Run: 2026-04-25-01KQ2J2CS8Y7DFZM1YERZFTYD9

Run Details

Model:
DeepSeek V4 Flash (Reasoning)
Test:
Language Writing
Scenario:
Character dialogue (Hindi) in a story
Duration:
19.8s
Cost:
$0.000393
Provider:
DeepSeek

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 – Scene: Café in Alborn, MN** **Selvi:** (Looking at camera screen, murmurs in Hindi) *"Yeh tasveer... yeh sab kuch galat hai. Main dekh kar dar gayi."* **Hunter:** (Approaches, clears throat) Excuse me, miss? I’m Detective Hunter. I need to ask you about the incident near the apple orchard last night. Did you see anything? **Selvi:** (Lifts head, startled; speaks shakily in Hindi) *"Main samajh nahi pa rahi hoon aapki baat. Lekin haan, mainne kuch dekha. Woh log... gayab ho gaye."* **Hunter:** (Frowns, shakes head) I’m sorry, I don’t follow. Do you speak English? (Pauses, points at her camera) Did you take photos? Something happen? **Selvi:** (Nods vigorously, points at camera, then at the direction of the orchard; voice trembling in Hindi) *"Haan, wahan. Andhera tha. Achanak se woh log ruk gaye, phir... nahi the. Mainne photo lee."* **Hunter:** (Sighs, rubs forehead) Okay, I’m not getting this. Let me try… (Gestures with hands, slow) You. Saw. Something. Bad. Yes? (Points at camera) Show me? **Selvi:** (Opens camera, shows him an image; speaks sorrowfully in Hindi) *"Yeh lo. Lekin ismein kuch nahi dikhta. Jaise woh mita diye gaye."* **Hunter:** (Squints at screen, then at her) That’s just a blurry field. Look, I need to know—(His phone rings) Hang on. (Answers call) Detective Hunter. … Right. On my way. **Hunter:** (Hangs up, looks at Selvi) I have to go. Stay safe. If you remember anything, come to the station. (Turns and leaves quickly) **Selvi:** (Calls after him in Hindi, desperate) *"Ruko! Main aapko samjha nahi paai! Yeh to sirf shuruaat hai!"* (Hunter exits without looking back. Selvi stares at her camera, troubled.)
created_at"2026-04-25T14:53:00.589Z" 4/25/2026, 2:53:00 PM
model"deepseek/deepseek-v4-flash-20260423"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency526
moderation_latency(null)
generation_time19107
tokens_prompt315
tokens_completion1410
native_tokens_prompt268
native_tokens_completion1372
native_tokens_completion_images(null)
native_tokens_reasoning859
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"
usage0.000393008
router(null)
provider_responses
0
endpoint_id"722e0746-2034-4d6e-a08f-e6271849ee9e"
id"79c6b833-1e3f-4b31-8db4-c7edb5e0787a"
is_byokfalse
latency281
model_permaslug"deepseek/deepseek-v4-flash-20260423"
provider_name"DeepSeek"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer(null)
request_id"req-1777128780-KQTeAWxWeDGgUJAICsp1"
session_id(null)
api_type"completions"
id"gen-1777128780-jEWq04aXkdtv4rtpKZoy"
upstream_id"79c6b833-1e3f-4b31-8db4-c7edb5e0787a"
total_cost0.000393008
cache_discount0.000028672
upstream_inference_cost0
provider_name"DeepSeek"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
50.00% Parse dialogue n/a
dialogue
0
name"Selvi"
dialogue"Yeh tasveer... yeh sab kuch galat hai. Main dekh kar dar gayi."
detectedLang"ro"
heavyLang"ber"
scores
ro0.4619205298013245
tr0.35000000000000003
es0.34210526315789475
tl0.3394308943089431
vi0.3257261410788381
sl0.32432432432432434
lt0.2793791574279379
nl0.2647058823529412
it0.23529411764705882
en0.23349056603773585
pt0.22248803827751198
fr0.21307506053268765
de0.1935483870967742
lv0.18952618453865336
ms0.18952618453865336
ca0.1875
et0.1875
sv0.1875
reliablefalse
passesfalse
1
name"Hunter"
dialogue"Excuse me, miss? I’m Detective Hunter. I need to ask you about the incident near the apple orchard last night. Did you see anything?"
