Run: 2026-04-25-01KQ2GZ2Y27B2D0MTJDDATGJMW

Run Details

Model:
DeepSeek V4 Pro (Reasoning)
Test:
Language Writing
Scenario:
Character dialogue (Hindi) in a story
Duration:
52.4s
Cost:
$0.001564
Provider:
DeepSeek

Evaluation summary

Score Evaluator
Details Link
53.85% 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 tha... mujhe samajh nahi aa raha... woh aadmi, woh raat ke andhere mein..." Hunter: "Excuse me, ma'am. I'm Detective Hunter. You were near the old orchard last night? Did you see anything?" Selvi: "Orchard? Haan, main wahan thi. Par main kuch galat nahi kiya. Woh log... woh aadmi ko pakad ke le gaye." Hunter: "I... I don't speak... that language. You saw a man? He was taken?" Selvi: "Aap samjhe? Haan, ek aadmi. Woh cheekh raha tha, aur doosre log use kheench rahe the. Main chhip gayi." Hunter: "You hid? From who? How many people? Can you show me on your camera?" Selvi: "Tasveer? Haan, camera mein hai. Yeh dekho." Hunter: "That's... that's Jason Miller's jacket. And those shadows—are those two men? Can you make the picture bigger?" Selvi: "Zoom karna hai? Is button se... Dekho, yeh teesra aadmi hai, haath mein kuch tha." Hunter: "A weapon? A knife? Wait... is that a tattoo on his arm? I need to get this to the station." (Phone rings) Hunter: "Hunter. ... Yes. Now? I'll be right there." (Hangs up.) "I have to go. Stay here—someone will come who speaks... I'll find someone. Don't leave this café." Selvi: "Jaldi aaiyega. Mujhe dar lag raha hai." Hunter: "Don't worry. Just wait."
created_at"2026-04-25T14:33:43.624Z" 4/25/2026, 2:33:43 PM
model"deepseek/deepseek-v4-pro-20260423"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency949
moderation_latency(null)
generation_time52338
tokens_prompt315
tokens_completion1725
native_tokens_prompt268
native_tokens_completion1781
native_tokens_completion_images(null)
native_tokens_reasoning1394
native_tokens_cached256
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"
usage0.00156397
router(null)
provider_responses
0
endpoint_id"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id"ab11c25f-a762-4730-93b8-d38627276c27"
is_byokfalse
latency280
model_permaslug"deepseek/deepseek-v4-pro-20260423"
provider_name"DeepSeek"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer(null)
request_id"req-1777127623-Rf36ql3SV7V9LR6jT6tO"
session_id(null)
api_type"completions"
id"gen-1777127623-g5qTClEbvru3a5cu7dKQ"
upstream_id"ab11c25f-a762-4730-93b8-d38627276c27"
total_cost0.00156397
cache_discount0.00010208
upstream_inference_cost0
provider_name"DeepSeek"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
53.85% Parse dialogue n/a
dialogue
0
name"Selvi"
dialogue"Kya hua tha... mujhe samajh nahi aa raha... woh aadmi, woh raat ke andhere mein..."
detectedLang"et"
heavyLang"de"
scores
et0.35251798561151076
no0.3253373313343328
ms0.31921331316187596
de0.3108728943338438
sq0.3023255813953488
eu0.2682926829268293
en0.22813036020583194
fi0.18772563176895307
cs0.18625678119349007
is0.1847826086956522
lv0.1773308957952468
tl0.1773308957952468
yo0.16356877323420074
da0.16044776119402984
sv0.15094339622641512
reliablefalse
passesfalse
1
name"Hunter"
dialogue"Excuse me, ma'am. I'm Detective Hunter. You were near the old orchard last night? Did you see anything?"
detectedLang"en"
heavyLang"en"
scores
en0.7890979883192731
tl0.6185446009389671
fr0.47283049472830496
no0.4313210848643919
sq0.4237588652482269
nl0.41704035874439455
et0.344758064516129
de0.3305870236869207
pt0.3305870236869207
da0.3285123966942149
it0.3271221532091097
ro0.3236212278876171
ms0.3150684931506849
es0.3010752688172043
ca0.2688413948256468
sv0.24855491329479767
sl0.2476851851851852
yo0.21780986762936222
cs0.1875
fi0.10344827586206896
hr0.09344490934449094
tr0.08321579689703808
reliabletrue
passestrue
2
name"Selvi"
dialogue"Orchard? Haan, main wahan thi. Par main kuch galat nahi kiya. Woh log... woh aadmi ko pakad ke le gaye."
