4 Pro 0813 (Reasoning, High)
Test:
Language Writing
Scenario:
Character dialogue (Hindi) in a story
Duration:
2m 2s
Cost:
$0.030736
Provider:
SiliconFlow

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
VOICE SHEET *(Selvi’s lines are in Hindi; translations are in parentheses.)* Selvi: (startled, in Hindi) "Aap... aap mujhse kya poochh rahe hain? Main sirf tasveerein le rahi thi." (*What... what are you asking me? I was just taking pictures.*) Hunter: (stares, confused) "I’m sorry—I don’t understand. Do you speak English? English?" Selvi: (shaking her head, in Hindi) "Mujhe English nahi aati." (*I don’t know English.*) Hunter: (sighs) "Okay. Look." (points at her camera) "Photo. Did you take photos?" Selvi: (gripping the camera, in Hindi) "Haan... maine bahut saari tasveerein li. Par woh aadmi... woh... woh jaise... gayab ho gaya." (*Yes... I took many pictures. But that man... he... he just... vanished.*) Hunter: "I keep hearing ‘aadmi.’ Man. You saw the man?" Selvi: (nodding, in Hindi) "Haan, aadmi. Woh ped ke paas tha. Maine uski ek tasveer li. Phir... phir woh nahin tha." (*Yes, the man. He was by the tree. I took a picture of him. Then... then he wasn’t there.*) Hunter: "Show me. The camera. Show me the photo." Selvi: (turns the camera screen toward him, in Hindi) "Yeh dekhiye. Yeh us aadmi ki aakhri tasveer hai." (*Look. This is the last picture of that man.*) Hunter: (leaning in) "That’s him. That’s the missing man. When did you take this?" Selvi: (in Hindi) "Parso raat... tyohaar ke baad. Uske baad sab kuch badal gaya." (*Night before last... after the festival. After that everything changed.*) Hunter: "I can’t understand you, but this photo is important. I need to take a copy. Copy—do you understand?" Selvi: (in Hindi) "Aap le sakte hain. Bas... mujhe yeh sab ajeeb lag raha hai." (*You can take it. Just... all this feels strange to me.*) Hunter: (phone buzzes; holds up a finger) "Hold on." (answers) "Hunter. ... Yeah. ... Now? ... I’m at the café with a witness. ... Understood. On my way." (hangs up; to Selvi, pointing at the ground) "I have to go. Stay here. I’ll get a translator. Don’t leave." Selvi: (in Hindi) "Theek hai... par jaldi laaiye. Mujhe yahan akele dar lag raha hai." (*Okay... but come quickly. I’m scared here alone.*) Hunter: "I still don’t know what you’re saying. Just wait. Don’t leave."
created_at"2026-09-03T10:10:09.416Z" 9/3/2026, 10:10:09 AM
model"deepseek/deepseek-v4-pro-20260813"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency838
moderation_latency(null)
generation_time122387
tokens_prompt302
tokens_completion7411
native_tokens_prompt347
native_tokens_completion7646
native_tokens_completion_images(null)
native_tokens_reasoning6961
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
num_fetches(null)
web_search_engine(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
service_tier(null)
usage0.0307362
router(null)
user_agent"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer(null)
request_id"req-1788430209-4r1kplkr9ogitgEvWmCx"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1788430209-EydmJnhkvR7x9gBbyZ3M"
upstream_id"chatcmpl-7a29a0bd-5889-4e1a-a57d-b6bc83055e52"
provider_responses
0
endpoint_id"65367950-3b6c-4abd-9cb0-d553a47de6d9"
id"chatcmpl-7a29a0bd-5889-4e1a-a57d-b6bc83055e52"
is_byokfalse
latency838
model_permaslug"deepseek/deepseek-v4-pro-20260813"
provider_name"SiliconFlow"
status200
total_cost0.0307362
cache_discount(null)
upstream_inference_cost0
provider_name"SiliconFlow"
response_cache_source_id(null)
data_region"global"
workspace_id"97e315e5-d303-487d-83c1-83180e8a13d4"

Evaluation details

Result Evaluator Details Meta Data
50.00% Parse dialogue n/a
dialogue
0
name"Selvi"
dialogue"Aap... aap mujhse kya poochh rahe hain? Main sirf tasveerein le rahi thi."