detectedLang"en"
heavyLang"en"
scores
en0.8003194888178914
tl0.6409519901518259
fr0.5244565217391305
no0.49942791762013733
nl0.4575325480471171
sq0.45482866043613707
da0.438382541720154
et0.4347545219638243
it0.42959582790091266
ro0.4162775183455637
de0.40476190476190477
ca0.403544648943422
es0.3953006219765031
cs0.3691420331651046
sv0.358974358974359
sl0.34652725914861837
pt0.33962264150943394
yo0.31640625
hr0.303343949044586
sk0.27566225165562913
pl0.2744610281923715
ms0.25468483816013626
lt0.2052679382379655
az0.19205909510618652
lv0.17452830188679244
tr0.12848605577689243
hu0.12587412587412586
fi0.07894736842105263
be0.07407407407407407
is0.06716417910447761
uk0.06716417910447761
vi0.06716417910447761
reliabletrue
passestrue
2
name"Selvi"
dialogue"Main samajh nahi pa rahi hoon aapki baat. Lekin haan, mainne kuch dekha. Woh log... gayab ho gaye."
detectedLang"fi"
heavyLang"tl"
scores
fi0.38335046248715315
tl0.35064935064935066
no0.34497816593886466
eu0.34210526315789475
lv0.3265993265993266
de0.27448609431680776
is0.24050632911392408
en0.2376111817026684
fr0.23076923076923078
et0.22680412371134018
ms0.22680412371134018
sv0.2073976221928666
sl0.2
ca0.16666666666666666
sk0.15611814345991562
hr0.15254237288135594
cs0.1501416430594901
it0.1501416430594901
sq0.1501416430594901
yo0.1465149359886202
da0.12536443148688048
lt0.12152269399707175
ro0.10714285714285714
reliablefalse
passesfalse
3
name"Hunter"
dialogue"I’m sorry, I don’t follow. Do you speak English? Did you take photos? Something happen?"
detectedLang"en"
heavyLang"en"
scores
en0.8096446700507615
tl0.6723102129983616
pt0.40828402366863903
hr0.35553168635875404
no0.35135135135135137
cs0.34497816593886466
sv0.3413830954994512
da0.3333333333333333
it0.3281075027995521
pl0.3095512082853855
sq0.29494712103407755
de0.27884615384615385
ca0.2583436341161928
sk0.2537313432835821
sl0.24812030075187969
fr0.23273657289002556
vi0.2248062015503876
nl0.2227979274611399
yo0.21568627450980393
ro0.2125984251968504
hu0.21156373193166886
es0.20844327176781002
ms0.2
lt0.19246298788694483
lv0.18256130790190736
hi0.1137370753323486
be0.1044776119402985
tr0.1044776119402985
az0.09502262443438914
et0.09502262443438914
is0.09502262443438914
uk0.09502262443438914
reliabletrue
passestrue
4
name"Selvi"
dialogue"Haan, wahan. Andhera tha. Achanak se woh log ruk gaye, phir... nahi the. Mainne photo lee."
detectedLang"ms"
heavyLang"de"
scores
ms0.5485812553740327
fr0.520109689213894
tl0.47657028913260224
en0.45764462809917356
eu0.42560175054704596
fi0.4101123595505618
sq0.3689903846153846
no0.34375
sv0.31462140992167104
cs0.29906542056074764
pt0.29435483870967744
hr0.29245283018867924
yo0.2895805142083897
ro0.2677824267782427
da0.2446043165467626
de0.22106824925816024
sl0.2009132420091324
es0.1984732824427481
hu0.15865384615384615
it0.15594855305466235
ca0.15458937198067632
lv0.1435562805872757
nl0.13793103448275862
hi0.12790697674418602
tr0.125
et0.12060301507537688
reliablefalse
passesfalse
5
name"Hunter"
dialogue"Okay, I’m not getting this. Let me try… You. Saw. Something. Bad. Yes? Show me?"
