Run: 2026-09-24-01M39VGN34TP18Z58NAH5V2MTS

Run Details

Model:
Aion 3.5 Mini (Reasoning, High)
Test:
Language Writing
Scenario:
Character dialogue (Spanish) in a story
Duration:
55.9s
Cost:
$0.003413
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: "¿Perdón? No entiendo... ¿Hablas español?" Hunter: "Ma'am, I don't have time for charades. Did you see anything near the apple orchard yesterday? Anyone acting strange?" Maria: "¿El huerto de manzanas? ¡Dios mío! ¿Estás preguntando por Elena? ¡Ella estaba allí ayer!" Hunter: "You know Elena? Where was she? Ma'am, focus." Maria: "¡Sí, sí! La vi en el sendero. Estaba tomando fotos de la niebla... yo estaba con mi cámara... ¡pero había un hombre! ¡Un hombre en el borde del bosque!" Hunter: "A man? Where? Did you get a name? Do you speak English at all?" Maria: "¡No hablo inglés! ¡Escucha! ¡El hombre llevaba una chaqueta verde! ¡Ella corrió hacia el lago y el hombre la siguió! ¡Lo tengo en una foto! ¡Aquí, mira!" Hunter: "I can't read that, lady. It's all Spanish to me. Look, I've got a crime scene to check. Do you have a translator? A friend? Anyone?" Maria: "¡No entiendes! ¡La foto! ¡Tengo la foto del hombre! ¡Se la puedo mostrar! ¡Espera, no te vayas!" Hunter: "Stay right there. Don't leave town. We'll get a translator down here to sort this mess out." Maria: "¡Espera! ¡No te vayas! ¡Es importante! ¡El hombre tenía un cuchillo... o un palo... no lo sé! ¡Por favor!"
created_at"2026-09-24T14:01:07.955Z" 9/24/2026, 2:01:07 PM
model"aion-labs/aion-3.5-mini-20260923"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1951
moderation_latency(null)
generation_time55800
tokens_prompt304
tokens_completion2397
native_tokens_prompt262
native_tokens_completion2404
native_tokens_completion_images(null)
native_tokens_reasoning2082
native_tokens_cached262
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)
usage0.00341276
router(null)
user_agent"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer(null)
request_id"req-1790258467-18RUFNLcQznpvYyKkx1M"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1790258467-L4c4iCSRmzJ8t8I4DDTf"
upstream_id"e6ac5f444bd04a4c94fe7ec9dcd0d4c4"
provider_responses
0
endpoint_id"60ac3bdc-90ec-4769-9193-2c00b4d79562"
id"e6ac5f444bd04a4c94fe7ec9dcd0d4c4"
is_byokfalse
latency1940
model_permaslug"aion-labs/aion-3.5-mini-20260923"
provider_name"AionLabs"
status200
total_cost0.00341276
cache_discount0.00013624
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"¿Perdón? No entiendo... ¿Hablas español?"
detectedLang"es"
heavyLang"es"
scores
es0.8048261178140526
pt0.6638141809290953
ca0.609375
fr0.5491803278688524
it0.5089285714285715
en0.4148936170212766
lv0.3226600985221675
eu0.30203045685279184
ms0.27055702917771884
hr0.26861702127659576
no0.260752688172043
fi0.2486338797814208
sk0.2486338797814208
tr0.24242424242424243
lt0.22969187675070027
tl0.22535211267605632
et0.21875
nl0.21875
pl0.21428571428571427
sq0.207492795389049
reliabletrue
passestrue
1
name"Hunter"
dialogue"Ma'am, I don't have time for charades. Did you see anything near the apple orchard yesterday? Anyone acting strange?"
detectedLang"en"
heavyLang"en"
scores
en0.7857525441885378
tl0.5918367346938775
no0.5257854179016005
nl0.5235259082787374
da0.517781796262809
sv0.46879150066401065
fr0.45092656142759097
de0.4074074074074074
pt0.3563958165728077
ca0.354317998385795
es0.35117599351175993
et0.33388842631140714
hr0.32145886344359625
sq0.31682322801024765
it0.30313588850174217
cs0.29701230228471004
ro0.2945326278659612
ms0.27927927927927926
pl0.25650557620817843
yo0.24953095684803
sk0.2248062015503876
is0.20398009950248755
lv0.14255091103965703
lt0.13978494623655913
tr0.13885898815931108
az0.13232104121475055
sl0.0990990990990991
be0.08045977011494253
hu0.07727797001153403
uk0.07300115874855156
vi0.07300115874855156
reliabletrue
passestrue
2
name"Maria"
dialogue"¿El huerto de manzanas? ¡Dios mío! ¿Estás preguntando por Elena? ¡Ella estaba allí ayer!"
