Run: 2026-09-03-01M1KY9TRP5E2XA3244Y4JXSKY

Run Details

Model:
Qwen 3.8 27B (Reasoning, XHigh)
Test:
Language Writing
Scenario:
Character dialogue (Spanish) in a story
Duration:
2m 46s
Cost:
$0.025391
Provider:
Reka

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
Hunter: "Ma'am, Detective Hunter. I see you have a camera. Did you take photos at the apple festival last night?" Maria: "Perdón... no entiendo. Estoy... tengo miedo." Hunter: "I'm sorry, I don't speak Spanish. I'm using a translator app. Did you see anything at the festival?" Maria: "Ah... ¿un traductor? Sí... estuve allí. Vi algo cerca del granero." Hunter: "What did you see near the barn?" Maria: "Una mujer. Miraba a los árboles. Parecía asustada." Hunter: "A woman? Was she alone?" Maria: "No. Había un hombre. Le hablaba de cerca. Parecía una discusión." Hunter: "What did the man look like?" Maria: "Alto, chaqueta oscura. No quiso mirarme. Tomé una foto, pero mi mano temblaba." Hunter: "Do you have the photo?" Maria: "Sí... pero la cara está borrosa." Hunter: "Keep the camera with you. Don't send the photo to anyone." Maria: "¿Por qué?" Hunter: "Because people are missing, ma'am." Maria: "¿Está muerto alguien?" Hunter: "No one is dead. But people are disappearing. Ma'am, I'm sorry—my phone is ringing. I have to go. I'll be back." Maria: "Perdón... ¿volverá?" Hunter: "I will. Stay away from the festival grounds." Maria: "¿La fiesta de las manzanas?" Hunter: "The festival grounds." Maria: "No iré." Hunter: "Good."
created_at"2026-09-03T15:30:50.782Z" 9/3/2026, 3:30:50 PM
model"qwen/qwen3.8-27b-20260814"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency201
moderation_latency(null)
generation_time165728
tokens_prompt304
tokens_completion9685
native_tokens_prompt333
native_tokens_completion9926
native_tokens_completion_images(null)
native_tokens_reasoning9352
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)
usage0.02539122
router(null)
user_agent"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer(null)
request_id"req-1788449450-cCLiNLMSus0Eznyuwu7F"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1788449450-TiyupguVvms328SpIKlE"
upstream_id"chatcmpl-fbbf96ef-f5f5-493c-9794-52c8f66d478a"
provider_responses
0
endpoint_id"15086968-df2f-4d69-86bb-c74c31644bb6"
id"chatcmpl-fbbf96ef-f5f5-493c-9794-52c8f66d478a"
is_byokfalse
latency199
model_permaslug"qwen/qwen3.8-27b-20260814"
provider_name"Reka"
status200
total_cost0.02539122
cache_discount(null)
upstream_inference_cost0
provider_name"Reka"
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"Hunter"
dialogue"Ma'am, Detective Hunter. I see you have a camera. Did you take photos at the apple festival last night?"
detectedLang"en"
heavyLang"en"
scores
en0.787556904400607
tl0.6800731261425961
fr0.6191512513601742
da0.5972382048331415
it0.56656346749226
ca0.5603015075376884
no0.5578016424510424
es0.5406824146981627
ro0.5382585751978892
nl0.5276653171390013
sv0.49640287769784175
de0.49201741654571846
pt0.48301329394387
cs0.45054945054945056
sq0.4470774091627172
hr0.4257588187038556
et0.4142259414225941
sl0.40728196443691783
ms0.3918331885317115
yo0.3560257589696412
lt0.33396764985727884
sk0.3137254901960784
pl0.29577464788732394
hu0.29292929292929293
lv0.27611168562564636
az0.2639327024185068
tr0.2273730684326711
is0.16467780429594273
vi0.15966386554621848
fi0.15254237288135594
hi0.0990990990990991
be0.09090909090909091
eu0.09090909090909091
uk0.08256880733944955
reliabletrue
passestrue
1
name"Maria"
dialogue"Perdón... no entiendo. Estoy... tengo miedo."
