Run: 2026-02-08-01KGYZC92MRQ5TTANGT5BGJS3J

Run Details

Model:
MoonshotAI: Kimi K2.5
Test:
Language Writing
Scenario:
Character dialogue (Spanish) in a story
Duration:
50.9s
Cost:
$0.006656
Provider:
Moonshot AI

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: "Excuse me, miss. I'm Detective Hunter. I need to ask about that camera—were you taking pictures near the cider mill yesterday afternoon?" Maria: "¿El molino de sidra? Sí, estaba allí. Estaba revisando las fotos ahora mismo. Es horrible... no puedo dejar de verlo." Hunter: "I'm sorry, I don't understand. Do you speak any English at all?" Maria: "No, no hablo inglés. Pero mire—mire esto." Hunter: "Slow down. You're shaking. Did you witness something?" Maria: "¡Sí! Vi a alguien. Una persona... se la llevaron. Estaba en la furgoneta blanca. Tomé la foto justo cuando cerraban las puertas." Hunter: "I can't... Look, just point. Did you see a vehicle? A white van?" Maria: "¡Exacto! Una furgoneta blanca, sin ventanas oscuras. Aquí, en la pantalla. ¿Ve? La sombra allí... esa persona necesita ayuda." Hunter: "Jesus, I need a translator. Is this about the disappearances? The missing person?" Maria: "¡Desaparecidos! Sí, sí. Y el hombre... llevaba una chaqueta roja. Tenga cuidado, por favor. Es muy peligroso." Hunter: "*Hunter.* Yeah. When? ... I'm ten minutes out. Don't touch anything until I get there." Maria: "¿Se va? ¡No, espere! La fotografía..." Hunter: "Miss, I have to take this call. It's an emergency. Stay right here, do you understand? Stay here. I'll send someone who speaks Spanish." Maria: "¡Detective! ¡No puede irse ahora! ¡La evidencia!" Hunter: "I promise I'll be back with an interpreter. Just don't delete those photos." Maria: "¡No la borraré! ¡Pero vuelva pronto... por favor!"
created_at"2026-02-08T15:55:18.714086+00:00" 2/8/2026, 3:55:18 PM
model"moonshotai/kimi-k2.5-0127"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency918
moderation_latency(null)
generation_time50864
tokens_prompt257
tokens_completion2076
native_tokens_prompt273
native_tokens_completion2164
native_tokens_completion_images(null)
native_tokens_reasoning1901
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
usage0.0066558
router(null)
provider_responses
0
id"chatcmpl-6988b1b36990a0bd1bf0b6ce"
status200
is_byokfalse
latency918
endpoint_id"49762299-66fd-4514-b0ee-c9e11e231e3b"
provider_name"Moonshot AI"
model_permaslug"moonshotai/kimi-k2.5-0127"
api_type"completions"
id"gen-1770566067-aGyaxaWzmR5eCC1hHDnC"
upstream_id"chatcmpl-6988b1b36990a0bd1bf0b6ce"
total_cost0.0066558
cache_discount(null)
upstream_inference_cost0
provider_name"Moonshot AI"

Evaluation details

Result Evaluator Details Meta Data
100.00% Parse dialogue n/a
dialogue
0
name"Hunter"
dialogue"Excuse me, miss. I'm Detective Hunter. I need to ask about that camera—were you taking pictures near the cider mill yesterday afternoon?"
detectedLang"en"
heavyLang"en"
scores
en0.7867680958967266
tl0.6314741035856574
no0.5
fr0.47887323943661975
ro0.4574780058651026
nl0.45715962441314556
da0.4441105769230769
sv0.41455696202531644
ca0.41232528589580686
it0.3890356671070013
sq0.386604774535809
de0.3406985032074127
pt0.3359655419956928
et0.33501078360891445
es0.3297101449275362
sl0.30503380916604056
cs0.29443173150266966
pl0.28405572755417957
sk0.27507836990595613
yo0.2635350318471338
hr0.25821972734562953
ms0.24055829228243022
tr0.23490488006617036
lv0.22464375523889354
lt0.15293040293040291
fi0.14351851851851852
is0.12653446647780925
az0.1248817407757805
be0.07035175879396985
hu0.06754032258064516
uk0.06376518218623482
vi0.06376518218623482
reliabletrue
passestrue
1
name"Maria"
dialogue"¿El molino de sidra? Sí, estaba allí. Estaba revisando las fotos ahora mismo. Es horrible... no puedo dejar de verlo."
