NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-16-01KHM5PBTXHMCNTV5R26CRHBSK
Run Details
Model:
DeepSeek V3.1
Test:
Language Writing
Scenario:
Character dialogue (German) in a story
Duration:
21.6s
Cost:
$0.000653
Provider:
SiliconFlow
Evaluation summary
Score
Evaluator
Details Link
100.00%
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="Melanie"> Melanie is a 30-year old college student on a study abroad program. Born in Germany, she is fluent in German 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 German, 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: Melanie 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 German, and Hunter looks confused. They talk for a while, until Hunter gets a call and has to leave. Return the dialogue between Melanie and Hunter as a voice sheet: Melanie: "..." Hunter: "..."
Model response
Messages
Meta
AI
**Melanie:** *[Muttering softly to herself in German, scrolling through photos on her camera]* "Seltsam. Dieses Licht... es sieht fast unnatürlich aus." (Strange. This light... it looks almost unnatural.) **Hunter:** *[Approaching the table, flashing his badge with a curt nod]* "Excuse me, ma'am. Hunter, Alborn PD. Mind if I ask you a few questions? You were taking pictures near the old mill yesterday afternoon." **Melanie:** *[Startled, looks up with wide, troubled eyes. Her voice is shaky]* "Es tut mir leid, ich verstehe nicht. Etwas ist nicht richtig dort draußen geschehen. Ich habe... ich habe Dinge gesehen." (I'm sorry, I don't understand. Something not right happened out there. I saw... I saw things.) **Hunter:** *[Frowns deeply, frustration evident on his face]* "English? Do you speak English? The mill. Yesterday. Did you see anyone?" **Melanie:** *[Shakes her head, becoming more agitated. She holds up her camera, pointing to it emphatically]* "Die Bilder! In den Bildern! Das ist nicht mein Fehler, oder? Das ist echt?" (The pictures! In the pictures! This is not my mistake, right? This is real?) **Hunter:** *[Leans in, trying to decipher her meaning, his tone softening slightly]* "Pictures? Okay, pictures. Can I see?" *[He gestures to the camera.]* **Melanie:** *[Nods vigorously, her hands trembling as she turns the camera screen toward him. She points to a specific image.]* "Sehen Sie? Dieser Schatten... er hatte keine... keine richtige Form." (See? This shadow... it had no... no proper shape.) **Hunter:** *[Squints at the photo of the mill, seeing nothing out of the ordinary to his eyes]* "It's a shadow, ma'am. Look, if you saw something—" **Hunter:** *[He's cut off by the sharp ring of his phone. He answers immediately.]* "Hunter." *[He listens for a moment, his expression turning grim.]* "Where? I'm on my way." *[He ends the call and stands up, nodding at Melanie, a look of utter frustration at the language barrier on his face.]* "We'll have to continue this later. Don't leave town." **Melanie:** *[Watches him hurry off, clutching her camera to her chest. She whispers to herself, even more shaken.]* "Er hat es nicht gesehen. Aber ich habe es gesehen." (He didn't see it. But I saw it.)
created_at
"2026-02-16T21:29:14.569661+00:00"
2/16/2026, 9:29:14 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1532
moderation_latency
(null)
generation_time
21545
tokens_prompt
336
tokens_completion
577
native_tokens_prompt
270
native_tokens_completion
580
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0006529
router
(null)
provider_responses
0
id
"019c685b3344676304686ecbc963892a"
status
200
is_byok
false
latency
1532
endpoint_id
"5d5c9c1d-af0d-4e4a-8aee-c5cd2b3883f3"
provider_name
"SiliconFlow"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771277332-sjINddCbVj6dgCVgrmBu"
upstream_id
"019c685b3344676304686ecbc963892a"
total_cost
0.0006529
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Parse dialogue
n/a
dialogue
0
name
"Melanie"
dialogue
"Seltsam. Dieses Licht... es sieht fast unnatürlich aus."