detectedLang"es"
heavyLang"es"
scores
es0.8065764023210832
pt0.6368038740920097
ca0.563953488372093
it0.5475113122171946
fr0.44751381215469616
ms0.40476190476190477
en0.3939393939393939
et0.33920704845814975
lv0.30394431554524365
eu0.27007299270072993
is0.2682926829268293
hr0.2518703241895262
no0.24433249370277077
fi0.23273657289002556
sk0.23273657289002556
tr0.22680412371134018
lt0.21465968586387435
tl0.21052631578947367
hu0.20424403183023873
nl0.20424403183023873
pl0.2
sq0.1935483870967742
reliabletrue
passestrue
2
name"Hunter"
dialogue"I'm sorry, I don't speak Spanish. I'm using a translator app. Did you see anything at the festival?"
detectedLang"en"
heavyLang"en"
scores
en0.8021481062747315
tl0.6321597477666842
no0.5726495726495726
da0.5679012345679012
sq0.5142262317834837
nl0.4787788533134773
ms0.4728915662650602
it0.46195234435049964
sv0.4602929838087896
ro0.45652173913043476
pt0.453978159126365
hr0.4514106583072101
cs0.44488501189532115
ca0.4422310756972112
et0.4345718901453958
de0.39759036144578314
fr0.3934142114384749
pl0.381078691423519
sl0.36189608021877845
es0.358974358974359
sk0.3536472760849492
hu0.34024505183788883
lt0.325626204238921
yo0.3089832181638697
az0.3069306930693069
lv0.2731048805815161
vi0.23995656894679696
is0.2324561403508772
tr0.23076923076923078
eu0.16367980884109917
fi0.15254237288135594
be0.09090909090909091
uk0.08256880733944955
reliabletrue
passestrue
3
name"Maria"
dialogue"Ah... ¿un traductor? Sí... estuve allí. Vi algo cerca del granero."
detectedLang"es"
heavyLang"es"
scores
es0.7760800842992623
ca0.7170439414114514
it0.6555915721231765
pt0.6013133208255159
ro0.586977648202138
fr0.5251396648044693
tl0.5137299771167049
da0.5040840140023337
yo0.4798041615667074
sv0.4627054361567636
no0.4537275064267352
en0.442257217847769
nl0.39801699716713884
lv0.3511450381679389
sl0.3369734789391576
hr0.23971377459749554
pl0.2328519855595668
sq0.22867513611615245
cs0.22303473491773307
lt0.22303473491773307
sk0.22303473491773307
de0.21731123388581952
vi0.1904761904761905
ms0.1290983606557377
et0.121900826446281
reliabletrue
passestrue
4
name"Hunter"
dialogue"What did you see near the barn?"
detectedLang"en"
heavyLang"en"
scores
en0.8304263565891472
no0.5179063360881543
tl0.5098039215686274
sv0.5070422535211268
et0.49275362318840576
da0.4852941176470589
yo0.3794326241134752
nl0.32432432432432434
cs0.308300395256917
fr0.308300395256917
ms0.308300395256917
sq0.308300395256917
is0.3055555555555556
reliabletrue
passestrue
5
name"Maria"
dialogue"Una mujer. Miraba a los árboles. Parecía asustada."
detectedLang"es"
heavyLang"es"
scores
es0.7994987468671679
ca0.6971990915972748
pt0.5495495495495496
it0.51278928136419
et0.4838709677419355
ro0.42938659058487877
en0.41348973607038125
fr0.4074074074074074
tl0.38176197836166925
lv0.3730407523510972
de0.3548387096774194
yo0.35064935064935066
sv0.33665008291873966
lt0.3103448275862069
ms0.3103448275862069
hu0.2805755395683453
tr0.2766726943942134
sq0.27007299270072993
fi0.26605504587155965
no0.26605504587155965
cs0.24812030075187969
sk0.24528301886792453
hr0.21875
pl0.2079207920792079
sl0.1836734693877551
is0.15789473684210525
da0.15254237288135594
az0.14893617021276595
eu0.14893617021276595
nl0.14893617021276595
vi0.14893617021276595
reliabletrue
passestrue
6
name"Hunter"
dialogue"A woman? Was she alone?"