detectedLang"es"
heavyLang"es"
scores
es0.7880794701986755
ca0.6520226185297956
pt0.5645073489384866
tl0.47575360419397117
it0.46559786239144957
fr0.4117647058823529
en0.39439818319454956
de0.37839937839937837
sl0.3563958165728077
hr0.3532740501212611
nl0.35064935064935066
ro0.33665008291873966
lt0.3327773144286906
lv0.32489451476793246
eu0.3127147766323024
hu0.28825622775800713
no0.24882629107981222
tr0.24242424242424243
sv0.23809523809523808
yo0.23224568138195778
sq0.2023928215353938
da0.18200408997955012
sk0.1649269311064718
ms0.14984059511158343
pl0.14346895074946467
az0.13232104121475055
is0.0990990990990991
fi0.08779931584948689
cs0.07727797001153403
et0.07300115874855156
reliabletrue
passestrue
2
name"Hunter"
dialogue"I'm sorry, I don't understand. Do you speak any English at all?"
detectedLang"en"
heavyLang"en"
scores
en0.8085106382978724
no0.6280991735537189
da0.604221635883905
tl0.6
sv0.5227995758218452
cs0.47058823529411764
pl0.4353826850690088
de0.42820838627700125
hr0.4238156209987196
sq0.4178525226390685
sk0.3943472409152086
it0.3894165535956581
ca0.37586685159500693
pt0.3626062322946175
ro0.3440233236151603
nl0.2834394904458599
vi0.27884615384615385
yo0.2682926829268293
et0.25124792013311154
is0.23339011925042585
sl0.21052631578947367
ms0.13793103448275862
be0.1346153846153846
tr0.1346153846153846
hu0.12959381044487428
az0.12280701754385964
lt0.12280701754385964
lv0.12280701754385964
uk0.12280701754385964
reliabletrue
passestrue
3
name"Maria"
dialogue"No, no hablo inglés. Pero mire—mire esto."
detectedLang"es"
heavyLang"es"
scores
es0.8003992015968064
tl0.5475113122171946
pt0.5180722891566265
ca0.5157384987893463
tr0.453551912568306
it0.43977591036414565
lv0.3957703927492447
sq0.3442622950819672
en0.34210526315789475
hu0.33993399339933994
hr0.33554817275747506
no0.3265993265993266
sk0.3127147766323024
fr0.3055555555555556
et0.2779783393501805
pl0.2727272727272727
reliabletrue
passestrue
4
name"Hunter"
dialogue"Slow down. You're shaking. Did you witness something?"
detectedLang"en"
heavyLang"en"
scores
en0.7985120892746436
tl0.5896464646464646
de0.3229166666666667
cs0.3200836820083682
pt0.3143459915611814
nl0.2388758782201405
no0.20924574209245742
es0.1935483870967742
ms0.1935483870967742
da0.1875
lv0.1875
fr0.1792929292929293
is0.1792929292929293
sv0.1792929292929293
reliabletrue
passestrue
5
name"Maria"
dialogue"¡Sí! Vi a alguien. Una persona... se la llevaron. Estaba en la furgoneta blanca. Tomé la foto justo cuando cerraban las puertas."
detectedLang"es"
heavyLang"es"
scores
es0.7908464566929134
ca0.6625645097260817
it0.5913461538461539
pt0.5638789122626988
tl0.5500264690312334
no0.4901019796040792
ro0.48702474351237174
sv0.48265368228849664
fr0.4785276073619632
da0.47335811648079307
lv0.4310575635876841
sq0.39801699716713884
cs0.3906810035842294
sl0.38226744186046513
hr0.37361827560795874
nl0.3670886075949367
yo0.3541033434650456
tr0.3328100470957614
eu0.33070866141732286
sk0.33070866141732286
ms0.30384930384930386
en0.29983525535420097
et0.2916666666666667
is0.2875104777870914
fi0.276595744680851
de0.23835125448028674
lt0.23007246376811596
vi0.23007246376811596
pl0.2107706592386258
hu0.2048643592142189
az0.1317671092951992
reliabletrue
passestrue
6
name"Hunter"
dialogue"I can't... Look, just point. Did you see a vehicle? A white van?"
