Run: 2026-09-03-01M1KAFJES8MDD7EEZF6T36EWM

Run Details

Model:
DeepSeek V4 Pro 0813 (Reasoning, High)
Test:
Language Writing
Scenario:
Character dialogue (French) in a story
Duration:
49.3s
Cost:
$0.008263
Provider:
Together

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: "Je n'arrive pas à y croire... c'était juste là, devant moi..." Hunter: "Ma'am? Detective Hunter. I need to ask you about the incident at the apple festival last night." Marie: "Oui... j'étais là. C'était affreux. Les gens criaient, tout le monde courait..." Hunter: "I can't understand you. Do you speak English? English?" Marie: "Non, je ne parle pas anglais. Je suis française. Je suis désolée." Hunter: "Okay... French. Great. Uh... photo? Camera?" (points at the camera) Marie: "Oui, j'ai des photos. Peut-être l'homme... il avait une casquette rouge. Il a bousculé une femme." Hunter: "Red cap? I saw that. Can you show me the picture?" Marie: "Tenez, regardez. C'est flou, mais on voit son visage, non?" Hunter: "That's him. I need this. Can I borrow your camera?" Marie: "Non, je ne peux pas vous le donner. Mais je peux vous envoyer la photo par courriel." Hunter: "I don't know what you're saying. Just... don't delete that. Stay here." Marie: "Je ne vais nulle part. J'ai trop peur." Hunter: "What's your name?" Marie: "Marie. Marie Laurent." Hunter: "Marie. Okay, Marie. Where are you staying?" Marie: "À la petite auberge près de l'église. La chambre quatre." Hunter: "Auberge? Church? Okay, I'll find it." Marie: "Je ne veux pas rester seule ce soir..." Hunter: (phone rings) "Hang on." (answers) "Hunter. ... Yeah. ... Now? ... I'm on my way." (to Marie) "I have to go. Don't leave town. I'll find someone who speaks French." Marie: "D'accord. Merci, détective. Faites attention."
created_at"2026-09-03T09:44:27.37Z" 9/3/2026, 9:44:27 AM
model"deepseek/deepseek-v4-pro-20260813"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency631
moderation_latency(null)
generation_time49252
tokens_prompt303
tokens_completion1936
native_tokens_prompt263
native_tokens_completion1999
native_tokens_completion_images(null)
native_tokens_reasoning1552
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)
usage0.0082632
router(null)
user_agent"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer(null)
request_id"req-1788428667-RNNHhGTsUjMk4nES9xXU"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1788428667-L8nJC2zJl6rkIAdgQCIw"
upstream_id"83a64de0-aws_ue2"
provider_responses
0
endpoint_id"218b0cec-3278-4b88-8ee0-3f346eccd35f"
id"83a64de0-aws_ue2"
is_byokfalse
latency631
model_permaslug"deepseek/deepseek-v4-pro-20260813"
provider_name"Together"
status200
total_cost0.0082632
cache_discount(null)
upstream_inference_cost0
provider_name"Together"
response_cache_source_id(null)
data_region"global"
workspace_id"97e315e5-d303-487d-83c1-83180e8a13d4"

Evaluation details

Result Evaluator Details Meta Data
100.00% Parse dialogue n/a
dialogue
0
name"Marie"
dialogue"Je n'arrive pas à y croire... c'était juste là, devant moi..."
detectedLang"fr"
heavyLang"fr"
scores
fr0.8154981549815498
yo0.45188794153471373
pt0.3910690121786198
nl0.3818681318681319
ca0.3723849372384937
vi0.3617021276595745
es0.3562231759656652
cs0.3333333333333333
en0.3293591654247392
no0.3293591654247392
sq0.3161094224924012
pl0.303405572755418
et0.29577464788732394
sl0.27768860353130015
hr0.2753623188405797
ms0.25124792013311154
da0.24369747899159663
sk0.24369747899159663
ro0.24114671163575044
de0.23857868020304565
tr0.1906474820143885
lt0.16820702402957485
it0.14285714285714285
eu0.1362763915547025
tl0.12959381044487428
sv0.11937377690802348
reliabletrue
passestrue
1
name"Hunter"
dialogue"Ma'am? Detective Hunter. I need to ask you about the incident at the apple festival last night."