detectedLang"en"
heavyLang"en"
scores
en0.8262164846077458
nl0.6111111111111112
ro0.5558375634517766
it0.5478036175710594
yo0.5406824146981627
cs0.5370370370370371
fr0.5257452574525745
de0.515235457063712
hr0.5111731843575419
pl0.5098039215686274
hu0.4712990936555891
fi0.4496855345911949
sq0.4496855345911949
tl0.4496855345911949
no0.44620253164556967
pt0.4444444444444444
ca0.4372990353697749
es0.4299674267100977
sk0.42622950819672134
sl0.33962264150943394
lt0.31906614785992216
tr0.3055555555555556
is0.3
da0.29149797570850206
az0.2857142857142857
eu0.2857142857142857
lv0.2857142857142857
vi0.2857142857142857
et0.2647058823529412
ms0.2647058823529412
sv0.2647058823529412
reliabletrue
passestrue
7
name"Maria"
dialogue"No. Había un hombre. Le hablaba de cerca. Parecía una discusión."
detectedLang"es"
heavyLang"es"
scores
es0.8332162921348315
ca0.7159090909090909
it0.689745264532985
ro0.6365723029839327
fr0.610655737704918
pt0.6061359867330016
tl0.5082815734989649
lv0.4508670520231214
en0.4135802469135802
yo0.40401505646173147
sk0.35374149659863946
nl0.326241134751773
no0.302496328928047
hu0.291044776119403
sl0.2813918305597579
tr0.2813918305597579
sv0.27370030581039756
da0.20033670033670034
hr0.1753472222222222
lt0.17102966841186737
et0.1592920353982301
fi0.14721723518850988
pl0.13636363636363635
eu0.12844036697247707
de0.12361623616236161
az0.1171003717472119
ms0.1171003717472119
sq0.1171003717472119
reliabletrue
passestrue
8
name"Hunter"
dialogue"What did the man look like?"
detectedLang"en"
heavyLang"en"
scores
en0.8461538461538461
no0.6767241379310345
da0.5798319327731093
sv0.5774647887323944
tl0.5726495726495726
nl0.5508982035928144
de0.4360902255639098
lv0.4186046511627907
yo0.4163424124513619
lt0.38524590163934425
fr0.34210526315789475
ms0.34210526315789475
sq0.34210526315789475
reliabletrue
passestrue
9
name"Maria"
dialogue"Alto, chaqueta oscura. No quiso mirarme. Tomé una foto, pero mi mano temblaba."
detectedLang"es"
heavyLang"es"
scores
es0.6989678899082569
it0.6049661399548533
ca0.5745542949756888
pt0.47500000000000003
tl0.39236111111111116
sk0.38307873090481787
fr0.3371212121212121
ro0.3181818181818182
hr0.3119266055045872
cs0.3037135278514589
pl0.29149797570850206
lv0.2698191933240611
yo0.2605633802816902
no0.25426136363636365
sl0.2435158501440922
tr0.2335766423357664
da0.21875
lt0.16798732171156894
ms0.16666666666666666
en0.16534181240063595
hu0.13934426229508196
sq0.1264559068219634
de0.10714285714285714
nl0.10714285714285714
et0.10102739726027396
reliabletrue
passestrue
10
name"Hunter"
dialogue"Do you have the photo?"