detectedLang"fr"
heavyLang"vi"
scores
fr0.3902439024390244
de0.2805755395683453
vi0.27927927927927926
it0.26605504587155965
eu0.25650557620817843
yo0.23371647509578544
es0.22928709055876687
sl0.2263056092843327
ro0.22178988326848248
en0.19839679358717435
hu0.19678714859437751
is0.1902834008097166
nl0.18032786885245902
reliablefalse
passesfalse
1
name"Hunter"
dialogue"I’m sorry—I don’t understand. Do you speak English? English?"
detectedLang"en"
heavyLang"en"
scores
en0.8052580331061344
tl0.6592844974446337
no0.5670995670995671
da0.5614035087719298
sv0.51278928136419
cs0.5
pl0.464524765729585
hr0.4528043775649795
sk0.4227994227994228
de0.39849624060150374
pt0.3902439024390244
sq0.38556067588325654
ro0.3710691823899371
it0.34959349593495936
nl0.3079584775086505
vi0.30313588850174217
yo0.2920353982300885
ca0.25650557620817843
is0.25512104283054005
sl0.23076923076923078
ms0.15254237288135594
be0.14893617021276595
tr0.14893617021276595
hu0.14346895074946467
az0.13606911447084233
et0.13606911447084233
lt0.13606911447084233
lv0.13606911447084233
uk0.13606911447084233
reliabletrue
passestrue
2
name"Selvi"
dialogue"Mujhe English nahi aati."
detectedLang"en"
heavyLang"tl"
scores
en0.5867768595041323
eu0.5238095238095238
no0.35344827586206895
da0.32432432432432434
de0.32432432432432434
hr0.32432432432432434
ms0.32432432432432434
ro0.32432432432432434
sv0.32432432432432434
reliabletrue
passesfalse
3
name"Hunter"
dialogue"Photo. Did you take photos?"
detectedLang"en"
heavyLang"en"
scores
en0.8049414824447333
fr0.6428571428571429
tl0.608355091383812
cs0.5253164556962026
es0.34782608695652173
lt0.34782608695652173
pt0.34782608695652173
sl0.34210526315789475
hi0.33920704845814975
ca0.3212669683257918
de0.3212669683257918
lv0.3212669683257918
nl0.3212669683257918
reliabletrue
passestrue
4
name"Selvi"
dialogue"Haan... maine bahut saari tasveerein li. Par woh aadmi... woh... woh jaise... gayab ho gaya."
detectedLang"fr"
heavyLang"de"
scores
fr0.4675456389452333
et0.4496855345911949
fi0.38524590163934425
de0.36594202898550726
tl0.34944237918215615
lv0.31640625
en0.31462140992167104
ca0.3055555555555556
ro0.29624664879356566
cs0.2647058823529412
it0.2647058823529412
no0.17452830188679244
sk0.17452830188679244
sq0.16666666666666666
hr0.16134185303514376
ms0.16
is0.1518578352180937
da0.15048543689320387
sv0.15048543689320387
nl0.1435562805872757
lt0.12353923205342236
pl0.12353923205342236
reliablefalse
passesfalse
5
name"Hunter"
dialogue"I keep hearing ‘aadmi.’ Man. You saw the man?"
detectedLang"en"
heavyLang"en"
scores
en0.7950819672131147
tl0.6958637469586375
da0.6513249651324965
sv0.6463932107496464
no0.6448863636363635
nl0.5471014492753623
ms0.5192307692307693
sq0.4588744588744588
de0.44196428571428575
yo0.4369369369369369
cs0.42263279445727486
lv0.40617577197149646
lt0.3857493857493857
hr0.3573264781491003
ca0.3556701030927836
pl0.33510638297872336
it0.3150684931506849
ro0.2647058823529412
fr0.2378048780487805
sk0.22360248447204967
be0.21875
tr0.21875
hu0.21135646687697163
az0.20127795527156547
et0.20127795527156547
is0.20127795527156547
uk0.20127795527156547
vi0.20127795527156547
reliabletrue
passestrue
6
name"Selvi"
dialogue"Haan, aadmi. Woh ped ke paas tha. Maine uski ek tasveer li. Phir... phir woh nahin tha."