detectedLang"en"
heavyLang"en"
scores
en0.7947704469443599
tl0.6781115879828327
no0.608241439349971
da0.6075581395348837
fr0.5916515426497277
ca0.5417515274949084
it0.5351239669421488
nl0.5309242529534399
ro0.5236414961185604
cs0.5087336244541485
es0.4917168674698795
sq0.4755244755244755
sv0.47388932190179267
de0.466403162055336
hr0.4630071599045346
pt0.4547657512116317
sl0.4547657512116317
et0.43983402489626555
sk0.4005328596802842
yo0.375
pl0.3685687558465856
lt0.3427458617332035
az0.32567432567432564
ms0.31886982845610495
lv0.2686890574214518
hu0.22235023041474655
tr0.16044776119402984
be0.09395973154362416
fi0.08536585365853659
is0.08536585365853659
uk0.08536585365853659
vi0.08536585365853659
reliabletrue
passestrue
2
name"Marie"
dialogue"Oui... j'étais là. C'était affreux. Les gens criaient, tout le monde courait..."
detectedLang"fr"
heavyLang"fr"
scores
fr0.8183799491463858
it0.46808510638297873
ca0.414519906323185
es0.3983152827918171
pt0.38650306748466257
ro0.358974358974359
en0.3581514762516046
nl0.3359893758300133
hu0.299719887955182
yo0.29577464788732394
tl0.24471299093655588
vi0.2389649923896499
lt0.19614147909967844
sl0.18962722852512154
lv0.16943521594684383
az0.16666666666666666
no0.15682967959527827
de0.13043478260869565
sv0.1289198606271777
reliabletrue
passestrue
3
name"Hunter"
dialogue"I can't understand you. Do you speak English? English?"
detectedLang"en"
heavyLang"en"
scores
en0.8084291187739464
no0.6359223300970874
da0.6305418719211823
sv0.5839112343966713
cs0.5714285714285714
pl0.5363214837712519
hr0.5245641838351823
tl0.5184590690208668
sk0.49409780775716694
de0.4690265486725664
sq0.455535390199637
ro0.44029850746268656
nl0.3723849372384937
vi0.3670886075949367
yo0.3548387096774194
pt0.34210526315789475
ca0.3150684931506849
is0.3135011441647597
sl0.2857142857142857
it0.27710843373493976
ms0.1935483870967742
be0.1891891891891892
tr0.1891891891891892
hu0.18256130790190736
az0.17355371900826447
et0.17355371900826447
lt0.17355371900826447
lv0.17355371900826447
uk0.17355371900826447
reliabletrue
passestrue
4
name"Marie"
dialogue"Non, je ne parle pas anglais. Je suis française. Je suis désolée."
detectedLang"fr"
heavyLang"fr"
scores
fr0.8029427220178665
sl0.6138002059732235
ca0.5743473325766175
it0.5588235294117647
sq0.5498199279711885
cs0.5410036719706242
hr0.5306633291614518
lt0.5300751879699248
en0.497991967871486
sk0.48840381991814463
nl0.4863013698630137
lv0.45652173913043476
ro0.4549418604651163
yo0.39320388349514557
pl0.37810945273631835
de0.37080536912751677
pt0.37080536912751677
hu0.3686868686868687
es0.3676222596964587
tr0.3654822335025381
ms0.35456110154905335
eu0.3081180811808118
et0.2732558139534884
no0.2632612966601179
az0.2618110236220473
da0.251497005988024
sv0.251497005988024
fi0.19006479481641467
tl0.1515837104072398
is0.1359447004608295
reliabletrue
passestrue
5
name"Hunter"
dialogue"Okay... French. Great. Uh... photo? Camera?"
detectedLang"en"
heavyLang"en"
scores
en0.7422680412371134
tl0.5860927152317881
fr0.5155038759689923
ro0.5078740157480316
it0.4845360824742268
es0.44071588366890374
ca0.28977272727272724
pt0.2711370262390671
cs0.26035502958579887
sv0.24698795180722888
hi0.23547400611620795
nl0.2331288343558282
de0.22360248447204967
ms0.22360248447204967
reliabletrue
passestrue
6
name"Marie"
dialogue"Oui, j'ai des photos. Peut-être l'homme... il avait une casquette rouge. Il a bousculé une femme."
