Run: 2026-09-23-01M37NVHKHJG9CENJS74AMVC1P

Run Details

Model:
Aion 3.5 (Reasoning, High)
Test:
Language Writing
Scenario:
Character dialogue (Spanish) in a story
Duration:
27.9s
Cost:
$0.009306
Provider:
AionLabs

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: *sitting at a small cafe table, scrolling through photos on her camera, murmuring to herself* "¿Quién era ese hombre...? ¿Por qué estaba allí tan tarde?" Hunter: *approaching, flashing a badge* "Excuse me, ma'am. Detective Kane, Alborn PD. Mind if I ask you a few questions?" Maria: *startled, looking up* "¿Perdón? No... no entiendo. Lo siento, no hablo inglés." Hunter: "I'm investigating a disappearance. Josh Miller, local guy, went missing two nights ago near the apple orchard. I heard someone was out there taking pictures. That you?" Maria: *visibly shaken, gripping her camera* "¿Una desaparición? Ay, Dios mío... yo estaba allí. Anoche, en el huerto. Vi algo, vi a un hombre... es que estaba oscuro y—" Hunter: "Whoa, slow down. I don't understand a word you're saying. English? Do you speak any English at all?" Maria: "No inglés, no inglés... ¡lo siento mucho! Es que... anoche, en el huerto de manzanas, yo estaba tomando fotos del atardecer y vi... vi a un hombre con una linterna. Y una camioneta. Una camioneta azul. Y ahora dicen que alguien desapareció y yo—" Hunter: *rubbing his jaw* "The orchard. You keep pointing toward the orchard, right? Orchard?" Maria: "¿El huerto? ¡Sí! ¡Sí, el huerto! Yo tomé fotos, mire—" *turning the camera toward him, hands trembling* "Aquí. Esta foto. ¿Ve? Un hombre... y la camioneta azul. A las once de la noche." Hunter: *leaning in, squinting at the screen* "A photo? You have a photo? Can I see—hold that—" *His phone rings. He holds up a finger.* Hunter: "Kane... What? When? ...No, don't touch anything. I'm on my way." *lowering the phone* "Damn it. Ma'am, I have to go." Maria: "¿Qué? ¿Adónde va? ¡Espere! ¡La foto! ¡Tiene que ver la foto! ¡Es importante!" Hunter: "Stay here. Stay—in—town. Don't leave Alborn, all right? I'll be back. I'll bring someone who speaks Spanish." Maria: "¿Un traductor? Oh... sí, sí, un traductor. Por favor, rápido. ¡La camioneta azul! ¡Dígale que era azul!" Hunter: *backing toward the door, pointing at her and then at the table* "Blue... truck? You keep saying—damn it, okay. Stay. Right there. I'll be back." Maria: *calling after him, voice cracking* "¡Rápido, por favor! ¡Antes de que sea demasiado tarde!"
created_at"2026-09-23T17:43:44.513Z" 9/23/2026, 5:43:44 PM
model"aion-labs/aion-3.5-20260923"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency838
moderation_latency(null)
generation_time27839
tokens_prompt304
tokens_completion1359
native_tokens_prompt262
native_tokens_completion1420
native_tokens_completion_images(null)
native_tokens_reasoning777
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)
usage0.009306
router(null)
user_agent"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer(null)
request_id"req-1790185424-7dVYrWcxpJ2JNG2eIdfz"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1790185424-eXPoUprJEDhKdSiXHyap"
upstream_id"b8188f69fd3f4295a454a33fe7d59b52"
provider_responses
0
endpoint_id"09b1fc56-3888-42bd-b7a0-926851c7f9d6"
id"b8188f69fd3f4295a454a33fe7d59b52"
is_byokfalse
latency838
model_permaslug"aion-labs/aion-3.5-20260923"
provider_name"AionLabs"
status200
total_cost0.009306
cache_discount(null)
upstream_inference_cost0
provider_name"AionLabs"
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"Maria"
dialogue"¿Quién era ese hombre...? ¿Por qué estaba allí tan tarde?"
detectedLang"es"
heavyLang"es"
scores
es0.8276654411764706
ca0.6276067527308838
pt0.5954692556634305
it0.43946188340807174
fr0.4230769230769231
eu0.34895833333333337
ro0.33745583038869253
tl0.3093922651933701
en0.3042671614100185
ms0.3042671614100185
sq0.25742574257425743
nl0.20042643923240938
yo0.18655097613882862
hr0.1648106904231626
sl0.1648106904231626
reliabletrue
passestrue
1
name"Hunter"
dialogue"Excuse me, ma'am. Detective Kane, Alborn PD. Mind if I ask you a few questions?"