detectedLang"tl"
heavyLang"de"
scores
tl0.5521806853582555
ms0.5366639806607574
fr0.4523809523809524
lv0.4401168451801363
yo0.3722707423580786
eu0.31952662721893493
ro0.3154761904761905
sl0.29706601466992666
es0.2532467532467532
lt0.24639580602883354
en0.23230974632843793
sv0.22611036339165547
vi0.21232876712328766
de0.2101648351648352
it0.20138888888888887
cs0.15191740412979352
hu0.14561664190193166
da0.13922155688622756
fi0.13273001508295626
ca0.11538461538461538
et0.11538461538461538
nl0.11538461538461538
no0.11538461538461538
tr0.11538461538461538
reliablefalse
passesfalse
3
name"Hunter"
dialogue"I... I don't speak... that language. You saw a man? He was taken?"
detectedLang"en"
heavyLang"en"
scores
en0.8234316576651434
tl0.6082949308755761
nl0.5473908413205538
no0.54004329004329
yo0.5186862967157418
da0.5011737089201878
ro0.4946492271105826
sv0.49404761904761907
de0.47788697788697787
ca0.46202531645569617
cs0.4256756756756757
lt0.41540577716643745
sk0.39716312056737585
hr0.371301775147929
ms0.37037037037037035
lv0.36186186186186187
it0.3609022556390977
pl0.35213414634146345
hu0.3441358024691358
is0.3431221020092735
es0.3369734789391576
sq0.3264659270998415
et0.32432432432432434
fr0.3055555555555556
sl0.28330522765598654
fi0.2659758203799654
eu0.2582897033158813
tr0.256993006993007
pt0.247787610619469
az0.23835125448028674
vi0.23835125448028674
be0.1414141414141414
uk0.1290983606557377
reliabletrue
passestrue
4
name"Selvi"
dialogue"Aap samjhe? Haan, ek aadmi. Woh cheekh raha tha, aur doosre log use kheench rahe the. Main chhip gayi."
detectedLang"en"
heavyLang"en"
scores
en0.5074862096138691
tl0.2460796139927624
sq0.2378048780487805
nl0.22744128553770088
ms0.2264851485148515
fr0.20986093552465232
et0.18407310704960833
tr0.1519674355495251
yo0.14617486338797814
ro0.14383561643835618
no0.13194444444444445
da0.11095305832147938
de0.11095305832147938
sv0.11095305832147938
reliablefalse
passesfalse
5
name"Hunter"
dialogue"You hid? From who? How many people? Can you show me on your camera?"
detectedLang"en"
heavyLang"en"
scores
en0.8191899710703955
tl0.6208291203235591
ca0.4257274119448699
fr0.423963133640553
et0.39903846153846156
it0.38825448613376834
nl0.3872549019607844
ms0.3842364532019704
fi0.375
es0.34895833333333337
pt0.3055555555555556
ro0.2964352720450282
cs0.28977272727272724
sq0.2829827915869981
no0.19527896995708155
hr0.19006479481641467
sl0.19006479481641467
hi0.1830065359477124
pl0.1830065359477124
sv0.17943107221006563
az0.17035398230088497
tr0.17035398230088497
sk0.16666666666666666
yo0.16666666666666666
de0.1610738255033557
reliabletrue
passestrue
6
name"Selvi"
dialogue"Tasveer? Haan, camera mein hai. Yeh dekho."
detectedLang"it"
heavyLang"ber"
scores
it0.5078740157480316
de0.44071588366890374
nl0.43566591422121903
ro0.3872549019607844
vi0.3857493857493857
ca0.28977272727272724
es0.28366762177650434
sv0.24698795180722888
en0.2331288343558282
fr0.2331288343558282
ms0.22360248447204967
tl0.22360248447204967
reliablefalse
passesfalse
7
name"Hunter"
dialogue"That's... that's Jason Miller's jacket. And those shadows—are those two men? Can you make the picture bigger?"