detectedLang"fr"
heavyLang"fr"
scores
fr0.8131539611360238
ca0.5078740157480316
it0.4409660107334526
en0.4036259541984733
da0.3854473942969518
no0.37624750499001997
de0.3693239152371342
hu0.3055555555555556
tr0.2799539170506913
ro0.2690058479532163
nl0.26297169811320753
pt0.26035502958579887
es0.2532855436081242
az0.22839506172839508
lt0.20584498094027956
fi0.1997439180537772
tl0.1925064599483204
lv0.18407310704960833
et0.1830065359477124
cs0.17437252311756934
sk0.17218543046357618
yo0.15994623655913978
hr0.1519674355495251
pl0.14383561643835618
sl0.12587412587412586
hi0.10968660968660969
is0.10714285714285714
sq0.10329985652797705
eu0.10071942446043164
vi0.10071942446043164
ms0.09156976744186046
sv0.09156976744186046
reliabletrue
passestrue
7
name"Hunter"
dialogue"Red cap? I saw that. Can you show me the picture?"
detectedLang"en"
heavyLang"en"
scores
en0.8107255520504733
tl0.6975806451612904
sq0.5896032831737346
fr0.5447647951441578
ca0.5290423861852434
no0.5245641838351823
hr0.5
da0.49324324324324326
it0.48364888123924266
yo0.4690265486725664
ms0.46619217081850534
ro0.460431654676259
nl0.4495412844036697
sl0.44751381215469616
sv0.4186046511627907
es0.38271604938271603
cs0.37888198757763975
pt0.3548387096774194
et0.34497816593886466
tr0.3288590604026846
az0.3181818181818182
pl0.29577464788732394
fi0.2
sk0.1935483870967742
de0.19137466307277629
be0.1891891891891892
hu0.18256130790190736
is0.17355371900826447
lt0.17355371900826447
lv0.17355371900826447
uk0.17355371900826447
vi0.17355371900826447
reliabletrue
passestrue
8
name"Marie"
dialogue"Tenez, regardez. C'est flou, mais on voit son visage, non?"
detectedLang"fr"
heavyLang"fr"
scores
fr0.788135593220339
en0.5148771021992239
it0.4549418604651163
es0.4477172312223858
ca0.4230769230769231
fi0.39999999999999997
tl0.38524590163934425
et0.38016528925619836
eu0.37810945273631835
pt0.3131868131868132
az0.22680412371134018
lt0.22520661157024793
tr0.22360248447204967
sv0.2203742203742204
lv0.21711899791231734
de0.21383647798742136
nl0.21052631578947367
hr0.19006479481641467
hi0.1830065359477124
pl0.1830065359477124
no0.17035398230088497
cs0.16666666666666666
sk0.16666666666666666
yo0.16666666666666666
ro0.1648106904231626
reliabletrue
passestrue
9
name"Hunter"
dialogue"That's him. I need this. Can I borrow your camera?"
detectedLang"en"
heavyLang"en"
scores
en0.804177545691906
tl0.52
ca0.5137763371150729
it0.47643979057591623
ro0.45255474452554745
sq0.43820224719101125
sv0.4230769230769231
et0.402390438247012
es0.39879759519038077
ms0.3333333333333333
tr0.3288590604026846
no0.3258426966292135
az0.3181818181818182
da0.31662870159453305
hr0.31662870159453305
pl0.29577464788732394
eu0.29411764705882354
cs0.25925925925925924
yo0.2248062015503876
fr0.20212765957446807
nl0.20212765957446807
de0.1935483870967742
sk0.1935483870967742
be0.1891891891891892
hu0.18256130790190736
is0.17355371900826447
lt0.17355371900826447
lv0.17355371900826447
uk0.17355371900826447
vi0.17355371900826447
reliabletrue
passestrue
10
name"Marie"
dialogue"Non, je ne peux pas vous le donner. Mais je peux vous envoyer la photo par courriel."