detectedLang
"de"
heavyLang
"de"
scores
de
0.797077922077922
et
0.4369369369369369
es
0.3951612903225807
ca
0.39123376623376627
nl
0.3892508143322475
lv
0.35121107266435986
hu
0.21383647798742136
pt
0.20718816067653278
sv
0.19700214132762314
lt
0.19527896995708155
da
0.18655097613882862
no
0.18655097613882862
tl
0.1812227074235808
ro
0.17218543046357618
en
0.16851441241685144
reliable
true
passes
true
1
name
"Hunter"
dialogue
"Excuse me, ma'am. Hunter, Alborn PD. Mind if I ask you a few questions? You were taking pictures near the old mill yesterday afternoon."
detectedLang
"en"
heavyLang
"en"
scores
en
0.7630955514609108
tl
0.5724465558194775
fr
0.5184590690208668
it
0.44581280788177335
no
0.44581280788177335
nl
0.44237918215613387
ca
0.4174757281553398
pt
0.40476190476190477
sv
0.3967828418230563
sq
0.3844049247606019
da
0.3754337265787648
ro
0.375
et
0.34687953555878087
es
0.3001555209953344
sk
0.27942353883106485
pl
0.2724333063864187
cs
0.25925925925925924
yo
0.258037922506183
hu
0.2568125516102395
sl
0.2549668874172185
de
0.25434962717481363
tr
0.24496644295302009
ms
0.2398648648648649
hr
0.21807124239791487
fi
0.1949910554561717
lv
0.1935483870967742
is
0.18845807033363388
lt
0.13875598086124402
az
0.1287512100677638
vi
0.1287512100677638
be
0.07216494845360825
eu
0.07216494845360825
uk
0.06542056074766354
reliable
true
passes
true
2
name
"Melanie"
dialogue
"Es tut mir leid, ich verstehe nicht. Etwas ist nicht richtig dort draußen geschehen. Ich habe... ich habe Dinge gesehen."
detectedLang
"de"
heavyLang
"de"
scores
de
0.8191430161380078
nl
0.4988434849653045
lt
0.35194416749750745
it
0.26719278466741825
lv
0.2545871559633027
es
0.24418604651162787
no
0.24242424242424243
ca
0.24065420560747666
sv
0.2388758782201405
sk
0.23076923076923078
tl
0.214975845410628
hu
0.2111650485436893
is
0.181360201511335
en
0.1709183673469388
fr
0.1709183673469388
ro
0.1698595146871009
eu
0.15032679738562094
pl
0.15032679738562094
hi
0.1402116402116402
cs
0.13333333333333333
hr
0.13333333333333333
da
0.12634408602150538
tr
0.12634408602150538
fi
0.11924119241192413
et
0.10220994475138122
pt
0.08835904628330996
az
0.08321579689703808
sq
0.08321579689703808
reliable
true
passes
true
3
name
"Hunter"
dialogue
"English? Do you speak English? The mill. Yesterday. Did you see anyone?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.8060010346611484
tl
0.5173745173745175
nl
0.37290969899665555
cs
0.36006825938566556
sq
0.34210526315789475
hr
0.33862433862433866
yo
0.33035714285714285
no
0.3206521739130435
et
0.3119266055045872
pt
0.2937853107344633
da
0.2857142857142857
ms
0.2857142857142857
sv
0.2857142857142857
pl
0.27606177606177607
sk
0.26035502958579887
sl
0.24242424242424243
vi
0.22839506172839508
fr
0.17218543046357618
de
0.1610738255033557
ro
0.1610738255033557
reliable
true
passes
true
4
name
"Melanie"
dialogue
"Die Bilder! In den Bildern! Das ist nicht mein Fehler, oder? Das ist echt?"
detectedLang
"de"
heavyLang
"de"
scores
de
0.8436196830692244
nl
0.6684350132625994
sv
0.5805369127516778
no
0.4769874476987448
en
0.46428571428571425
tr
0.4195046439628483
da
0.41497659906396256
eu
0.37707641196013286
az
0.35456110154905335
cs
0.3409490333919156
yo
0.3194192377495462
pt
0.30683918669131244
sl
0.29111531190926276
it
0.2816091954022989
ro
0.27466150870406186
hi
0.2203742203742204
tl
0.19871794871794873
pl
0.1830065359477124
sq
0.16851441241685144
ms
0.16666666666666666
ru
0.1648106904231626
reliable
true
passes
true
5
name
"Hunter"
dialogue
"Pictures? Okay, pictures. Can I see?"
