Run: 2026-04-25-01KQ2EKPDBMQHA927FWAH3RP5K

Run Details

Model:
DeepSeek V4 Pro (Reasoning)
Test:
Language Writing
Scenario:
Character dialogue (French) in a story
Duration:
9m 1s
Cost:
$0.002367
Provider:
DeepSeek

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="Marie"> Marie is a 30-year old college student on a study abroad program. Born in France, she is fluent in French 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 French, 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: Marie 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 French, and Hunter looks confused. They talk for a while, until Hunter gets a call and has to leave. Return the dialogue between Marie and Hunter as a voice sheet: Marie: "..." Hunter: "..."

Model response

AI
Marie: "Oh, vous êtes de la police? L'inspecteur dont tout le monde parle?" Hunter: "Yes, Detective Hunter. I need to ask you a few questions about the disappearances. You're a photographer, correct?" Marie: "Oui, je prends des photos du paysage. Mais... comment vous dire... j'ai été témoin de quelque chose. Je suis encore toute secouée." Hunter: "Witness? You saw something? What did you see? Slow down... I don't understand." Marie: "Je ne parle pas anglais, désolée. Je vais essayer d'expliquer... Près du vieux bâtiment abandonné, à la sortie du verger, j'ai vu un homme. Et puis, d'un seul coup... il n'était plus là. Disparu." Hunter: "Disparu? That sounds like 'disappeared'. You saw a man disappear? Where? Show me on the camera." Marie: "Attendez... oui, j'ai une photo prise juste avant. Regardez, cette ombre au fond, c'est lui, je crois." Hunter: "The old barn. I know the place. There's a figure here... When was this taken? Yesterday? Today?" Marie: "Hier soir, pendant le coucher du soleil. Le festival des pommes venait de finir. J'étais seule à photographier le paysage, et puis... cette silhouette. J'ai eu tellement peur." Hunter: "Last night... sunset... you were alone. Did you see where he went? Did he walk into the barn?" Marie: "Il est entré par la porte de côté, celle qui grince. Je n'ai rien entendu après, juste le silence. C'était anormal." Hunter: "Anormal... abnormal. Everything about this is abnormal. Alright, I need you to stay put, we'll get a translator. This could be important." Marie: "Vous croyez que j'ai vu l'un des disparus? Vous pensez que le ravisseur était là?" Hunter: "Ravis... what? I wish I knew what you were saying. Let me see that photo again. Zoom in. Hmm... (his phone buzzes) Excuse me." Hunter: "Hunter. Yeah. Where? The old barn, you're saying another one? I'm on my way." Hunter: "I have to go. Right now. Stay exactly where you are — someone will be here to take a full statement. Don't leave the cafe."
created_at"2026-04-25T14:00:35.655Z" 4/25/2026, 2:00:35 PM
model"deepseek/deepseek-v4-pro-20260423"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency919
moderation_latency(null)
generation_time58791
tokens_prompt316
tokens_completion2861
native_tokens_prompt263
native_tokens_completion2707
native_tokens_completion_images(null)
native_tokens_reasoning2165
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"
usage0.002367415
router(null)
provider_responses
0
endpoint_id"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id"db2b8356-b817-4b8f-93b0-8ccdc917da88"
is_byokfalse
latency267
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-1777125635-7WuTGLpx0OjQLFNijiAS"
session_id(null)
api_type"completions"
id"gen-1777125635-DPs2uwajhP78qIriv9KO"
upstream_id"db2b8356-b817-4b8f-93b0-8ccdc917da88"
total_cost0.002367415
cache_discount0.00010208
upstream_inference_cost0
provider_name"DeepSeek"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
100.00% Parse dialogue n/a
dialogue
0
name"Marie"
dialogue"Oh, vous êtes de la police? L'inspecteur dont tout le monde parle?"
