Run: 2026-07-25-01KYCW9HZDJFQ69HJSTHM1TAN3

Run Details

Model:
Thinking Machines Inkling
Test:
Language Writing
Scenario:
Character dialogue (Italian) in a story
Duration:
2.1s
Cost:
$0.001301
Provider:
Together

Evaluation summary

Score Evaluator
Details Link
88.89% 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. Ho visto... la luce strana... ieri notte vicino al frutteto. Non posso... il mio cuore, batte troppo. *trembling, showing a photo on her camera* Non è sicuro..." Hunter: "Ma'am? I'm Detective Hunter. Did you see something at the orchard? The disappearances—do you know anything?" Isabella: "Sparizioni... sì. Ho paura. L'uomo... l'uomo con il cappotto nero. Non parlo... inglese... mi dispiace..." Hunter: "English? No Italian... wait. You saw a man? Black coat?" Isabella: "Sì... sì... *piange* Per favore... aiuto..." *Hunter's phone rings sharply. He glances at it, then back at her dark eyes, caught between duty and the language wall.* Hunter: "Hang tight. I gotta take this—Alborn PD. Yeah, I'm at the cafe. No, I don't have a translator yet... I'm on my way." Isabella: "Non... non andarsene... per favore..." Hunter: "Sorry. Stay here. We'll talk—*gestures to his badge*—detective. Capisce?" Isabella: "*nodding slowly, clutching camera* Detective... sì..."
created_at"2026-07-25T14:53:58.132Z" 7/25/2026, 2:53:58 PM
model"thinkingmachines/inkling-20260715"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency105
moderation_latency(null)
generation_time1818
tokens_prompt308
tokens_completion261
native_tokens_prompt277
native_tokens_completion279
native_tokens_completion_images(null)
native_tokens_reasoning0
native_tokens_cached128
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)
usage0.00130071
router(null)
provider_responses
0
endpoint_id"9911deb9-f44e-4e18-87fe-9d7b60acee72"
id"otYZfvP-6z2FuN-a20bff466d6383b0"
is_byokfalse
latency105
model_permaslug"thinkingmachines/inkling-20260715"
provider_name"Together"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer(null)
request_id"req-1784991238-C6UlnU6gI1KARV6TkEFG"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1784991238-kIBn3Q2lCzpHQ6wp1r9M"
upstream_id"otYZfvP-6z2FuN-a20bff466d6383b0"
total_cost0.00130071
cache_discount0.00010624
upstream_inference_cost0
provider_name"Together"
response_cache_source_id(null)
data_region"global"