detectedLang"en"
heavyLang"en"
scores
en0.8081056186674854
tl0.6127633209417597
sv0.4186046511627907
no0.4030563514804203
da0.3926141885325559
fr0.3842364532019704
sq0.35831622176591377
yo0.30709534368070956
nl0.28734321550741165
tr0.27494199535962877
de0.26985981308411217
ro0.26556991774383076
is0.21972534332084895
ca0.21383647798742136
az0.20986093552465232
it0.19041450777202074
eu0.16666666666666666
ja0.13793103448275862
et0.1355463347164592
hu0.12464985994397759
es0.12095639943741208
hr0.12095639943741208
sl0.11347517730496455
cs0.11095305832147938
ms0.11095305832147938
fi0.10714285714285714
reliabletrue
passestrue
8
name"Selvi"
dialogue"Zoom karna hai? Is button se... Dekho, yeh teesra aadmi hai, haath mein kuch tha."
detectedLang"en"
heavyLang"vi"
scores
en0.4026284348864994
it0.3548387096774194
nl0.33065595716198126
sq0.31412894375857336
yo0.31224209078404397
sv0.302649930264993
sl0.28977272727272724
de0.28876244665718354
ro0.2774566473988439
is0.27641099855282203
ms0.27219796215429404
tl0.25595238095238093
vi0.2389649923896499
hu0.23547400611620795
no0.22720247295208654
cs0.21383647798742136
hr0.21011058451816747
es0.20634920634920634
pt0.19224555735056545
pl0.18962722852512154
fr0.17898193760262726
fi0.16943521594684383
ca0.1610738255033557
da0.15540540540540537
reliablefalse
passesfalse
9
name"Hunter"
dialogue"A weapon? A knife? Wait... is that a tattoo on his arm? I need to get this to the station."
detectedLang"en"
heavyLang"en"
scores
en0.8016622591613147
tl0.6389270976616231
yo0.6040723981900453
fr0.5308310991957105
da0.5244565217391305
no0.5231607629427792
hr0.49664429530201337
pl0.4942196531791907
cs0.49078564500484967
et0.47657028913260224
sk0.4712990936555891
hu0.4696969696969697
nl0.467005076142132
sv0.467005076142132
ca0.41536748329621387
sq0.4006849315068493
it0.3951612903225807
is0.38596491228070173
lt0.38162544169611307
lv0.37722419928825623
ro0.36823104693140796
fi0.3597560975609756
sl0.3429286608260325
de0.32778489116517284
tr0.2818057455540356
ms0.27586206896551724
az0.27184466019417475
pt0.21052631578947367
vi0.20212765957446807
es0.2009132420091324
hi0.13793103448275862
zh0.12790697674418602
be0.11764705882352942
eu0.11764705882352942
uk0.10714285714285714
reliabletrue
passestrue
10
name"Hunter"
dialogue"I have to go. Stay here—someone will come who speaks... I'll find someone. Don't leave this café."
detectedLang"en"
heavyLang"en"
scores
en0.8103448275862069
tl0.4850187265917603
da0.47115384615384615
pl0.4015233949945593
yo0.35370152761457113
pt0.3357487922705314
it0.3349455864570738
hr0.3167701863354037
no0.3159203980099502
cs0.3002544529262086
sq0.298469387755102
sk0.27055702917771884
et0.26861702127659576
nl0.26666666666666666
lv0.25170068027210885
lt0.2329149232914923
ca0.2005813953488372
sv0.2005813953488372
sl0.18032786885245902
de0.16158536585365854
ro0.140625
es0.12420382165605094
be0.11290322580645161
tr0.11290322580645161
hu0.1085899513776337
az0.10277324632952692
is0.10277324632952692
uk0.10277324632952692
vi0.10277324632952692
reliabletrue
passestrue
11
name"Selvi"
dialogue"Jaldi aaiyega. Mujhe dar lag raha hai."
detectedLang"et"
heavyLang"is"
scores
et0.4669509594882729
vi0.3857493857493857
ro0.33862433862433866
lt0.33510638297872336
eu0.29775280898876405
it0.2857142857142857
no0.2816091954022989
is0.2732558139534884
es0.2711370262390671
pt0.2711370262390671
sv0.2711370262390671
de0.23547400611620795
nl0.23547400611620795
reliablefalse
passesfalse
12
name"Hunter"
dialogue"Don't worry. Just wait."
detectedLang"en"
heavyLang"en"
scores
en0.8138957816377173
et0.40476190476190477
sv0.40476190476190477
tl0.39999999999999997
ca0.33920704845814975
reliabletrue
passestrue