detectedLang"fr"
heavyLang"fr"
scores
fr0.8281476121562953
it0.576271186440678
en0.489247311827957
ro0.48759439050701187
sl0.46808510638297873
ca0.4644870349492672
tl0.46206115515288787
yo0.4424882629107981
cs0.40025252525252525
sq0.3994943109987357
es0.3807040417209909
pt0.37989556135770236
nl0.3782722513089006
hr0.3741765480895916
de0.3572395128552098
lv0.35197817189631647
lt0.2983751846381093
sv0.291044776119403
no0.2857142857142857
da0.2759146341463415
hu0.27480916030534347
sk0.23387096774193547
tr0.16520210896309317
pl0.1607773851590106
fi0.15630550621669628
eu0.15480427046263345
ms0.15026833631484796
vi0.15026833631484796
hi0.1394927536231884
reliabletrue
passestrue
11
name"Hunter"
dialogue"I don't know what you're saying. Just... don't delete that. Stay here."
detectedLang"en"
heavyLang"en"
scores
en0.8240262787423744
sv0.45014662756598234
no0.4477172312223858
sq0.44526627218934917
ca0.4292237442922375
tl0.4230769230769231
tr0.3951612903225807
et0.3902439024390244
ro0.3822075782537067
da0.35456110154905335
it0.3267504488330341
hu0.2870722433460076
hr0.2704280155642024
pl0.251497005988024
cs0.21875
yo0.1883116883116883
pt0.1758241758241758
sl0.16666666666666666
sk0.1610738255033557
be0.15730337078651685
es0.1515837104072398
nl0.1515837104072398
az0.14383561643835618
is0.14383561643835618
lt0.14383561643835618
lv0.14383561643835618
uk0.14383561643835618
vi0.14383561643835618
reliabletrue
passestrue
12
name"Marie"
dialogue"Je ne vais nulle part. J'ai trop peur."
detectedLang"fr"
heavyLang"fr"
scores
fr0.7783251231527093
sl0.5722433460076045
it0.5714285714285714
hr0.5579567779960707
cs0.5044052863436124
ca0.45121951219512196
fi0.44306930693069313
yo0.4201030927835051
sk0.39189189189189183
nl0.358974358974359
sv0.34210526315789475
sq0.336283185840708
lt0.33035714285714285
da0.32228915662650603
no0.32228915662650603
en0.3202416918429003
lv0.31402439024390244
ro0.3119266055045872
et0.296875
tr0.29467084639498436
pl0.2879746835443038
hu0.267100977198697
de0.26229508196721313
reliabletrue
passestrue
13
name"Hunter"
dialogue"What's your name?"
detectedLang"en"
heavyLang"en"
scores
en0.8198198198198198
de0.43820224719101125
ms0.43820224719101125
nl0.43820224719101125
tl0.43820224719101125
reliabletrue
passestrue
14
name"Marie"
dialogue"Marie. Marie Laurent."
detectedLang"ro"
heavyLang"fr"
scores
ro0.7695852534562212
fr0.7607655502392344
no0.75
it0.7005988023952096
da0.6805111821086262
en0.635036496350365
ca0.6168582375478927
sv0.5867768595041323
lt0.5798319327731093
nl0.5798319327731093
et0.5726495726495726
fi0.5652173913043478
lv0.5652173913043478
tl0.4350282485875706
hr0.42857142857142855
pt0.4186046511627907
sl0.4186046511627907
es0.40119760479041916
pl0.40119760479041916
de0.38650306748466257
eu0.38650306748466257
ms0.38650306748466257
sk0.38650306748466257
sq0.38650306748466257
yo0.38650306748466257
cs0.3710691823899371
reliabletrue
passestrue
15
name"Hunter"
dialogue"Marie. Okay, Marie. Where are you staying?"
detectedLang"en"
heavyLang"en"
scores
en0.8
tl0.6153846153846154
ro0.592391304347826
it0.4201030927835051
fr0.39189189189189183
no0.39189189189189183
da0.3869209809264305
sv0.3869209809264305
de0.38524590163934425
sq0.38524590163934425
cs0.3784530386740331
hr0.25
pt0.24242424242424243
sl0.24242424242424243
ca0.23728813559322032
es0.22945205479452058
lt0.22945205479452058
pl0.22945205479452058
et0.21875
eu0.21875
ms0.21875
nl0.21875
sk0.21875
yo0.21875
fi0.2077464788732394
lv0.2077464788732394
reliabletrue
passestrue
16
name"Marie"
dialogue"À la petite auberge près de l'église. La chambre quatre."
