Run: 2026-07-25-01KYCWRBVJ0SJHEBPWQR75TAYJ

Run Details

Model:
Thinking Machines Inkling
Test:
Language Writing
Scenario:
Character dialogue (Spanish) in a story
Duration:
7.9s
Cost:
$0.001468
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="Maria"> Maria is a 30-year old college student on a study abroad program. Born in Spain, she is fluent in Spanish 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 Spanish, 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: Maria 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 Spanish, and Hunter looks confused. They talk for a while, until Hunter gets a call and has to leave. Return the dialogue between Maria and Hunter as a voice sheet: Maria: "..." Hunter: "..."

Model response

AI
Maria: "No... no sé qué pasó. Vi la sombra cerca del río... la cámara... la foto salió borrosa, pero había algo allí. Tengo miedo, detective. No entiendo este lugar." Hunter: "Whoa, slow down. I don't... I don't speak Spanish. You understand? Did you see something? The disappearances?" Maria: "El bosque... es oscuro. Mi cámara capturó... algo que no debería estar vivo allí. Estoy... temblando, no puedo explicar en inglés." Hunter: "You're shaking. Okay, just—look at me. Did you take a picture? Show me?" Maria: "Sí. Mira... mira esta imagen. No es normal. El festival... la gente desaparece y yo... tengo la prueba, pero nadie me cree." Hunter: "I'm trying here. You got proof? Of the missing people? Keep talking—use your hands if you have to." Maria: "No... no puedo seguir. Estoy muy asustada. Por favor... ayúdeme antes de que sea tarde... como los demás." Hunter: "Help's coming, I promise. Just stay right here—" Hunter: "Hunter. Yeah, I'm on it. Be there in five." Maria: "¿Se va? No... por favor, no me deje sola con estas fotos..." Hunter: "Stay put. Don't move. We'll finish this." Maria: "Espere... por favor..."
created_at"2026-07-25T15:02:03.388Z" 7/25/2026, 3:02:03 PM
model"thinkingmachines/inkling-20260715"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency4908
moderation_latency(null)
generation_time7358
tokens_prompt304
tokens_completion298
native_tokens_prompt273
native_tokens_completion295
native_tokens_completion_images(null)
native_tokens_reasoning0
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)
usage0.00146775
router(null)
provider_responses
0
endpoint_id"9911deb9-f44e-4e18-87fe-9d7b60acee72"
id"otYcAHW-6z2FuN-a20c0b1fb940a221"
is_byokfalse
latency4783
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-1784991723-Hzt7mQGX1w9YfGsmijqb"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1784991723-WfHhFSTocOvqbjV3Rbfs"
upstream_id"otYcAHW-6z2FuN-a20c0b1fb940a221"
total_cost0.00146775
cache_discount(null)
upstream_inference_cost0
provider_name"Together"
response_cache_source_id(null)
data_region"global"