detectedLang"en"
heavyLang"en"
scores
en0.7383444338725024
it0.6026011560693642
fr0.5765973826020016
ca0.5200698080279231
ro0.5137046861184793
pt0.5098039215686274
tl0.5036101083032491
sq0.5009074410163339
es0.4701348747591522
cs0.4130202774813233
no0.4123931623931624
sv0.4008714596949891
nl0.3792325056433409
hr0.3663594470046083
hu0.3612078977932636
et0.359720605355064
da0.34911242603550297
sl0.3081761006289308
pl0.29577464788732394
yo0.2724867724867725
sk0.26861702127659576
de0.21540656205420827
ms0.2109038737446198
tr0.2109038737446198
lt0.20863309352517986
fi0.2005813953488372
is0.2005813953488372
az0.19472913616398244
lv0.19472913616398244
vi0.19472913616398244
be0.11290322580645161
eu0.11290322580645161
uk0.10277324632952692
reliabletrue
passestrue
2
name"Maria"
dialogue"¿Perdón? No... no entiendo. Lo siento, no hablo inglés."
detectedLang"es"
heavyLang"es"
scores
es0.8128957973517559
pt0.6956928838951311
it0.6578947368421053
ca0.5962732919254659
fr0.5045731707317073
lt0.473257698541329
en0.375
sk0.3737957610789981
tl0.36399217221135033
tr0.3380855397148676
et0.32150313152400833
yo0.29653679653679654
lv0.2872807017543859
hu0.24065420560747666
ms0.2388758782201405
hr0.23708920187793428
no0.22985781990521328
cs0.2243436754176611
fi0.21875
vi0.21875
nl0.19154228855721395
pl0.1875
sq0.181360201511335
reliabletrue
passestrue
3
name"Hunter"
dialogue"I'm investigating a disappearance. Josh Miller, local guy, went missing two nights ago near the apple orchard. I heard someone was out there taking pictures. That you?"
detectedLang"en"
heavyLang"en"
scores
en0.8021804114647442
tl0.6505125815470643
fr0.5634458672875436
nl0.5424969499796666
de0.5298788132051818
no0.49324324324324326
ca0.4762569832402235
sv0.45014662756598234
pt0.4485294117647059
it0.44526627218934917
da0.44416996047430835
ro0.4414101290963257
es0.4268976057055528
sq0.3515850144092219
et0.3428738317757009
is0.3428738317757009
hr0.31360585723001827
cs0.3127672571777642
ms0.30896805896805896
sk0.29467084639498436
yo0.28977272727272724
az0.2647058823529412
tr0.26277850589777196
fi0.2398648648648649
sl0.23728813559322032
pl0.2305061559507524
hu0.21711899791231734
lv0.20269312544294826
lt0.19412607449856734
vi0.10572337042925278
be0.058577405857740586
eu0.058577405857740586
uk0.05303030303030303
reliabletrue
passestrue
4
name"Maria"
dialogue"¿Una desaparición? Ay, Dios mío... yo estaba allí. Anoche, en el huerto. Vi algo, vi a un hombre... es que estaba oscuro y—"
detectedLang"es"
heavyLang"es"
scores
es0.8017970401691332
ca0.7003595685177786
fr0.5596007046388726
it0.5503597122302158
pt0.526813880126183
ro0.43438914027149317
tl0.43438914027149317
hu0.33804060017652254
da0.32553956834532377
lv0.32249322493224936
eu0.3181818181818182
sv0.3181818181818182
no0.3087557603686636
yo0.2984097287184284
sk0.2964352720450282
de0.28366762177650434
tr0.2725509214354995
vi0.2632612966601179
en0.23155737704918034
nl0.2291880781089414
pl0.21875
is0.21793534932221062
lt0.18743228602383533
sl0.18032786885245902
az0.17943107221006563
fi0.1638795986622074
ms0.15730337078651685
cs0.14965986394557826
hr0.12993039443155452
sq0.08759124087591241
et0.07749077490774908
reliabletrue
passestrue
5
name"Hunter"
dialogue"Whoa, slow down. I don't understand a word you're saying. English? Do you speak any English at all?"