detectedLang"tl"
heavyLang"de"
scores
tl0.4102228047182176
ro0.3293591654247392
nl0.3253373313343328
fr0.3161094224924012
cs0.29245283018867924
en0.265905383360522
et0.265905383360522
fi0.265905383360522
de0.24623115577889448
eu0.24623115577889448
ms0.23728813559322032
sq0.20634920634920634
tr0.199288256227758
ca0.19786096256684493
hr0.18330308529945552
lv0.16356877323420074
yo0.16356877323420074
it0.15572232645403375
lt0.1412213740458015
pl0.1412213740458015
reliablefalse
passesfalse
7
name"Hunter"
dialogue"Show me. The camera. Show me the photo."
detectedLang"en"
heavyLang"en"
scores
en0.7776365946632783
fr0.7131147540983607
tl0.6698113207547169
nl0.6471774193548386
it0.576271186440678
ms0.5721271393643031
sq0.5635910224438903
es0.5345744680851064
no0.515235457063712
pt0.4852941176470589
sv0.47761194029850745
ro0.47447447447447455
yo0.3794326241134752
ca0.36823104693140796
et0.35185185185185186
cs0.3346007604562738
sl0.3346007604562738
da0.308300395256917
hi0.3055555555555556
fi0.3
de0.29149797570850206
reliabletrue
passestrue
8
name"Selvi"
dialogue"Yeh dekhiye. Yeh us aadmi ki aakhri tasveer hai."
detectedLang"vi"
heavyLang"ber"
scores
vi0.3435448577680525
az0.34210526315789475
sl0.33774834437086093
hu0.28741092636579574
nl0.2805755395683453
yo0.2736077481840194
en0.25925925925925924
tr0.25742574257425743
it0.25
de0.23273657289002556
tl0.21875
ca0.2
es0.2
pt0.2
reliablefalse
passesfalse
9
name"Hunter"
dialogue"That’s him. That’s the missing man. When did you take this?"
detectedLang"en"
heavyLang"en"
scores
en0.8396645288603848
tl0.6713852376137512
nl0.5854591836734694
da0.5156482861400895
sv0.48083067092651754
no0.45561139028475717
de0.36647173489278756
ms0.36647173489278756
sq0.3538767395626242
it0.336734693877551
is0.3186582809224318
fr0.3157894736842105
lv0.2494226327944573
yo0.2476851851851852
lt0.2243436754176611
cs0.1935483870967742
fi0.1935483870967742
sl0.1935483870967742
ca0.181360201511335
az0.16666666666666666
et0.16666666666666666
pt0.16666666666666666
reliabletrue
passestrue
10
name"Selvi"
dialogue"Parso raat... tyohaar ke baad. Uske baad sab kuch badal gaya."
detectedLang"ms"
heavyLang"tlh"
scores
ms0.5105421686746987
tl0.4003690036900369
pl0.344758064516129
eu0.2545871559633027
cs0.24065420560747666
yo0.21307506053268765
ca0.19154228855721395
sk0.19154228855721395
sl0.19154228855721395
reliablefalse
passesfalse
11
name"Hunter"
dialogue"I can’t understand you, but this photo is important. I need to take a copy. Copy—do you understand?"