detectedLang"en"
heavyLang"en"
scores
en0.8108448928121058
tl0.6616541353383458
nl0.44649446494464945
ms0.4396014943960149
pt0.40789473684210525
it0.35437589670014347
sl0.3001555209953344
cs0.296875
de0.2857142857142857
es0.2857142857142857
no0.27999999999999997
sq0.2474916387959866
et0.17431192660550457
fr0.16820702402957485
sv0.15094339622641512
tr0.14772727272727273
da0.14611005692599618
fi0.14285714285714285
is0.14285714285714285
hr0.12959381044487428
ro0.12959381044487428
reliabletrue
passestrue
6
name"Selvi"
dialogue"Yeh lo. Lekin ismein kuch nahi dikhta. Jaise woh mita diye gaye."
detectedLang"eu"
heavyLang"tl"
scores
eu0.43820224719101125
es0.25925925925925924
hu0.25650557620817843
yo0.25512104283054005
it0.23809523809523808
tr0.23809523809523808
fr0.21414538310412573
fi0.1902834008097166
ca0.18533604887983707
vi0.18533604887983707
is0.18032786885245902
pt0.17355371900826447
en0.16317991631799164
et0.16317991631799164
reliablefalse
passesfalse
7
name"Hunter"
dialogue"That’s just a blurry field. Look, I need to know— Hang on. Detective Hunter. … Right. On my way."
detectedLang"en"
heavyLang"en"
scores
en0.8084584737971193
tl0.6527777777777778
ca0.5243531202435312
cs0.4902120717781403
it0.4796003330557868
fr0.4747899159663866
no0.4707874682472481
da0.4703389830508474
pl0.4644387317909169
ro0.46351931330472107
hr0.4551002615518745
et0.45462478184991273
sk0.44196428571428575
yo0.4404655326768129
sq0.4228993536472761
sv0.4131455399061033
nl0.3854473942969518
pt0.37374749498997994
sl0.3503118503118503
de0.3336886993603412
es0.3315508021390375
lv0.28977272727272724
lt0.28489702517162474
hu0.26297169811320753
fi0.2541766109785203
tr0.24789410348977134
is0.18086500655307994
az0.17546174142480211
vi0.17546174142480211
ms0.16331994645247658
hi0.11847672778561354
be0.10071942446043164
eu0.10071942446043164
uk0.09156976744186046
reliabletrue
passestrue
8
name"Hunter"
dialogue"I have to go. Stay safe. If you remember anything, come to the station."
detectedLang"en"
heavyLang"en"
scores
en0.8302527348170502
tl0.6525096525096525
da0.6439873417721518
yo0.6259351620947631
no0.601063829787234
sv0.5897903372835005
pl0.4897959183673469
nl0.4809688581314879
sk0.46492271105826394
fr0.46428571428571425
ms0.4630071599045346
it0.4578313253012048
sq0.4571773220747889
cs0.4558645707376058
de0.43396226415094336
hr0.4140625
sl0.4094488188976378
lv0.3553008595988539
hu0.3515850144092219
lt0.34971098265895956
is0.3253373313343328
et0.30769230769230765
ro0.2706645056726094
ca0.23469387755102045
tr0.2227979274611399
az0.21875
fi0.15413533834586465
zh0.14611005692599618
be0.1346153846153846
uk0.12280701754385964
vi0.12280701754385964
reliabletrue
passestrue
9
name"Selvi"
dialogue"Ruko! Main aapko samjha nahi paai! Yeh to sirf shuruaat hai!"
detectedLang"en"
heavyLang"tl"
scores
en0.4075829383886255
eu0.3055555555555556
vi0.2951127819548872
yo0.267578125
pl0.2647058823529412
sk0.26035502958579887
cs0.258893280632411
lv0.2454728370221328
sl0.24395161290322584
hr0.23625254582484725
no0.22520661157024793
da0.21711899791231734
lt0.21711899791231734
it0.21052631578947367
fr0.19006479481641467
tl0.19006479481641467
de0.17218543046357618
reliablefalse
passesfalse