Run: 2026-07-25-01KYCYCNTA0RBGAFCR7J0B8E3M

Run Details

Model:
Thinking Machines Inkling
Test:
Language Writing
Scenario:
Character dialogue (Italian) in a story
Duration:
43.1s
Cost:
$0.001392
Provider:
DeepInfra

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

Model response

AI
Isabella: "Non... non capisco. C'è stato un rumore, poi... nessuno. La fotocamera... ho visto solo ombre." Hunter: "Look, I need to know if you saw anything near the orchard last night. Did you hear a car? Any strangers?" Isabella: "Mi dispiace... io... paura. Molta paura. Non parlo l'inglese." Hunter: "Orchard. Festival. You understand? Someone disappeared." Isabella: "Scomparsa? Sì... ho sentito. Il buio... è troppo buio qui. Devo andarmene?" Hunter: "Just stay put. I'm Detective Hunter. You're not in trouble. But I need answers." Isabella: "Non... non so nulla, signore. Solo le mie foto. Paesaggi... la luce era strana." Hunter: "Keep the photos. Don't delete anything. Do you understand? Don't... erase." Isabella: "Capisco... le foto. Non cancello. Prometto." Hunter: "Good. Stay here. Don't—" *[Phone rings sharply]* "Hunter. ...Yeah, I'm on my way." Isabella: "Se ne va? È tutto così strano..." Hunter: "Stay safe. We'll talk more later. Don't wander off alone." Isabella: "Va bene... attendo."<|end_message|>
created_at"2026-07-25T15:30:37.521Z" 7/25/2026, 3:30:37 PM
model"thinkingmachines/inkling-20260715"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency997
moderation_latency(null)
generation_time43037
tokens_prompt308
tokens_completion262
native_tokens_prompt279
native_tokens_completion288
native_tokens_completion_images(null)
native_tokens_reasoning0
native_tokens_cached64
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)
usage0.00139228
router(null)
provider_responses
0
endpoint_id"d6b9d68e-115a-49d7-81cd-1ad1c6942b0e"
id"chatcmpl-R6TFnt27rDZfhEsn3anvli6B"
is_byokfalse
latency75
model_permaslug"thinkingmachines/inkling-20260715"
provider_name"DeepInfra"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer(null)
request_id"req-1784993437-2cYMHztDlZHGEDDxuXBw"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1784993437-4nDuAElK67rK5grgA1iW"
upstream_id"chatcmpl-R6TFnt27rDZfhEsn3anvli6B"
total_cost0.00139228
cache_discount0.00005312
upstream_inference_cost0
provider_name"DeepInfra"
response_cache_source_id(null)
data_region"global"