detectedLang"en"
heavyLang"en"
scores
en0.8161120840630472
tl0.6773202212661339
no0.5911214953271028
da0.5895230648944488
cs0.5885579937304075
fr0.569672131147541
pl0.5278776978417267
ro0.5240253853127833
ca0.5214220601640838
sk0.5138888888888888
yo0.5075046904315197
pt0.4842829076620825
hr0.48122529644268774
sv0.4770916334661355
nl0.47657028913260224
it0.453125
sl0.43790149892933616
sq0.42622950819672134
hu0.4179600886917961
es0.38524590163934425
lt0.37869822485207094
is0.3667068757539204
et0.3354430379746835
de0.3312101910828026
lv0.3269230769230769
vi0.31729518855656696
tr0.3018617021276596
az0.20212765957446807
hi0.12790697674418602
be0.11764705882352942
eu0.11764705882352942
fi0.10714285714285714
ms0.10714285714285714
uk0.10714285714285714
reliabletrue
passestrue
12
name"Selvi"
dialogue"Aap le sakte hain. Bas... mujhe yeh sab ajeeb lag raha hai."
detectedLang"fr"
heavyLang"ber"
scores
fr0.42748091603053434
it0.3951612903225807
sq0.32553956834532377
nl0.3206521739130435
no0.3169398907103825
de0.31066176470588236
vi0.2951127819548872
et0.2732558139534884
eu0.2690058479532163
yo0.2454728370221328
es0.24089068825910928
sl0.2378048780487805
ro0.2331288343558282
ms0.21052631578947367
hu0.20718816067653278
sv0.19871794871794873
da0.16851441241685144
reliablefalse
passesfalse
13
name"Hunter"
dialogue"I have to go. Stay here. I’ll get a translator. Don’t leave."
detectedLang"en"
heavyLang"en"
scores
en0.8247422680412372
tl0.6198568872987478
pl0.5897683397683398
da0.579624134520277
hr0.5360262008733625
sq0.5159453302961275
no0.5131729667812142
cs0.5011737089201878
yo0.49704142011834324
sk0.48296836982968366
ro0.4785276073619632
ca0.4509043927648579
sl0.4378306878306878
lv0.4310575635876841
sv0.43029490616621985
lt0.4264507422402159
it0.4162087912087912
pt0.39801699716713884
et0.36661698956780925
is0.358974358974359
hu0.3441358024691358
vi0.34210526315789475
tr0.33070866141732286
es0.32965299684542587
de0.3210862619808307
nl0.32
fr0.3167202572347267
az0.3111831442463533
ms0.30098684210526316
eu0.24377224199288253
be0.1414141414141414
fi0.1290983606557377
uk0.1290983606557377
reliabletrue
passestrue
14
name"Selvi"
dialogue"Theek hai... par jaldi laaiye. Mujhe yahan akele dar lag raha hai."
detectedLang"et"
heavyLang"tl"
scores
et0.4378306878306878
nl0.4193989071038251
sv0.3044189852700491
vi0.2697594501718213
lv0.2672413793103448
fr0.2530755711775044
ms0.24511545293072823
tl0.23561151079136694
ro0.2314647377938517
lt0.22867513611615245
eu0.19962335216572505
it0.1904761904761905
no0.18738049713193117
is0.18111753371868977
da0.17953667953667954
es0.17953667953667954
pt0.17953667953667954
fi0.17153996101364524
de0.1533864541832669
reliablefalse
passesfalse
15
name"Hunter"
dialogue"I still don’t know what you’re saying. Just wait. Don’t leave."
detectedLang"en"
heavyLang"en"
scores
en0.823943661971831
sv0.49044585987261147
tl0.4490358126721763
no0.36808846761453395
da0.3620414673046252
ca0.34959349593495936
sq0.34318555008210183
is0.34210526315789475
hr0.33993399339933994
it0.3127147766323024
tr0.2982456140350877
et0.2920353982300885
lt0.24528301886792453
lv0.24528301886792453
pl0.23954372623574144
cs0.2079207920792079
ro0.1836734693877551
yo0.17864476386036962
sk0.15254237288135594
be0.14893617021276595
de0.14346895074946467
hu0.14346895074946467
nl0.14346895074946467
az0.13606911447084233
uk0.13606911447084233
vi0.13606911447084233
reliabletrue
passestrue