detectedLang"fr"
heavyLang"fr"
scores
fr0.8104549082202713
it0.6728650137741047
ro0.6374045801526718
nl0.6236133122028527
es0.6206070287539935
ca0.5796460176991151
en0.49788583509513745
hu0.48814655172413796
sl0.46868008948545864
tl0.45652173913043476
pt0.42839951865222625
no0.41789215686274506
sv0.41430332922318125
yo0.3933588761174968
de0.37745740498034075
sq0.3725231175693527
da0.3606998654104979
cs0.34027777777777785
hr0.3271954674220963
tr0.3252840909090909
sk0.3233618233618234
az0.30453879941434847
ms0.30453879941434847
eu0.2566510172143975
pl0.24603174603174602
et0.24242424242424243
lt0.24000000000000002
lv0.2375601926163724
fi0.15026833631484796
vi0.15026833631484796
reliabletrue
passestrue
1
name"Hunter"
dialogue"Yes, Detective Hunter. I need to ask you a few questions about the disappearances. You're a photographer, correct?"
detectedLang"en"
heavyLang"en"
scores
en0.8133457769482034
fr0.6641477749790092
tl0.5652173913043478
ca0.5299647473560517
it0.5260663507109005
pt0.5037220843672456
nl0.4494150034411562
ro0.4393833216538192
es0.41986947063089197
no0.4190268700072622
da0.41133186166298746
cs0.3930197268588771
yo0.36
sq0.35275080906148865
hr0.35170178282009723
sv0.34210526315789475
pl0.313893653516295
sl0.2963940193491645
sk0.2945326278659612
lv0.2914083259521701
ms0.27140255009107467
et0.24882629107981222
lt0.23736892278360344
de0.2300288739172281
hu0.2179863147605083
tr0.2047713717693837
is0.14712153518123666
az0.14255091103965703
vi0.14255091103965703
hi0.08779931584948689
be0.08045977011494253
eu0.08045977011494253
fi0.07300115874855156
uk0.07300115874855156
reliabletrue
passestrue
2
name"Marie"
dialogue"Oui, je prends des photos du paysage. Mais... comment vous dire... j'ai été témoin de quelque chose. Je suis encore toute secouée."
detectedLang"fr"
heavyLang"fr"
scores
fr0.8211963589076723
en0.597953216374269
de0.49168207024029575
nl0.4518272425249169
it0.43259972489683635
tl0.4140625
pt0.41322901849217636
ca0.39999999999999997
es0.336283185840708
sk0.30730478589420657
yo0.27947598253275113
cs0.27695004382120947
hr0.27568042142230026
da0.2744063324538259
ro0.27055702917771884
sv0.26141450313339304
no0.25339366515837103
sl0.24242424242424243
sq0.2090124640460211
eu0.20443587270973965
lt0.1758241758241758
tr0.17002012072434608
hu0.16243654822335027
pl0.1607324516785351
az0.13249211356466878
fi0.11290322580645161
vi0.10714285714285714
hi0.08536585365853659
lv0.07924107142857142
ms0.07094594594594594
reliabletrue
passestrue
3
name"Hunter"
dialogue"Witness? You saw something? What did you see? Slow down... I don't understand."
detectedLang"en"
heavyLang"en"
scores
en0.8053633217993079
da0.533678756476684
no0.4955156950672646
tl0.4712103407755582
sv0.4367959949937422
cs0.4318181818181818
de0.3732590529247911
et0.34114202049780384
pl0.3119266055045872
ms0.2834394904458599
nl0.2834394904458599
ro0.267100977198697
sk0.26350245499181674
hr0.23599320882852293
ca0.23469387755102045
lv0.23469387755102045
is0.23339011925042585
sq0.22945205479452058
it0.20353982300884957
yo0.16201117318435754
es0.14772727272727273
pt0.14772727272727273
be0.1346153846153846
tr0.1346153846153846
hu0.12959381044487428
az0.12280701754385964
lt0.12280701754385964
uk0.12280701754385964
vi0.12280701754385964
reliabletrue
passestrue
4
name"Marie"
dialogue"Je ne parle pas anglais, désolée. Je vais essayer d'expliquer... Près du vieux bâtiment abandonné, à la sortie du verger, j'ai vu un homme. Et puis, d'un seul coup... il n'était plus là. Disparu."