detectedLang"es"
heavyLang"es"
scores
es0.7790868924889544
pt0.6529786003470215
ca0.649737302977233
it0.511400651465798
ro0.4685562444641275
hu0.3839835728952772
tl0.34210526315789475
hr0.30151338766006985
sv0.2966002344665885
no0.29577464788732394
nl0.27710843373493976
ms0.2762364294330519
fr0.2753623188405797
en0.27184466019417475
sq0.24337957124842372
eu0.23371647509578544
sl0.20948616600790515
de0.1847826086956522
az0.18032786885245902
lv0.1758241758241758
da0.16550764951321278
tr0.14040114613180515
lt0.13544668587896252
yo0.13544668587896252
cs0.1044776119402985
sk0.1044776119402985
is0.1031390134529148
reliabletrue
passestrue
3
name"Hunter"
dialogue"You know Elena? Where was she? Ma'am, focus."
detectedLang"en"
heavyLang"en"
scores
en0.7833935018050542
de0.569583931133429
it0.3617021276595745
ro0.3617021276595745
cs0.33035714285714285
nl0.3087557603686636
yo0.2248062015503876
sq0.20634920634920634
tl0.20634920634920634
ca0.1891891891891892
es0.1891891891891892
hr0.1891891891891892
pt0.1891891891891892
sk0.1891891891891892
sl0.1891891891891892
sv0.1891891891891892
reliabletrue
passestrue
4
name"Maria"
dialogue"¡Sí, sí! La vi en el sendero. Estaba tomando fotos de la niebla... yo estaba con mi cámara... ¡pero había un hombre! ¡Un hombre en el borde del bosque!"
detectedLang"es"
heavyLang"es"
scores
es0.797724399494311
ca0.6521739130434783
it0.6082272282076395
fr0.5912110373019929
pt0.5362318840579711
no0.5240928019036288
da0.5124923826934796
tl0.5124923826934796
sv0.5098039215686274
ro0.4715984147952444
yo0.43741209563994377
nl0.3957703927492447
tr0.38414164742109314
eu0.3019197207678883
pl0.3019197207678883
de0.30131004366812225
sl0.29328621908127206
vi0.2825112107623318
hu0.27732610659439927
lv0.27338782924613986
en0.27140255009107467
is0.2202729044834308
sq0.20318725099601595
ms0.17098445595854922
cs0.15700737618545837
sk0.15700737618545837
hr0.15343915343915343
lt0.15164369034994699
az0.13232104121475055
fi0.09502262443438914
et0.07300115874855156
reliabletrue
passestrue
5
name"Hunter"
dialogue"A man? Where? Did you get a name? Do you speak English at all?"
detectedLang"en"
heavyLang"en"
scores
en0.8275862068965517
tl0.6149897330595482
de0.5629370629370629
no0.5624270711785297
da0.5443499392466585
cs0.4777158774373259
sq0.4747899159663866
sv0.4710860366713681
hr0.4477172312223858
pt0.44113263785394935
sk0.4113029827315541
nl0.3980738362760835
pl0.3980738362760835
ro0.36006825938566556
sl0.358974358974359
it0.3444055944055944
yo0.3444055944055944
vi0.32553956834532377
lv0.3218806509945751
lt0.3194192377495462
is0.3181818181818182
hu0.2937853107344633
et0.2870722433460076
ca0.2661448140900196
ms0.2647058823529412
es0.26035502958579887
fr0.2378048780487805
tr0.17035398230088497
az0.15730337078651685
eu0.15730337078651685
fi0.14383561643835618
reliabletrue
passestrue
6
name"Maria"
dialogue"¡No hablo inglés! ¡Escucha! ¡El hombre llevaba una chaqueta verde! ¡Ella corrió hacia el lago y el hombre la siguió! ¡Lo tengo en una foto! ¡Aquí, mira!"
detectedLang"es"
heavyLang"es"
scores
es0.796977216332055
ca0.6930422919508867
it0.5683453237410072
fr0.47856315179606024
pt0.46745562130177515
ro0.45088468578401464
tl0.39839572192513373
no0.3885869565217392
nl0.3612491128459901
tr0.34450109249817923
da0.29797191887675506
hr0.2822966507177033
is0.27710843373493976
sq0.27594529364440873
hu0.25311203319502074
vi0.23273657289002556
sk0.2194275802254987
pl0.2125984251968504
de0.20283436669619131
yo0.20283436669619131
lv0.1773308957952468
en0.1758241758241758
eu0.1712707182320442
sl0.14448669201520914
sv0.1412213740458015
et0.13127413127413126
ms0.10179640718562875
az0.09182643794147326
fi0.08536585365853659
cs0.06152241918665276
reliabletrue
passestrue
7
name"Hunter"
dialogue"I can't read that, lady. It's all Spanish to me. Look, I've got a crime scene to check. Do you have a translator? A friend? Anyone?"