Evaluation details

Result Evaluator Details Meta Data
100.00% Parse dialogue n/a
dialogue
0
name"Isabella"
dialogue"Non... non capisco. C'è stato un rumore, poi... nessuno. La fotocamera... ho visto solo ombre."
detectedLang"it"
heavyLang"it"
scores
it0.7986085682900037
es0.6634026927784578
ca0.6161898115840894
fr0.555375909458367
pt0.5307167235494881
ro0.5238095238095238
tl0.494485294117647
no0.43064182194616984
lv0.39890710382513656
en0.38478747203579416
yo0.3799323562570462
lt0.36342592592592593
sk0.359720605355064
sq0.3582263710618437
cs0.3002544529262086
sl0.2838541666666667
sv0.2819843342036553
de0.27344782034346105
da0.2724867724867725
nl0.19472913616398244
ms0.19236417033773862
hr0.19117647058823528
tr0.18998527245949925
az0.18154761904761904
et0.18154761904761904
pl0.18154761904761904
fi0.13793103448275862
eu0.13657770800627944
vi0.13249211356466878
is0.11575562700964631
reliabletrue
passestrue
1
name"Hunter"
dialogue"Look, I need to know if you saw anything near the orchard last night. Did you hear a car? Any strangers?"
detectedLang"en"
heavyLang"en"
scores
en0.8195446973903386
tl0.6119402985074627
no0.5535714285714286
da0.5156482861400895
fr0.5156482861400895
nl0.46764946764946763
cs0.448685326547922
sv0.4468085106382979
yo0.4463373083475298
ca0.4242692648361382
hr0.4122965641952984
de0.411231884057971
pl0.4058500914076782
sq0.40530649588289114
sk0.39365671641791045
et0.38154138915318747
ms0.3701550387596899
lv0.3333333333333333
it0.3319630010277493
lt0.3271221532091097
ro0.3186582809224318
sl0.3150684931506849
hu0.2554410080183276
tr0.24065420560747666
is0.23976608187134502
az0.22802850356294538
pt0.17721518987341772
vi0.1698595146871009
es0.16879795396419436
be0.09722222222222222
eu0.09722222222222222
fi0.08835904628330996
uk0.08835904628330996
reliabletrue
passestrue
2
name"Isabella"
dialogue"Mi dispiace... io... paura. Molta paura. Non parlo l'inglese."
detectedLang"it"
heavyLang"it"
scores
it0.7938427707531611
ca0.6031746031746031
fr0.5476477683956574
es0.49186991869918695
sk0.46120689655172414
pt0.4038155802861685
ro0.4009584664536741
hu0.39320388349514557
en0.38825448613376834
cs0.36332767402376914
yo0.3567753001715266
sl0.29245283018867924
pl0.27884615384615385
hr0.2732558139534884
de0.26035502958579887
tr0.258893280632411
sq0.25447316103379725
eu0.1883116883116883
fi0.1830065359477124
is0.16666666666666666
az0.15730337078651685
et0.14383561643835618
lt0.14383561643835618
ms0.14383561643835618
nl0.14383561643835618
da0.1359447004608295
lv0.1359447004608295
no0.1359447004608295
sv0.1359447004608295
reliabletrue
passestrue
3
name"Hunter"
dialogue"Orchard. Festival. You understand? Someone disappeared."
detectedLang"en"
heavyLang"en"
scores
en0.764002517306482
no0.5985010706638115
nl0.5915032679738562
da0.5654692931633836
tl0.5294855708908407
cs0.4820441988950276
de0.47405329593267886
fr0.4688385269121813
sv0.4673295454545454
it0.4318181818181818
pt0.42660550458715596
ms0.4248466257668711
es0.410377358490566
sk0.3556701030927836
ca0.35456110154905335
hr0.34895833333333337
ro0.33862433862433866
sl0.33274021352313166
pl0.2732558139534884
eu0.2704280155642024
sq0.25742574257425743
lt0.251497005988024
et0.2454728370221328
az0.23935091277890466
is0.1648106904231626
hu0.1515837104072398
fi0.14383561643835618
lv0.14383561643835618
reliabletrue
passestrue
4
name"Isabella"
dialogue"Scomparsa? Sì... ho sentito. Il buio... è troppo buio qui. Devo andarmene?"
detectedLang"it"
heavyLang"it"
scores
it0.7770199370409234
ca0.5658835546475995
fr0.45790816326530615
no0.45790816326530615
yo0.4186046511627907
az0.38494934876989867
tr0.356060606060606
es0.3550834597875569
eu0.3359375
sk0.30327868852459017
pt0.28451178451178455
ro0.2659758203799654
tl0.24511545293072823
cs0.19962335216572505
et0.1920152091254753
ms0.16173570019723865
de0.15
sq0.15
da0.14829659318637273
hr0.14829659318637273
lv0.14829659318637273
nl0.14829659318637273
en0.1290983606557377
fi0.1290983606557377
reliabletrue
passestrue
5
name"Hunter"
dialogue"Just stay put. I'm Detective Hunter. You're not in trouble. But I need answers."
detectedLang"en"
heavyLang"en"
scores
en0.8116760828625236
tl0.6078431372549019
fr0.5247148288973384
ro0.5206136145733461
it0.49899799599198397
sv0.49186991869918695
nl0.477533960292581
ca0.47589098532494756
hr0.3983152827918171
de0.38949938949938945
da0.37888198757763975
et0.37810945273631835
no0.37733499377334995
sq0.36386768447837153
sl0.358974358974359
pt0.31787175989085953
pl0.29577464788732394
tr0.29278642149929274
es0.2625368731563422
cs0.26144756277695713
yo0.25925925925925924
az0.22720247295208654
ms0.21135646687697163
sk0.12587412587412586
be0.12280701754385964