detectedLang"fr"
heavyLang"fr"
scores
fr0.8087672844954398
ca0.5977722772277227
it0.460804645375363
ro0.4581075448103376
pt0.3899577663068982
de0.3838862559241706
da0.38330170777988615
es0.35707220573689413
sl0.3457473578258682
sq0.34077079107505076
cs0.3363961204696274
yo0.3271221532091097
no0.32150313152400833
nl0.2961559285327558
lt0.28532160527762507
sk0.28017718715393136
et0.27455357142857145
en0.27048260381593714
sv0.26136363636363635
lv0.24550203134068485
hr0.23976608187134502
vi0.2073170731707317
tl0.20440636474908203
az0.19950738916256158
tr0.19901417128773877
eu0.16452442159383035
pl0.14754098360655737
ms0.14134742404227213
hu0.1402116402116402
fi0.11323328785811733
reliabletrue
passestrue
5
name"Hunter"
dialogue"Disparu? That sounds like 'disappeared'. You saw a man disappear? Where? Show me on the camera."
detectedLang"en"
heavyLang"en"
scores
en0.7829107328933658
tl0.560478199718706
fr0.5082612116443744
nl0.4881244881244881
it0.46626814688300594
ms0.44196428571428575
no0.4318181818181818
sq0.41588785046728977
es0.40702087286527516
sv0.4064577397910731
ca0.405893536121673
pt0.39320388349514557
de0.3914313534566699
ro0.38605108055009824
cs0.3615934627170583
et0.3329775880469584
yo0.32505399568034554
fi0.3154435925520263
da0.3086283185840708
sk0.3047830923248054
hr0.24242424242424243
pl0.23218673218673216
lv0.22166874221668745
sl0.22166874221668745
lt0.21972534332084895
hu0.1997439180537772
be0.13793103448275862
hi0.11847672778561354
tr0.10968660968660969
is0.10714285714285714
az0.10071942446043164
eu0.10071942446043164
vi0.10071942446043164
reliabletrue
passestrue
6
name"Marie"
dialogue"Attendez... oui, j'ai une photo prise juste avant. Regardez, cette ombre au fond, c'est lui, je crois."
detectedLang"fr"
heavyLang"fr"
scores
fr0.8120300751879699
en0.4961779013203613
ro0.4850852272727273
it0.4715743440233236
ca0.45075757575757575
es0.4448698315467075
no0.39834024896265563
pt0.3927973199329984
nl0.3813993174061433
da0.36067019400352734
de0.35669920141969835
tl0.34802158273381295
sk0.30952380952380953
et0.30886558627264066
sv0.27860696517412936
sl0.2728184553660983
hr0.26693629929221435
cs0.24479166666666666
sq0.23924449108079748
tr0.23036093418259024
yo0.18355855855855857
hu0.14099526066350712
lt0.12650602409638553
pl0.11151960784313725
hi0.09600997506234414
lv0.09488139825218476
eu0.08919597989949749
ms0.0845959595959596
reliabletrue
passestrue
7
name"Hunter"
dialogue"The old barn. I know the place. There's a figure here... When was this taken? Yesterday? Today?"
detectedLang"en"
heavyLang"en"
scores
en0.8151125401929261
tl0.5089666951323655
no0.49781659388646293
nl0.4888888888888889
fr0.4833782569631626
sv0.4829136690647482
da0.47584320875113945
ro0.4753649635036496
yo0.45856873822975514
sq0.44498069498069504
ca0.4221105527638191
cs0.3991640543364681
pt0.39790575916230364
es0.3947368421052632
de0.3817204301075269
it0.3495475113122172
pl0.3488108720271801
sk0.32748538011695905
hr0.30387409200968524
hu0.27944862155388467
is0.2721518987341772
sl0.22611036339165547
tr0.203601108033241
lt0.20138888888888887
ms0.19692737430167598
az0.18785310734463279
lv0.18785310734463279
vi0.18785310734463279
et0.1797432239657632
be0.10852713178294573
eu0.10852713178294573
fi0.0987460815047022
uk0.0987460815047022
reliabletrue
passestrue
8
name"Marie"
dialogue"Hier soir, pendant le coucher du soleil. Le festival des pommes venait de finir. J'étais seule à photographier le paysage, et puis... cette silhouette. J'ai eu tellement peur."