detectedLang"en"
heavyLang"en"
scores
en0.8097955301949595
tl0.64711071901191
sq0.517490952955368
no0.4897959183673469
da0.47780678851174935
pl0.4740302432610125
pt0.46631087391594395
it0.46272666218938885
ro0.46272666218938885
hr0.4616419919246299
cs0.44367176634214184
nl0.43741209563994377
sl0.4310099573257468
sk0.4269340974212034
sv0.40298507462686567
lt0.3745113369820172
de0.3579454253611557
fr0.35064935064935066
et0.34906427990235966
yo0.3447993447993448
es0.3237531699070161
ca0.30374238468233244
vi0.29328621908127206
lv0.28698752228163993
hu0.2687385740402194
ms0.25023430178069356
tr0.2079207920792079
az0.1935483870967742
fi0.14712153518123666
is0.14712153518123666
eu0.14621131270010673
be0.08045977011494253
uk0.07300115874855156
reliabletrue
passestrue
8
name"Maria"
dialogue"¡No entiendes! ¡La foto! ¡Tengo la foto del hombre! ¡Se la puedo mostrar! ¡Espera, no te vayas!"
detectedLang"es"
heavyLang"es"
scores
es0.7998475028593214
ca0.7233930453108536
it0.6536939313984169
pt0.6258018531717747
fr0.5497427101200686
no0.5257452574525745
ro0.49567723342939485
hr0.47968285431119917
tl0.4519832985386221
sl0.4324324324324324
da0.41275167785234906
en0.3986254295532647
sv0.38882421420256114
sq0.37869822485207094
et0.3510506798516687
nl0.34944237918215615
yo0.34863523573200994
lv0.3445692883895131
cs0.34375
sk0.3110236220472441
pl0.308300395256917
eu0.2905405405405405
fi0.26880222841225626
is0.26160337552742613
hu0.23020527859237538
de0.22680412371134018
ms0.16267942583732056
tr0.1435562805872757
vi0.13793103448275862
reliabletrue
passestrue
9
name"Hunter"
dialogue"Stay right there. Don't leave town. We'll get a translator down here to sort this mess out."
detectedLang"en"
heavyLang"en"
scores
en0.8062641265741038
tl0.5352439969016266
da0.43820224719101125
de0.4301994301994302
sq0.3981945837512537
no0.3858751279426817
pl0.3858751279426817
hr0.3697478991596639
fr0.3677555321390938
sl0.35553168635875404
yo0.3548387096774194
sk0.35135135135135137
cs0.3492407809110629
ro0.3333333333333333
ca0.3250843644544432
pt0.318955732122588
lv0.30151338766006985
lt0.2966002344665885
es0.2583436341161928
nl0.25
it0.23857868020304565
et0.23371647509578544
ms0.23371647509578544
sv0.23371647509578544
is0.22580645161290325
vi0.20844327176781002
hu0.20634920634920634
tr0.1891891891891892
eu0.18588873812754408
az0.17695473251028807
fi0.09502262443438914
reliabletrue
passestrue
10
name"Maria"
dialogue"¡Espera! ¡No te vayas! ¡Es importante! ¡El hombre tenía un cuchillo... o un palo... no lo sé! ¡Por favor!"
detectedLang"es"
heavyLang"es"
scores
es0.7912652536929994
ca0.7226962457337884
it0.6625129802699896
pt0.6451965065502184
ro0.5865139949109415
tl0.5479833101529903
fr0.4905956112852664
yo0.45606694560669453
lv0.4347826086956522
sq0.4263018534863195
en0.4080145719489982
no0.36399217221135033
hr0.3374108053007136
pl0.30703624733475476
sl0.2872807017543859
tr0.282560706401766
hu0.2588369441277081
de0.2554410080183276
nl0.2415402567094516
sk0.2415402567094516
lt0.23349056603773585
da0.16879795396419436
sv0.16879795396419436
is0.1591203104786546
cs0.14921465968586387
az0.1390728476821192
eu0.13793103448275862
vi0.12280701754385964
et0.10591471801925723
reliabletrue
passestrue