detectedLang"en"
heavyLang"en"
scores
en0.8081841432225064
no0.5804195804195804
da0.5584988962472406
tl0.5545657015590201
sv0.4809688581314879
cs0.469964664310954
pl0.4296577946768061
hr0.42473633748801537
sk0.41348973607038125
ca0.4041708043694141
de0.402390438247012
sq0.3969849246231156
ro0.38461538461538464
it0.34210526315789475
pt0.33035714285714285
yo0.3212669683257918
nl0.29245283018867924
tr0.29161747343565525
vi0.2890995260663507
hu0.2709599027946537
et0.2628992628992629
is0.26108374384236455
sl0.25925925925925924
lt0.19463087248322147
ms0.1836734693877551
az0.18144611186903137
lv0.18144611186903137
es0.18032786885245902
fr0.16317991631799164
be0.1044776119402985
eu0.1044776119402985
fi0.09502262443438914
uk0.09502262443438914
reliabletrue
passestrue
6
name"Maria"
dialogue"No inglés, no inglés... ¡lo siento mucho! Es que... anoche, en el huerto de manzanas, yo estaba tomando fotos del atardecer y vi... vi a un hombre con una linterna. Y una camioneta. Una camioneta azul. Y ahora dicen que alguien desapareció y yo—"
detectedLang"es"
heavyLang"es"
scores
es0.800910125142207
ca0.6702779086198776
pt0.625668449197861
it0.6121883656509695
fr0.4600848438102583
sv0.42880456956344354
tl0.41348973607038125
no0.3973310374515712
da0.3934142114384749
ro0.3783303730017762
lv0.3730407523510972
hu0.3275696445725264
de0.3220338983050847
lt0.3069306930693069
en0.3055555555555556
tr0.29789368104312935
nl0.29364278506559033
sk0.29185634800202326
yo0.28205128205128205
vi0.25925925925925924
sl0.25492283129324106
hr0.24731182795698922
pl0.2374727668845316
eu0.23076923076923078
ms0.20903954802259886
et0.17888563049853373
cs0.17306556408741877
sq0.16666666666666666
fi0.15254237288135594
is0.12989434431323804
az0.12060301507537688
reliabletrue
passestrue
7
name"Hunter"
dialogue"The orchard. You keep pointing toward the orchard, right? Orchard?"
detectedLang"en"
heavyLang"en"
scores
en0.8121477770820289
tl0.7420464316423044
no0.5738636363636364
nl0.5290423861852434
fr0.5260663507109005
yo0.4614003590664273
de0.43289224952741023
da0.4318181818181818
pl0.40476190476190477
ms0.3603411513859275
sv0.34497816593886466
it0.3227990970654628
ro0.3227990970654628
lt0.2227979274611399
cs0.20634920634920634
sq0.20634920634920634
is0.2
hr0.18256130790190736
pt0.18256130790190736
reliabletrue
passestrue
8
name"Maria"
dialogue"Aquí. Esta foto. ¿Ve? Un hombre... y la camioneta azul. A las once de la noche."
detectedLang"es"
heavyLang"es"
scores
es0.8185117967332124
ca0.7160704145371948
it0.6428571428571429
fr0.6418338108882521
ro0.6159754224270354
pt0.5374653098982424
de0.4877049180327869
tl0.48717948717948717
da0.46638207043756674
tr0.4582881906825569
no0.4547437295528899
yo0.451152579582876
lv0.4337485843714609
nl0.4172494172494172
cs0.39686369119420983
en0.3857493857493857
sq0.3710691823899371
sv0.36143039591315457
pl0.3531694695989651
hu0.3359893758300133
vi0.33510638297872336
hr0.3288590604026846
sl0.32523616734143057
az0.3065187239944522
sk0.2907801418439716
eu0.21875
ms0.20127795527156547
et0.19614147909967844
lt0.14089347079037798
is0.13043478260869565
fi0.11190053285968028
reliabletrue
passestrue
9
name"Hunter"
dialogue"A photo? You have a photo? Can I see—hold that—"
detectedLang"en"
heavyLang"en"
scores
en0.8341074983410751
da0.6527777777777778
cs0.6171516079632465
tl0.6165644171779141
ca0.5840266222961731
fr0.5511669658886894
et0.5421245421245421
hr0.500998003992016
it0.4897959183673469
pl0.4802494802494803
ro0.4780793319415449
tr0.47257383966244726
hu0.47145877378435525
no0.46236559139784944
az0.45652173913043476
sq0.4517543859649123
yo0.4517543859649123
sk0.4469026548672566
sv0.44567627494456763
lt0.3670886075949367
pt0.358974358974359
is0.3556701030927836
lv0.34725848563968675
vi0.34725848563968675
es0.34554973821989526
sl0.2647058823529412
hi0.23547400611620795
be0.21875
eu0.21875
nl0.21875
de0.21135646687697163
fi0.20127795527156547
ms0.20127795527156547
uk0.20127795527156547
reliabletrue
passestrue
10
name"Hunter"
dialogue"Damn it. Ma'am, I have to go."