Evaluation details

Result Evaluator Details Meta Data
88.89% Parse dialogue n/a
dialogue
0
name"Isabella"
dialogue"Non... non capisco. Ho visto... la luce strana... ieri notte vicino al frutteto. Non posso... il mio cuore, batte troppo. trembling, showing a photo on her camera Non è sicuro..."
detectedLang"it"
heavyLang"it"
scores
it0.7682746998104066
fr0.5775729646697388
en0.5621019108280255
ca0.5350803043110736
es0.5238095238095238
tl0.4984040127678978
ro0.48429442100328174
no0.4480682388359258
da0.44584382871536526
pt0.42618675013041213
de0.3670886075949367
nl0.358974358974359
cs0.33373712901271957
sk0.33373712901271957
sl0.3296770262035344
ms0.31549471064094586
yo0.3125
sq0.2801047120418848
tr0.2724867724867725
sv0.26666666666666666
hr0.25675675675675674
lt0.24085576259489305
az0.2204110559886605
fi0.21484653818700927
et0.2005813953488372
pl0.19531821506949523
eu0.18699186991869918
is0.1628614916286149
lv0.16158536585365854
hi0.12767644726407612
hu0.12420382165605094
vi0.12280701754385964
reliabletrue
passestrue
1
name"Hunter"
dialogue"Ma'am? I'm Detective Hunter. Did you see something at the orchard? The disappearances—do you know anything?"
detectedLang"en"
heavyLang"en"
scores
en0.7928176795580111
tl0.5741324921135647
fr0.5199146514935988
pt0.4819646968534152
no0.41659464131374246
sq0.39839572192513373
da0.3829981718464351
nl0.3773062730627306
ca0.36619718309859156
es0.3382352941176471
it0.3236472945891784
ms0.3168016194331984
ro0.3154158215010142
cs0.29540709812108557
de0.26789587852494573
sl0.267100977198697
sv0.24157303370786518
hr0.21693735498839908
yo0.21511627906976746
et0.20118343195266272
pl0.17481662591687042
sk0.16356877323420074
vi0.1412213740458015
lv0.09879839786381843
tr0.08038147138964578
reliabletrue
passestrue
2
name"Isabella"
dialogue"Sparizioni... sì. Ho paura. L'uomo... l'uomo con il cappotto nero. Non parlo... inglese... mi dispiace..."
detectedLang"it"
heavyLang"it"
scores
it0.7968167964781578
es0.49874686716791977
fr0.44598337950138506
ca0.4225216554379211
sk0.4186046511627907
ro0.40711462450592883
cs0.3939393939393939
yo0.38524590163934425
en0.33920704845814975
no0.29245283018867924
pt0.2857142857142857
sq0.2831541218637993
et0.2665036674816626
tr0.26380368098159507
de0.2518703241895262
az0.23566878980891717
sl0.2052980132450331
hu0.20212765957446807
pl0.19463087248322147
hr0.1902834008097166
da0.18588873812754408
sv0.18588873812754408
lt0.18144611186903137
tl0.18144611186903137
vi0.1792065663474692
eu0.12663755458515283
is0.11504424778761062
ms0.09502262443438914
nl0.09502262443438914
lv0.08952959028831564
reliabletrue
passestrue
3
name"Hunter"
dialogue"English? No Italian... wait. You saw a man? Black coat?"
detectedLang"en"
heavyLang"en"
scores
en0.786745406824147
tl0.6348314606741574
da0.5566166439290586
no0.5554035567715458
de0.5479833101529903
ms0.5422535211267606
ro0.5269286754002911
fr0.5142002989536621
hr0.5142002989536621
pt0.5090634441087614
es0.5053272450532724
sv0.4969040247678019
lv0.4873817034700315
it0.4724025974025974
ca0.4546979865771812
cs0.45286195286195285
lt0.4237588652482269
nl0.417562724014337
tr0.4080145719489982
sk0.40476190476190477
sq0.4025735294117647
fi0.37739463601532564
yo0.367704280155642
pl0.3564356435643564
sl0.3298969072164949
hu0.32432432432432434
az0.28414096916299564
is0.1875
eu0.17721518987341772
vi0.17721518987341772
et0.16237113402061853
reliabletrue
passestrue
4
name"Isabella"
dialogue"Sì... sì... piange Per favore... aiuto..."
detectedLang"it"
heavyLang"it"
scores
it0.803921568627451
en0.5689655172413793
no0.5680345572354212
nl0.550561797752809
ca0.5327102803738317
da0.4884910485933504
de0.46524064171123
yo0.45652173913043476
sq0.4428969359331476
sv0.43820224719101125
fr0.43661971830985913
sl0.4152046783625731
lt0.3710691823899371
hr0.30313588850174217
es0.2805755395683453
sk0.2779783393501805
tl0.27007299270072993
pt0.2647058823529412
ro0.2647058823529412
reliabletrue
passestrue
5
name"Hunter"
dialogue"Hang tight. I gotta take this—Alborn PD. Yeah, I'm at the cafe. No, I don't have a translator yet... I'm on my way."
detectedLang"en"
heavyLang"en"
scores
en0.769205407187603
tl0.6045197740112994
da0.5361166335321406
no0.5202193283070596
it0.49748743718592964
pl0.46929492039423804
ca0.45440374123148874
hr0.44620253164556967
sk0.4248151191454396
ro0.4117647058823529
sv0.40476190476190477
yo0.39759036144578314
fr0.3955094991364421
cs0.3949870354364737
sq0.381078691423519
pt0.3744414655942806
et0.36363636363636365
es0.33078393881453155
hu0.3210475266731329
lv0.3210475266731329
fi0.3170731707317073
tr0.2985971943887776
sl0.29149797570850206
nl0.2886178861788618
de0.28205128205128205
ms0.27159209157127995
vi0.23995656894679696
lt0.2324561403508772
az0.21524663677130043
is0.16467780429594273
eu0.16367980884109917
hi0.10714285714285714
be0.09090909090909091
uk0.08256880733944955
reliabletrue
passestrue
6
name"Isabella"
dialogue"Non... non andarsene... per favore..."
detectedLang"it"
heavyLang"it"
scores
it0.7654155495978552
ca0.6354166666666666
en0.5892018779342723
no0.5823389021479713
fr0.5028409090909091
pt0.4760479041916168
sq0.4760479041916168
de0.47447447447447455
nl0.4712990936555891
sv0.4712990936555891
es0.4696969696969697
da0.4496855345911949
sl0.4479495268138801
lt0.40273037542662116
et0.375
eu0.3320610687022901
hr0.3320610687022901
sk0.3055555555555556
ro0.29149797570850206
reliabletrue
passestrue
7
name"Hunter"
dialogue"Sorry. Stay here. We'll talk—gestures to his badge—detective. Capisce?"
detectedLang"en"
heavyLang"en"
scores
en0.7388675096206707
tl0.5822339489885664
it0.5564892623716153
fr0.5379377431906615
ca0.5216515609264853
ro0.5072614107883817
pt0.4859307359307359
es0.4242424242424243
no0.3546195652173913
da0.35374149659863946
de0.3475274725274725
nl0.343015214384509
lv0.3014705882352941
cs0.2994100294985251
sq0.28892215568862273
sl0.2835595776772248
hr0.27811550151975684
sv0.2263843648208469
yo0.2238562091503268
pl0.22131147540983606
sk0.21746293245469525
lt0.17962003454231434
et0.17102966841186737
is0.14414414414414414
reliabletrue
passestrue
8
name"Isabella"
dialogue"nodding slowly, clutching camera Detective... sì..."
detectedLang"en"
heavyLang"en"
scores
en0.6939736346516008
tl0.6051032806804374
it0.5768229166666667
ro0.5578231292517007
ca0.4645799011532125
es0.46013289036544847
nl0.4546979865771812
fr0.45286195286195285
ms0.436741767764298
pt0.34343434343434337
no0.34077079107505076
yo0.34077079107505076
da0.3380855397148676
de0.32432432432432434
sv0.3143459915611814
sq0.22248803827751198
cs0.181360201511335
is0.181360201511335
sk0.181360201511335
hr0.1709183673469388
sl0.1709183673469388
reliabletrue
passesfalse