detectedLang"fr"
heavyLang"fr"
scores
fr0.8078770413064361
ca0.7023809523809523
pt0.6074582924435721
it0.5934959349593496
ro0.5815899581589958
es0.5652173913043478
tl0.5073891625615764
no0.4609164420485175
yo0.43342776203966005
nl0.358974358974359
sv0.3162393162393162
sl0.2857142857142857
en0.26335174953959484
sq0.26062846580406657
de0.25650557620817843
da0.22928709055876687
et0.22330097087378642
tr0.19678714859437751
hu0.19517102615694165
hr0.17695473251028807
vi0.17355371900826447
eu0.14893617021276595
az0.13606911447084233
ms0.13606911447084233
reliabletrue
passestrue
17
name"Hunter"
dialogue"Auberge? Church? Okay, I'll find it."
detectedLang"en"
heavyLang"en"
scores
en0.7159090909090909
tl0.47506561679790027
de0.42857142857142855
da0.3333333333333333
lv0.3006993006993007
sq0.3006993006993007
fr0.2805755395683453
no0.2805755395683453
ro0.2805755395683453
yo0.2753623188405797
reliabletrue
passestrue
18
name"Marie"
dialogue"Je ne veux pas rester seule ce soir..."
detectedLang"fr"
heavyLang"fr"
scores
fr0.821300929235168
sl0.6307237813884786
hr0.6165644171779141
ro0.5961227786752827
nl0.5901639344262295
sq0.5874587458745875
it0.5454545454545454
ca0.5404411764705882
cs0.5387453874538745
lt0.5107632093933464
de0.4692144373673036
tr0.46351931330472107
sk0.46236559139784944
ms0.4517543859649123
yo0.3946731234866829
lv0.39320388349514557
pl0.3872549019607844
da0.3842364532019704
no0.3811881188118812
sv0.375
hu0.3670886075949367
en0.3654822335025381
et0.35233160621761656
es0.3403693931398417
pt0.3403693931398417
tl0.33510638297872336
fi0.26035502958579887
az0.19093851132686085
reliabletrue
passestrue
19
name"Hunter"
dialogue"I have to go. Don't leave town. I'll find someone who speaks French."
detectedLang"en"
heavyLang"en"
scores
en0.8161764705882353
da0.5212765957446809
tl0.4943820224719101
pl0.45054945054945056
yo0.4007989347536618
hr0.3617021276595745
no0.36079545454545453
cs0.3440233236151603
sk0.3119266055045872
et0.3098159509202454
it0.29906542056074764
lv0.2913385826771654
es0.281150159744409
pt0.2753623188405797
lt0.2706645056726094
ca0.23469387755102045
sv0.23469387755102045
sq0.22945205479452058
sl0.2119089316987741
ro0.16666666666666666
be0.1346153846153846
tr0.1346153846153846
hu0.12959381044487428
az0.12280701754385964
is0.12280701754385964
uk0.12280701754385964
vi0.12280701754385964
reliabletrue
passestrue
20
name"Marie"
dialogue"D'accord. Merci, détective. Faites attention."
detectedLang"fr"
heavyLang"fr"
scores
fr0.8012232415902141
en0.726890756302521
it0.6788537549407115
tl0.5672436750998668
de0.5547945205479452
ca0.5535714285714286
ro0.49455676516329705
es0.48494453248811414
no0.473257698541329
da0.4425385934819897
sv0.4206773618538324
pt0.4058500914076782
nl0.40476190476190477
sl0.38446969696969696
sq0.3298969072164949
yo0.3298969072164949
fi0.30851063829787234
ms0.29501084598698485
lt0.2934782608695652
lv0.2934782608695652
hr0.2919389978213508
et0.2872807017543859
pl0.2111650485436893
cs0.19154228855721395
zh0.19154228855721395
tr0.1751269035532995
az0.1709183673469388
reliabletrue
passestrue