detectedLang"en"
heavyLang"en"
scores
en0.8102466793168881
ca0.6268656716417911
tl0.5073891625615764
fr0.5055624227441285
et0.49874686716791977
da0.47643979057591623
hu0.464524765729585
pl0.4467496542185339
cs0.4405594405594406
ro0.43422913719943423
sv0.4310099573257468
hr0.38556067588325654
nl0.38271604938271603
it0.375
es0.35379644588045234
no0.34959349593495936
sq0.33993399339933994
yo0.33993399339933994
sk0.33554817275747506
tr0.2687385740402194
lt0.26605504587155965
pt0.25925925925925924
is0.25650557620817843
az0.24953095684803
lv0.24953095684803
vi0.24953095684803
sl0.1836734693877551
be0.14893617021276595
eu0.14893617021276595
de0.14346895074946467
fi0.13606911447084233
ms0.13606911447084233
uk0.13606911447084233
reliabletrue
passestrue
7
name"Maria"
dialogue"¡Exacto! Una furgoneta blanca, sin ventanas oscuras. Aquí, en la pantalla. ¿Ve? La sombra allí... esa persona necesita ayuda."
detectedLang"es"
heavyLang"es"
scores
es0.7743562516591452
ca0.6799698795180722
it0.5602690118986032
ro0.4961470065204505
pt0.4723774053382992
fr0.4537275064267352
no0.4448073154800784
sv0.42837928715534634
lv0.42528735632183906
tl0.3911174785100286
da0.38494934876989867
tr0.33123524783634933
hr0.32486100079428115
en0.31006493506493504
sq0.3044189852700491
nl0.30384930384930386
ms0.302707136997539
is0.2975206611570248
sl0.27101200686106347
fi0.25241864555848725
cs0.23971377459749554
eu0.23076923076923078
sk0.21875
yo0.17315175097276264
lt0.16338582677165356
az0.1474423269809428
de0.1474423269809428
et0.14228052472250252
vi0.08993576017130622
hu0.06900328587075576
pl0.06490649064906491
reliabletrue
passestrue
8
name"Hunter"
dialogue"Jesus, I need a translator. Is this about the disappearances? The missing person?"
detectedLang"en"
heavyLang"en"
scores
en0.8059964726631392
tl0.6381578947368421
pt0.5928941524796447
nl0.5922905856189771
fr0.5749613601236476
da0.56
no0.5510204081632653
ca0.5462046204620462
sv0.5462046204620462
et0.5162708883025505
sq0.5128432240921169
ms0.5031616982836495
it0.49679780420860015
is0.48405253283302063
ro0.462890625
hu0.4444444444444444
hr0.4410569105691057
yo0.4404883011190234
pl0.4370522006141249
de0.4324045407636739
es0.4123931623931624
cs0.39226519337016574
lv0.38820912124582874
sk0.3707093821510297
az0.3648960739030023
lt0.3405275779376499
tr0.3349455864570738
vi0.28664072632944226
sl0.2763157894736842
fi0.2040520984081042
eu0.19941775836972345
be0.11290322580645161
uk0.10277324632952692
reliabletrue
passestrue
9
name"Maria"
dialogue"¡Desaparecidos! Sí, sí. Y el hombre... llevaba una chaqueta roja. Tenga cuidado, por favor. Es muy peligroso."