detectedLang"en"
heavyLang"en"
scores
en0.8360655737704918
cs0.665924276169265
fr0.6411483253588517
tl0.6332518337408314
da0.6
sq0.5652173913043478
yo0.5522388059701493
pt0.5098039215686274
pl0.48805460750853247
sk0.46808510638297873
hr0.4444444444444444
sl0.4444444444444444
vi0.42528735632183906
no0.3877551020408163
nl0.358974358974359
ms0.34210526315789475
sv0.34210526315789475
hi0.33920704845814975
reliabletrue
passestrue
11
name"Maria"
dialogue"Sí... pero la cara está borrosa."
detectedLang"es"
heavyLang"es"
scores
es0.8237885462555066
ca0.7028231797919762
pt0.6721311475409836
tl0.5515695067264574
yo0.5454545454545454
it0.5412844036697247
fr0.453551912568306
ro0.4428969359331476
eu0.38461538461538464
ms0.3174061433447099
cs0.30313588850174217
no0.29577464788732394
vi0.29577464788732394
sq0.2805755395683453
sk0.2779783393501805
reliabletrue
passestrue
12
name"Hunter"
dialogue"Keep the camera with you. Don't send the photo to anyone."
detectedLang"en"
heavyLang"en"
scores
en0.8157894736842104
tl0.6380558428128231
fr0.49567723342939485
cs0.4590417310664606
yo0.41077441077441074
ms0.3944636678200692
no0.36823104693140796
da0.34210526315789475
nl0.3137254901960784
sv0.3137254901960784
it0.3110236220472441
ro0.3110236220472441
pl0.27835051546391754
sk0.2738589211618257
lv0.2584745762711864
sl0.25690021231422505
hr0.24892703862660948
lt0.2290748898678414
ca0.22566371681415928
es0.22048997772828507
sq0.1822429906542056
hi0.18032786885245902
de0.17061611374407584
reliabletrue
passestrue
13
name"Maria"
dialogue"¿Por qué?"
detectedLang"es"
heavyLang"es"
scores
es0.8567335243553008
pt0.7448979591836735
sq0.7222222222222222
reliablefalse
passestrue
14
name"Hunter"
dialogue"Because people are missing, ma'am."
detectedLang"en"
heavyLang"en"
scores
en0.8048568950563747
ro0.5243128964059197
tl0.471830985915493
nl0.43890274314214467
no0.4155844155844156
de0.4140625
fr0.4140625
is0.40318302387267907
da0.3818681318681319
ms0.3283582089552239
sv0.29906542056074764
fi0.25742574257425743
ca0.24242424242424243
az0.22413793103448276
et0.22413793103448276
it0.22413793103448276
pt0.22413793103448276
reliabletrue
passestrue
15
name"Maria"
dialogue"¿Está muerto alguien?"
detectedLang"es"
heavyLang"es"
scores
es0.8316498316498316
pt0.7584541062801933
ca0.6688741721854304
it0.42084942084942084
et0.40476190476190477
cs0.3670886075949367
sk0.33920704845814975
tl0.336283185840708
reliabletrue
passestrue
16
name"Hunter"
dialogue"No one is dead. But people are disappearing. Ma'am, I'm sorry—my phone is ringing. I have to go. I'll be back."
detectedLang"en"
heavyLang"en"
scores
en0.7901591895803184
tl0.6182201158504477
da0.4802867383512545
no0.4657332350773766
pl0.462166172106825
nl0.4414483821263482
yo0.42277070063694266
it0.3866328257191201
hr0.37928082191780826
sk0.3444846292947558
ms0.3255813953488372
hu0.3179680150517403
sv0.3166823751178134
cs0.30754536771728747
lv0.30355427473583096
lt0.2778884462151395
ca0.27354709418837675
fr0.25564681724846
pt0.24714434060228452
ro0.24714434060228452
vi0.21281216069489683
tr0.17893544733861835
de0.17800453514739228
is0.17613636363636365
et0.1751990898748578
es0.15893271461716937
sq0.1559953434225844
sl0.1430260047281324
be0.0880503144654088
az0.0799492385786802
uk0.0799492385786802
reliabletrue
passestrue
17
name"Maria"
dialogue"Perdón... ¿volverá?"