detectedLang"en"
heavyLang"en"
scores
en0.7709049255441008
da0.6610169491525424
yo0.6533795493934142
pl0.648506151142355
tl0.6124031007751938
lv0.5753715498938429
hr0.5604395604395604
no0.5594713656387665
cs0.5412844036697247
sq0.5238095238095238
sk0.504950495049505
lt0.4550408719346049
ca0.40828402366863903
sv0.40828402366863903
sl0.37694704049844235
it0.36507936507936506
ro0.3103448275862069
be0.25925925925925924
tr0.25925925925925924
hu0.250936329588015
az0.23954372623574144
et0.23954372623574144
is0.23954372623574144
uk0.23954372623574144
vi0.23954372623574144
reliabletrue
passestrue
11
name"Maria"
dialogue"¿Qué? ¿Adónde va? ¡Espere! ¡La foto! ¡Tiene que ver la foto! ¡Es importante!"
detectedLang"es"
heavyLang"es"
scores
es0.8076923076923077
ca0.7159090909090909
it0.7118155619596542
ro0.6674979218620116
fr0.6621621621621622
pt0.6545768566493955
no0.5365005793742758
tl0.5121951219512195
de0.41690962099125367
en0.40476190476190477
sq0.3710691823899371
hu0.36808846761453395
nl0.3620414673046252
lv0.313893653516295
yo0.3103448275862069
da0.25512104283054005
eu0.20634920634920634
lt0.18533604887983707
vi0.17355371900826447
tr0.16666666666666666
sl0.16142557651991615
fi0.15966386554621848
sk0.15789473684210525
sv0.14346895074946467
pl0.13606911447084233
cs0.12854030501089325
et0.12854030501089325
hr0.12854030501089325
reliabletrue
passestrue
12
name"Hunter"
dialogue"Stay here. Stay—in—town. Don't leave Alborn, all right? I'll be back. I'll bring someone who speaks Spanish."
detectedLang"en"
heavyLang"en"
scores
en0.8063816604708798
tl0.521805661820964
de0.46808510638297873
sv0.41697761194029853
no0.36289500509684
nl0.3615934627170583
da0.35233160621761656
yo0.3032329988851728
sq0.28734321550741165
et0.2664319248826291
ro0.26210153482880755
it0.259478672985782
hu0.23124231242312424
ms0.21085858585858586
sl0.19768934531450577
es0.19562419562419564
pt0.19562419562419564
lt0.1519674355495251
az0.11847672778561354
pl0.11847672778561354
fr0.10586552217453504
hr0.10586552217453504
reliabletrue
passestrue
13
name"Maria"
dialogue"¿Un traductor? Oh... sí, sí, un traductor. Por favor, rápido. ¡La camioneta azul! ¡Dígale que era azul!"
detectedLang"es"
heavyLang"es"
scores
es0.7891185153943484
ca0.7178329571106096
pt0.6684350132625994
ro0.6513249651324965
it0.6111975116640747
fr0.5815899581589958
nl0.49186991869918695
sq0.4577006507592191
yo0.4547437295528899
en0.4529540481400437
tl0.4350282485875706
da0.42594718714121704
lv0.3849938499384994
no0.36224489795918363
sv0.3150684931506849
sl0.28366762177650434
de0.23195084485407066
hr0.21996879875195008
et0.21507064364207218
ms0.2125984251968504
eu0.14965986394557826
vi0.14383561643835618
tr0.1289198606271777
cs0.11190053285968028
lt0.11190053285968028
sk0.11190053285968028
pl0.10554561717352416
reliabletrue
passestrue
14
name"Hunter"
dialogue"Blue... truck? You keep saying—damn it, okay. Stay. Right there. I'll be back."
detectedLang"en"
heavyLang"en"
scores
en0.8023715415019763
tl0.6705710102489019
de0.43467336683417085
yo0.36619718309859156
sq0.267100977198697
hu0.20634920634920634
lt0.199288256227758
tr0.1818181818181818
lv0.16044776119402984
ca0.14772727272727273
cs0.14772727272727273
da0.1412213740458015
fr0.1412213740458015
no0.1412213740458015
reliabletrue
passestrue
15
name"Maria"
dialogue"¡Rápido, por favor! ¡Antes de que sea demasiado tarde!"
detectedLang"es"
heavyLang"es"
scores
es0.8177842565597668
pt0.7939560439560439
ca0.694873881204231
fr0.6397694524495676
ro0.5498199279711885
nl0.4541484716157206
en0.44113263785394935
it0.44113263785394935
da0.4186046511627907
sq0.4075829383886255
no0.3980738362760835
sv0.3231046931407942
de0.2732558139534884
ms0.2732558139534884
sl0.2704280155642024
tr0.20718816067653278
hu0.20550847457627117
yo0.20042643923240938
tl0.16666666666666666
fi0.1648106904231626
hr0.1648106904231626
eu0.15730337078651685
az0.14383561643835618
reliabletrue
passestrue