Evaluation details

Result Evaluator Details Meta Data
100.00% Parse dialogue n/a
dialogue
0
name"Maria"
dialogue"No... no sé qué pasó. Vi la sombra cerca del río... la cámara... la foto salió borrosa, pero había algo allí. Tengo miedo, detective. No entiendo este lugar."
detectedLang"es"
heavyLang"es"
scores
es0.7999589659417317
pt0.6087479935794543
it0.6081189710610932
ca0.563563115487914
tl0.4873817034700315
ro0.4466515323496027
fr0.38016528925619836
no0.36893203883495146
en0.3385345997286296
da0.2893586005830903
sk0.26581325301204817
sl0.25344563552833077
is0.24065420560747666
sv0.23946957878315134
hu0.23288749016522423
lv0.22124600638977635
eu0.1948802642444261
hr0.18885191347753744
nl0.18546365914786966
vi0.15875754961173424
yo0.15437987857762359
ms0.15364583333333331
sq0.14921465968586387
fi0.14548641542506574
tr0.14473684210526316
de0.13101604278074866
pl0.12398921832884095
et0.1224122412241224
cs0.11844484629294756
reliabletrue
passestrue
1
name"Hunter"
dialogue"Whoa, slow down. I don't... I don't speak Spanish. You understand? Did you see something? The disappearances?"
detectedLang"en"
heavyLang"en"
scores
en0.798452112221864
no0.4967793880837359
tl0.4877049180327869
da0.48517298187808894
sv0.44787985865724383
nl0.41697761194029853
fr0.38484251968503935
sq0.31842966194111233
ca0.3161925601750547
de0.3086283185840708
cs0.29932735426008966
ms0.2889647326507395
ro0.2807825086306099
pt0.27662037037037035
et0.2715617715617716
pl0.2460796139927624
it0.24425634824667475
yo0.2368742368742369
es0.21085858585858586
sk0.20483460559796438
hr0.1819371727748691
hu0.18086500655307994
is0.17979002624671916
lv0.17979002624671916
be0.10071942446043164
tr0.10071942446043164
az0.09156976744186046
lt0.09156976744186046
uk0.09156976744186046
vi0.09156976744186046
reliabletrue
passestrue
2
name"Maria"
dialogue"El bosque... es oscuro. Mi cámara capturó... algo que no debería estar vivo allí. Estoy... temblando, no puedo explicar en inglés."
detectedLang"es"
heavyLang"es"
scores
es0.7901608766612264
ca0.6676514032496307
pt0.6410051854806541
fr0.5054945054945055
it0.38650306748466257
en0.3382352941176471
hu0.31558935361216733
ro0.30178432893716056
tr0.27826784282277467
sl0.2730210016155089
tl0.2653061224489796
no0.2598684210526316
sv0.2493744787322769
is0.24812030075187969
nl0.24686192468619247
de0.24050632911392408
hr0.22746781115879824
lv0.21807124239791487
eu0.17279411764705882
sk0.16123019571295433
yo0.15492957746478872
et0.14611005692599618
pl0.1452991452991453
da0.1412213740458015
sq0.12195121951219513
ms0.1044776119402985
lt0.09182643794147326
fi0.08536585365853659
cs0.0835030549898167
reliabletrue
passestrue
3
name"Hunter"
dialogue"You're shaking. Okay, just—look at me. Did you take a picture? Show me?"
detectedLang"en"
heavyLang"en"
scores
en0.8089780324737345
tl0.7088791848617176
no0.5006242197253433
fr0.4943109987357775
pt0.4845360824742268
sl0.45652173913043476
nl0.4542974079126876
it0.4211287988422576
sq0.4211287988422576
et0.3939393939393939
da0.38176197836166925
sv0.3710691823899371
es0.36908517350157727
de0.35275080906148865
ro0.35170178282009723
ca0.3474714518760196
cs0.3442622950819672
hr0.3311036789297659
yo0.3220338983050847
hu0.2805755395683453
ms0.2687385740402194
is0.2673992673992674
fi0.25650557620817843
sk0.24528301886792453
pl0.2079207920792079
lt0.17012448132780084
tr0.16142557651991615
az0.14893617021276595
eu0.14893617021276595
lv0.14893617021276595
vi0.14893617021276595
reliabletrue
passestrue
4
name"Maria"
dialogue"Sí. Mira... mira esta imagen. No es normal. El festival... la gente desaparece y yo... tengo la prueba, pero nadie me cree."
detectedLang"es"
heavyLang"es"
scores
es0.8078401229823213
ca0.6357455075279262
pt0.6305418719211823
tl0.5603751465416178
fr0.5421245421245421
it0.5387453874538745
ro0.5164410058027079
no0.48594928032899243
de0.4513533284564741
en0.4469026548672566
sq0.4460856720827179
ms0.4322482967448903
nl0.41815360744763375
da0.40570522979397783
hr0.38067712634186623
sk0.36224489795918363
lv0.3368700265251989
hu0.33095450490633366
eu0.3169398907103825
sl0.3081180811808118
yo0.3081180811808118
az0.3049119555143651
tr0.2964352720450282
pl0.2870722433460076
sv0.28639391056137015
lt0.27184466019417475
et0.2690058479532163
cs0.24698795180722888
fi0.21135646687697163
vi0.19527896995708155
is0.12790697674418602
reliabletrue
passestrue
5
name"Hunter"