detectedLang"es"
heavyLang"es"
scores
es0.808282208588957
pt0.6366279069767442
cs0.4813278008298755
is0.47257383966244726
ms0.44933920704845814
sv0.4444444444444444
ca0.423963133640553
it0.4131455399061033
sk0.410377358490566
fr0.3961352657004831
lt0.3961352657004831
sq0.3654822335025381
reliabletrue
passestrue
18
name"Hunter"
dialogue"I will. Stay away from the festival grounds."
detectedLang"en"
heavyLang"en"
scores
en0.8136856368563685
tl0.7470101195952161
no0.6082621082621082
sv0.5997088791848617
da0.5949926362297496
fr0.5709828393135725
ca0.555735056542811
sq0.5542949756888168
hr0.5528455284552846
it0.532312925170068
cs0.5149911816578483
nl0.494485294117647
ms0.48308270676691734
ro0.43064182194616984
pt0.4222689075630252
yo0.4136460554371002
sk0.40860215053763443
lt0.4073275862068965
pl0.4073275862068965
sl0.40476190476190477
et0.40217391304347827
es0.39956331877729256
az0.39692982456140347
de0.3902439024390244
hu0.3276283618581907
lv0.314214463840399
be0.20289855072463767
tr0.20289855072463767
fi0.1863905325443787
is0.1863905325443787
uk0.1863905325443787
vi0.1863905325443787
reliabletrue
passestrue
19
name"Maria"
dialogue"¿La fiesta de las manzanas?"
detectedLang"es"
heavyLang"es"
scores
es0.7929606625258799
ca0.71671388101983
ro0.6610169491525424
tl0.6503496503496503
it0.6190476190476191
pt0.6161228406909789
fr0.6124031007751938
no0.5594713656387665
ms0.5157384987893463
lv0.49874686716791977
yo0.48186528497409326
sv0.4805194805194805
hr0.4791666666666667
nl0.43342776203966005
sq0.41348973607038125
da0.3730407523510972
fi0.33993399339933994
tr0.3288590604026846
hu0.3265993265993266
lt0.3197278911564626
vi0.29577464788732394
is0.2727272727272727
sk0.2727272727272727
sl0.2727272727272727
eu0.25925925925925924
de0.250936329588015
az0.23954372623574144
en0.23954372623574144
reliabletrue
passestrue
20
name"Hunter"
dialogue"The festival grounds."
detectedLang"en"
heavyLang"en"
scores
en0.7928176795580111
tl0.7536945812807881
fr0.7093023255813954
no0.6527777777777778
sv0.6462264150943396
nl0.6420047732696896
da0.6385542168674699
ms0.6314496314496314
sq0.5810055865921787
ca0.5786516853932584
hr0.5726495726495726
pt0.5726495726495726
it0.5689655172413793
cs0.5548961424332344
sl0.5548961424332344
es0.5495495495495496
lt0.45652173913043476
et0.4485294117647059
az0.44029850746268656
ro0.44029850746268656
sk0.44029850746268656
yo0.4163424124513619
de0.3181818181818182
hu0.3087557603686636
fi0.29577464788732394
lv0.29577464788732394
pl0.29577464788732394
reliabletrue
passestrue
21
name"Maria"
dialogue"No iré."
detectedLang"pt"
heavyLang"es"
scores
pt0.7340425531914894
es0.732620320855615
ca0.7297297297297297
lv0.7237569060773481
en0.6753246753246753
hr0.6688741721854304
no0.6598639455782312
sk0.6453900709219859
tr0.6376811594202898
it0.6153846153846154
tl0.6153846153846154
pl0.6
reliablefalse
passestrue
22
name"Hunter"
dialogue"Good."
detectedLang"en"
heavyLang"en"
scores
en0.8417721518987342
tl0.8
reliablefalse
passestrue