detectedLang"fr"
heavyLang"fr"
scores
fr0.8021456208230742
en0.5214802211824756
ca0.46858762399622106
da0.46530418250950567
de0.46197991391678617
no0.4549418604651163
nl0.4204018547140649
pt0.39320388349514557
it0.375
sv0.3658399098083427
ro0.3530764807360552
es0.34895833333333337
tl0.33510638297872336
hu0.3123471882640587
et0.29555416405760804
lt0.27184466019417475
sq0.2680546519193234
yo0.2618110236220473
sl0.25
ms0.24698795180722888
tr0.23832092078537576
hr0.23155737704918034
cs0.2219917012448133
az0.17823228634039445
sk0.17702999268471104
eu0.15856394913986538
lv0.12790697674418602
fi0.10643367752184274
pl0.10358565737051792
vi0.08088235294117647
is0.07254740313272877
hi0.06405990016638935
reliabletrue
passestrue
9
name"Hunter"
dialogue"Last night... sunset... you were alone. Did you see where he went? Did he walk into the barn?"
detectedLang"en"
heavyLang"en"
scores
en0.8151750972762647
tl0.5343137254901961
no0.4324970131421744
da0.42493946731234866
yo0.37335092348284965
et0.34210526315789475
fr0.3252840909090909
sv0.27480916030534347
nl0.2531446540880503
sq0.24722662440570525
de0.24242424242424243
ca0.1607773851590106
fi0.1607773851590106
it0.15480427046263345
es0.15026833631484796
cs0.1410488245931284
ms0.1410488245931284
is0.1394927536231884
pl0.1394927536231884
reliabletrue
passestrue
10
name"Marie"
dialogue"Il est entré par la porte de côté, celle qui grince. Je n'ai rien entendu après, juste le silence. C'était anormal."
detectedLang"fr"
heavyLang"fr"
scores
fr0.8062470643494598
it0.6101134215500945
ca0.5784363822176801
es0.5554956896551724
pt0.5053956834532374
ro0.49756394640682094
tl0.48340638697557925
en0.46911196911196906
da0.45364238410596025
no0.43454420836189167
yo0.4214586255259467
tr0.3986880466472303
nl0.3951612903225807
cs0.3870728083209509
de0.3857036485480268
et0.34679334916864607
sl0.3462757527733756
sk0.3287225386493084
sq0.2960750853242321
sv0.2838541666666667
az0.2712014134275618
lv0.25675675675675674
ms0.23892988929889297
hu0.23822714681440443
eu0.23184357541899442
hr0.22096317280453256
is0.18558736426456074
pl0.1607324516785351
fi0.1260593220338983
vi0.0924092409240924
lt0.0667420814479638
reliabletrue
passestrue
11
name"Hunter"
dialogue"Anormal... abnormal. Everything about this is abnormal. Alright, I need you to stay put, we'll get a translator. This could be important."
detectedLang"en"
heavyLang"en"
scores
en0.8063891577928364
tl0.6011964107676969
ro0.5021779713752333
ca0.49653870358716173
fr0.4838709677419355
no0.4747209455022981
da0.4740302432610125
hr0.4616419919246299
yo0.44713199723566
pt0.43977591036414565
pl0.42028985507246375
cs0.41818181818181815
lt0.4164843180160467
it0.4152046783625731
es0.4078460399703923
hu0.38176197836166925
nl0.38128383604021654
sq0.37839937839937837
sk0.3630573248407643
sv0.36254980079681276
et0.35691318327974275
de0.34156378600823045
sl0.332220367278798
ms0.32998324958123953
lv0.32260795935647757
tr0.3150684931506849
is0.2920353982300885
az0.28888888888888886
vi0.21645445641527913
eu0.20318725099601595
be0.08045977011494253
fi0.07300115874855156
uk0.07300115874855156
reliabletrue
passestrue
12
name"Marie"
dialogue"Vous croyez que j'ai vu l'un des disparus? Vous pensez que le ravisseur était là?"