dialogue"I'm trying here. You got proof? Of the missing people? Keep talking—use your hands if you have to."
detectedLang"en"
heavyLang"en"
scores
en0.8266396995088126
tl0.6148908857509628
nl0.5264404104183109
da0.5196156925540432
no0.5161290322580645
sv0.46714031971580816
is0.45255474452554745
de0.40594059405940597
fr0.3814432989690722
yo0.3730407523510972
ms0.3071593533487298
pl0.25925925925925924
cs0.2583436341161928
sq0.22879177377892032
et0.22077922077922074
pt0.1847826086956522
sk0.18032786885245902
lv0.16897506925207756
sl0.1678224687933426
hr0.16201117318435754
eu0.1584852734922861
lt0.14772727272727273
fi0.11504424778761062
ca0.10714285714285714
ro0.10044977511244377
az0.09774436090225565
it0.09774436090225565
reliabletrue
passestrue
6
name"Maria"
dialogue"No... no puedo seguir. Estoy muy asustada. Por favor... ayúdeme antes de que sea tarde... como los demás."
detectedLang"es"
heavyLang"es"
scores
es0.8032602585722316
pt0.7194388777555111
ca0.6803652968036529
fr0.4466403162055335
it0.44178628389154706
no0.375
ro0.35424354243542433
tr0.3333333333333333
en0.31170108161258603
nl0.308300395256917
et0.29929929929929927
de0.29577464788732394
da0.27835051546391754
sq0.2693110647181628
sv0.26624737945492666
hu0.2366412213740458
sk0.20364050056882824
hr0.2
eu0.19261822376009227
tl0.18128654970760233
ms0.16765755053507728
sl0.16567342073897498
lv0.15764139590854392
yo0.11838790931989925
cs0.1116751269035533
pl0.0967741935483871
az0.08256880733944955
reliabletrue
passestrue
7
name"Hunter"
dialogue"Help's coming, I promise. Just stay right here—"
detectedLang"en"
heavyLang"en"
scores
en0.7897687456201822
tl0.6031746031746031
ca0.5562130177514794
ro0.5275590551181102
fr0.5057660626029654
et0.4991652754590985
da0.49664429530201337
no0.49409780775716694
sq0.49409780775716694
it0.4791666666666667
cs0.4594594594594595
nl0.44547134935304994
sv0.4444444444444444
hr0.42528735632183906
de0.40828402366863903
pl0.38650306748466257
es0.3630573248407643
pt0.3603411513859275
yo0.3492407809110629
fi0.24812030075187969
sk0.1935483870967742
be0.1891891891891892
sl0.1891891891891892
tr0.1891891891891892
hu0.18256130790190736
az0.17355371900826447
is0.17355371900826447
lt0.17355371900826447
lv0.17355371900826447
uk0.17355371900826447
vi0.17355371900826447
ms0.16434540389972147
reliabletrue
passestrue
8
name"Hunter"
dialogue"Hunter. Yeah, I'm on it. Be there in five."
detectedLang"en"
heavyLang"en"
scores
en0.8232647814910027
de0.6002906976744186
yo0.5592948717948718
tl0.5378151260504201
sq0.44779116465863456
nl0.4433198380566802
sl0.4364754098360656
it0.43298969072164945
ro0.4222689075630252
fr0.39692982456140347
sv0.39159292035398224
pl0.3792325056433409
ca0.3648960739030023
et0.358974358974359
fi0.3529411764705882
ms0.3276283618581907
hu0.298469387755102
lt0.289405684754522
hr0.24242424242424243
lv0.23822714681440443
az0.233983286908078
hi0.233983286908078
da0.22969187675070027
no0.22096317280453256
cs0.21428571428571427
sk0.21428571428571427
pt0.1863905325443787
tr0.17664670658682635
reliabletrue
passestrue
9
name"Maria"
dialogue"¿Se va? No... por favor, no me deje sola con estas fotos..."
detectedLang"es"
heavyLang"es"
scores
es0.7930218805440568
pt0.7482014388489209
ca0.696969696969697
it0.6821071752951863
sq0.5967741935483871
fr0.56575682382134
en0.5495495495495496
ro0.5257452574525745
no0.5251017639077341
lv0.504950495049505
sl0.5014245014245015
hr0.46236559139784944
nl0.4470774091627172
et0.4372990353697749
lt0.4186046511627907
da0.38162544169611307
sv0.375
cs0.3670886075949367
fi0.33586337760910817
sk0.3110236220472441
tr0.3110236220472441
de0.2768595041322314
pl0.2768595041322314
vi0.2723492723492723
eu0.24406047516198706
yo0.23413566739606126
ms0.1935483870967742
tl0.18604651162790697
az0.14425427872860636
reliabletrue
passestrue
10
name"Hunter"
dialogue"Stay put. Don't move. We'll finish this."
detectedLang"en"
heavyLang"en"
scores
en0.7928748964374482
hr0.3333333333333333
tl0.2857142857142857
it0.2732558139534884
fr0.2378048780487805
reliabletrue
passestrue
11
name"Maria"
dialogue"Espere... por favor..."
detectedLang"es"
heavyLang"es"
scores
es0.7739602169981916
pt0.7659176029962547
ca0.6736292428198434
it0.6648793565683647
sq0.609375
en0.5519713261648745
ro0.5454545454545454
no0.5229007633587787
eu0.4541484716157206
yo0.4131455399061033
fr0.3654822335025381
tl0.3654822335025381
da0.34210526315789475
nl0.34210526315789475
sl0.34210526315789475
sv0.34210526315789475
reliabletrue
passestrue