detectedLang
"en"
heavyLang
"fr"
scores
en
0.7842170160295932
ca
0.6875
tl
0.6548323471400395
et
0.6541501976284586
ro
0.580335731414868
no
0.5535714285714286
da
0.5466321243523317
sv
0.5454545454545454
fr
0.5231607629427792
tr
0.45652173913043476
lv
0.45482866043613707
az
0.4444444444444444
hr
0.44267515923566875
sq
0.4336569579288026
pl
0.4186046511627907
it
0.396551724137931
cs
0.375
yo
0.3320610687022901
de
0.29149797570850206
nl
0.29149797570850206
sk
0.29149797570850206
be
0.2857142857142857
hu
0.2768595041322314
is
0.2647058823529412
lt
0.2647058823529412
uk
0.2647058823529412
vi
0.2647058823529412
reliable
true
passes
true
6
name
"Melanie"
dialogue
"Sehen Sie? Dieser Schatten... er hatte keine... keine richtige Form."
detectedLang
"de"
heavyLang
"de"
scores
de
0.8317498020585906
nl
0.6605431309904153
no
0.6493399339933994
da
0.6001881467544685
sv
0.5405405405405406
fi
0.3902439024390244
it
0.37037037037037035
fr
0.3675595238095238
en
0.3656716417910448
tl
0.28451178451178455
is
0.28209459459459457
tr
0.2735042735042735
eu
0.21296296296296297
pl
0.2085661080074488
et
0.17794970986460348
ms
0.1550695825049702
ro
0.15
sk
0.1431451612903226
reliable
true
passes
true
7
name
"Hunter"
dialogue
"It's a shadow, ma'am. Look, if you saw something—"
detectedLang
"en"
heavyLang
"en"
scores
en
0.7755524861878453
tl
0.42882249560632685
ms
0.4257950530035336
pt
0.4014732965009208
cs
0.3925233644859813
es
0.3925233644859813
sv
0.3340163934426229
hu
0.32432432432432434
ro
0.2995689655172413
ca
0.29501084598698485
sk
0.2857142857142857
it
0.2777777777777778
yo
0.268018018018018
fr
0.2647058823529412
hr
0.2562929061784897
pl
0.24418604651162787
sl
0.21686746987951808
lt
0.20147420147420148
tr
0.19154228855721395
is
0.1875
da
0.181360201511335
sq
0.181360201511335
az
0.17721518987341772
eu
0.17721518987341772
lv
0.17721518987341772
nl
0.17721518987341772
no
0.17721518987341772
vi
0.17721518987341772
de
0.1709183673469388
et
0.16237113402061853
fi
0.16237113402061853
reliable
true
passes
true
8
name
"Hunter"
dialogue
"We'll have to continue this later. Don't leave town."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8114630467571644
fr
0.5046235138705416
da
0.4791666666666667
tl
0.4777158774373259
nl
0.4477172312223858
pt
0.4427934621099554
it
0.375
ro
0.37080536912751677
ca
0.36332767402376914
pl
0.36006825938566556
es
0.35456110154905335
no
0.34782608695652173
de
0.2937853107344633
yo
0.267578125
sk
0.26035502958579887
cs
0.258893280632411
lv
0.2454728370221328
sl
0.24395161290322584
hr
0.23625254582484725
lt
0.21711899791231734
sv
0.18655097613882862
ms
0.17218543046357618
hi
0.16851441241685144
et
0.1610738255033557
reliable
true
passes
true
9
name
"Melanie"
dialogue
"Er hat es nicht gesehen. Aber ich habe es gesehen."
detectedLang
"de"
heavyLang
"de"
scores
de
0.856156501726122
nl
0.5344506517690875
hu
0.4318181818181818
da
0.40617577197149646
is
0.4004796163069544
no
0.39759036144578314
ca
0.37027707808564225
es
0.37027707808564225
sk
0.3315508021390375
lv
0.32432432432432434
eu
0.3150684931506849
pl
0.3150684931506849
cs
0.2857142857142857
lt
0.2668621700879765
fi
0.26035502958579887
tr
0.2378048780487805
reliable
true
passes
true