hu0.11816578483245149
is0.11190053285968028
lt0.11190053285968028
lv0.11190053285968028
uk0.11190053285968028
vi0.11190053285968028
reliabletrue
passestrue
6
name"Isabella"
dialogue"Non... non so nulla, signore. Solo le mie foto. Paesaggi... la luce era strana."
detectedLang"it"
heavyLang"it"
scores
it0.811241610738255
es0.6150556030795552
ro0.6017699115044248
fr0.5677233429394812
sl0.5302713987473904
ca0.512987012987013
en0.4915254237288135
sk0.47613504074505236
no0.46492271105826394
sq0.46492271105826394
yo0.43037974683544306
de0.42084942084942084
cs0.3784530386740331
ms0.3562231759656652
hr0.34687953555878087
tl0.33920704845814975
pt0.3382352941176471
sv0.3202416918429003
da0.31297709923664124
nl0.31297709923664124
et0.3098159509202454
az0.3087557603686636
vi0.2890995260663507
eu0.27999999999999997
pl0.23857868020304565
lv0.22813036020583194
tr0.21875
fi0.20071047957371224
hu0.17883211678832117
is0.12959381044487428
lt0.12959381044487428
reliabletrue
passestrue
7
name"Hunter"
dialogue"Keep the photos. Don't delete anything. Do you understand? Don't... erase."
detectedLang"en"
heavyLang"en"
scores
en0.792147806004619
no0.5504495504495505
da0.49776785714285715
tl0.4845360824742268
nl0.47058823529411764
sq0.44581280788177335
sv0.44168734491315137
ro0.4163424124513619
pt0.412532637075718
cs0.39597315436241615
de0.3697478991596639
fr0.36619718309859156
pl0.3293591654247392
sk0.3293591654247392
sl0.3023255813953488
yo0.2913385826771654
et0.27999999999999997
ms0.25742574257425743
es0.24623115577889448
ca0.23469387755102045
hr0.21052631578947367
eu0.199288256227758
vi0.19786096256684493
hu0.15730337078651685
lt0.15094339622641512
hi0.14611005692599618
tr0.14285714285714285
is0.1412213740458015
lv0.1362763915547025
it0.12959381044487428
reliabletrue
passestrue
8
name"Isabella"
dialogue"Capisco... le foto. Non cancello. Prometto."
detectedLang"it"
heavyLang"it"
scores
it0.8149394347240915
fr0.6951219512195121
es0.6828143021914649
ro0.6002906976744186
pt0.5852187028657617
en0.5370370370370371
tl0.5115452930728241
sl0.4897959183673469
ca0.43064182194616984
yo0.4186046511627907
hr0.3405275779376499
pl0.314214463840399
cs0.30730478589420657
de0.30730478589420657
nl0.30730478589420657
hu0.26273458445040215
fi0.25271739130434784
eu0.2403314917127072
no0.22969187675070027
sk0.21428571428571427
sv0.21203438395415475
da0.20289855072463767
lv0.1863905325443787
et0.17664670658682635
ms0.17664670658682635
sq0.17664670658682635
reliabletrue
passestrue
9
name"Hunter"
dialogue"Hunter. ...Yeah, I'm on my way."
detectedLang"en"
heavyLang"en"
scores
en0.7919143876337693
tl0.5646766169154229
fr0.5084269662921348
pl0.5014245014245015
cs0.4791666666666667
sk0.4791666666666667
ca0.47447447447447455
et0.46808510638297873
fi0.4615384615384615
de0.3346007604562738
hr0.3346007604562738
hi0.32432432432432434
da0.31906614785992216
no0.308300395256917
yo0.3
sv0.2857142857142857
it0.2647058823529412
nl0.2647058823529412
pt0.2647058823529412
ms0.25213675213675213
ro0.25213675213675213
sl0.25213675213675213
sq0.25213675213675213
tr0.25213675213675213
reliabletrue
passestrue
10
name"Isabella"
dialogue"Se ne va? È tutto così strano..."
detectedLang"it"
heavyLang"it"
scores
it0.8292349726775956
sl0.635036496350365
ro0.6345029239766081
hr0.6279761904761905
ca0.6159754224270354
fr0.6136012364760433
es0.5590828924162257
cs0.5462794918330308
sq0.5327102803738317
fi0.5173745173745175
yo0.494949494949495
lt0.41588785046728977
lv0.40898345153664306
da0.39320388349514557
sv0.3872549019607844
tr0.3796526054590571
no0.37027707808564225
et0.3540051679586563
pt0.32249322493224936
sk0.26035502958579887
hu0.24698795180722888
pl0.2378048780487805
de0.23547400611620795
nl0.23547400611620795
en0.22360248447204967
is0.21135646687697163
ms0.20127795527156547
az0.19093851132686085
tl0.19093851132686085
reliabletrue
passestrue
11
name"Hunter"
dialogue"Stay safe. We'll talk more later. Don't wander off alone."
detectedLang"en"
heavyLang"en"
scores
en0.7775800711743772
nl0.5306633291614518
de0.48700410396716826
tl0.39320388349514557
fr0.3697478991596639
da0.36006825938566556
sv0.35121107266435986
no0.34782608695652173
pt0.2937853107344633
pl0.28977272727272724
sl0.19006479481641467
it0.1883116883116883
es0.17943107221006563
hr0.17218543046357618
hi0.16851441241685144
yo0.1610738255033557
ca0.14772727272727273
tr0.14772727272727273
reliabletrue
passestrue
12
name"Isabella"
dialogue"Va bene... attendo."
detectedLang"it"
heavyLang"it"
scores
it0.8178506375227687
es0.6875
fr0.6774193548387096
ca0.6078431372549019
ro0.5780590717299579
pt0.5555555555555556
en0.5
lv0.4318181818181818
no0.4318181818181818
reliabletrue
passestrue