detectedLang"fr"
heavyLang"fr"
scores
fr0.7982243744955609
ca0.48717948717948717
es0.48240165631469983
pt0.40968122786304606
it0.3924665856622114
de0.3718592964824121
ro0.3564993564993565
nl0.3315508021390375
yo0.29577464788732394
ms0.2570579494799406
lt0.25037481259370314
et0.24127465857359634
vi0.2389649923896499
no0.2163009404388715
sl0.18962722852512154
hu0.1638795986622074
fi0.15824915824915825
en0.14089347079037798
lv0.1243432574430823
cs0.12126537785588754
sk0.12126537785588754
sq0.12126537785588754
az0.1087344028520499
da0.1087344028520499
sv0.1087344028520499
reliabletrue
passestrue
13
name"Hunter"
dialogue"Ravis... what? I wish I knew what you were saying. Let me see that photo again. Zoom in. Hmm... Excuse me."
detectedLang"en"
heavyLang"en"
scores
en0.7826908541194255
tl0.4763205828779599
fr0.4439071566731141
nl0.4334975369458128
et0.4197780020181635
cs0.3997912317327766
sl0.37635574837310193
it0.37295528898582336
no0.36882546652030734
sq0.3290548424737456
sv0.2987804878048781
ro0.2874845105328377
da0.2730720606826802
pl0.267515923566879
yo0.23333333333333334
tr0.22818791946308725
fi0.2271505376344086
ms0.21662125340599456
az0.203601108033241
de0.203601108033241
hr0.19467787114845939
ca0.1935483870967742
es0.15066469719350073
pt0.13273001508295626
hi0.11809815950920245
sk0.11128284389489954
be0.10852713178294573
hu0.1043613707165109
is0.0987460815047022
lt0.0987460815047022
lv0.0987460815047022
uk0.0987460815047022
vi0.0987460815047022
reliabletrue
passestrue
14
name"Hunter"
dialogue"Hunter. Yeah. Where? The old barn, you're saying another one? I'm on my way."
detectedLang"en"
heavyLang"en"
scores
en0.8156055900621119
tl0.6015100671140939
da0.40624999999999994
no0.358974358974359
pl0.35636856368563685
fr0.3528610354223433
sv0.3448275862068966
sq0.3115942028985507
yo0.2770167427701674
hr0.2692307692307693
de0.25897035881435254
cs0.2531446540880503
sk0.2531446540880503
tr0.250788643533123
ca0.24960505529225907
et0.2448330683624801
fi0.24000000000000002
nl0.23633440514469453
ms0.2238562091503268
es0.1739130434782609
hi0.15026833631484796
is0.1394927536231884
it0.1171003717472119
pt0.1171003717472119
ro0.11048689138576778
sl0.11048689138576778
reliabletrue
passestrue
15
name"Hunter"
dialogue"I have to go. Right now. Stay exactly where you are — someone will be here to take a full statement. Don't leave the cafe."
detectedLang"en"
heavyLang"en"
scores
en0.8265054846653235
tl0.5984455958549223
yo0.5192307692307693
da0.5159275452841974
no0.5038412291933418
sq0.4621790423317141
ro0.44204463642908565
pl0.4379985496736766
cs0.42464736451373425
sv0.421209858103062
fr0.4133232399697199
hr0.38880126182965297
de0.3785084202085004
sk0.3704305442729488
lt0.3600330305532618
it0.34764309764309764
hu0.34210526315789475
ca0.33590402742073694
es0.3159752868490733
sl0.3123336291038154
lv0.2909423604757548
nl0.28174235403151066
pt0.27093132643461904
az0.2504835589941973
tr0.20998980632008157
ms0.2051282051282051
et0.19270833333333331
is0.15115005476451257
vi0.14647577092511013
be0.08284023668639054
eu0.08284023668639054
fi0.07517899761336516
uk0.07517899761336516
reliabletrue
passestrue