detectedLang"es"
heavyLang"es"
scores
es0.7988505747126436
ca0.6342737722048066
pt0.5825879546809779
it0.41225860621326615
fr0.37275985663082434
hu0.3027888446215139
tl0.2907801418439716
ro0.2893401015228426
ms0.2677824267782427
sq0.21787709497206703
lt0.20364050056882824
en0.17550058892815076
yo0.17452830188679244
de0.16963226571767495
no0.16963226571767495
lv0.14634146341463414
is0.13580246913580246
pl0.13043478260869565
fi0.12280701754385964
vi0.12280701754385964
eu0.11616161616161616
sk0.10941475826972011
tr0.0990990990990991
da0.08496732026143791
nl0.08496732026143791
sl0.08496732026143791
sv0.08496732026143791
reliabletrue
passestrue
10
name"Hunter"
dialogue"Hunter. Yeah. When? ... I'm ten minutes out. Don't touch anything until I get there."
detectedLang"en"
heavyLang"en"
scores
en0.8098859315589354
sq0.4410569105691057
ca0.4335736354273944
de0.4264859228362878
tl0.4204425711275026
no0.39956331877729256
fr0.39091915836101887
pl0.3514150943396226
da0.3436754176610978
cs0.3365500603136309
sv0.3357487922705314
sk0.30904522613065327
it0.3081761006289308
lt0.28664072632944226
ro0.28478543563068925
nl0.28292046936114734
et0.2724867724867725
hr0.2724867724867725
pt0.26861702127659576
ms0.26273458445040215
is0.2286115007012623
es0.20634920634920634
sl0.19236417033773862
tr0.18998527245949925
yo0.13657770800627944
fi0.11575562700964631
be0.11290322580645161
hu0.1085899513776337
az0.10277324632952692
lv0.10277324632952692
uk0.10277324632952692
vi0.10277324632952692
reliabletrue
passestrue
11
name"Maria"
dialogue"¿Se va? ¡No, espere! La fotografía..."
detectedLang"es"
heavyLang"es"
scores
es0.7977346278317152
ca0.7591522157996147
it0.7443762781186094
ro0.7113163972286375
pt0.6630727762803235
no0.6428571428571429
fr0.6366279069767442
hr0.5974235104669887
sq0.5652173913043478
yo0.5344506517690875
cs0.5192307692307693
sl0.5183044315992292
lv0.5029821073558649
en0.494949494949495
tl0.48559670781893005
sk0.4692144373673036
tr0.4646680942184154
da0.45652173913043476
sv0.44933920704845814
pl0.44071588366890374
de0.33510638297872336
lt0.33510638297872336
et0.32795698924731176
nl0.32795698924731176
eu0.2937853107344633
fi0.28977272727272724
vi0.251497005988024
az0.19093851132686085
ms0.19093851132686085
reliabletrue
passestrue
12
name"Hunter"
dialogue"Miss, I have to take this call. It's an emergency. Stay right here, do you understand? Stay here. I'll send someone who speaks Spanish."
detectedLang"en"
heavyLang"en"
scores
en0.8184458968772695
tl0.5689655172413793
da0.5484647802528597
no0.4845360824742268
pl0.43095599393019723
cs0.414519906323185
de0.3907392363931763
yo0.38524590163934425
sq0.36494496189669773
sv0.36386768447837153
sk0.3617021276595745
hr0.3333333333333333
ro0.31255728689275897
nl0.30747922437673125
sl0.2984097287184284
pt0.29245283018867924
vi0.27395934172313646
it0.2690058479532163
es0.23391215526046988
fr0.23391215526046988
et0.21218487394957983
lv0.19786096256684493
lt0.18211559432933477
tr0.15824915824915825
ca0.15540540540540537
hu0.15540540540540537
is0.1544532130777903
eu0.12177985948477751
ms0.09638554216867469
be0.08536585365853659
az0.07749077490774908
uk0.07749077490774908
reliabletrue
passestrue
13
name"Maria"
dialogue"¡Detective! ¡No puede irse ahora! ¡La evidencia!"
detectedLang"es"
heavyLang"es"
scores
es0.8051558752997601
ca0.7074707470747075
pt0.6723790322580645
it0.6475054229934923
en0.639289678135405
ro0.5977722772277227
fr0.5723684210526315
tl0.5467224546722455
no0.44539249146757676
lv0.3890977443609023
sq0.344758064516129
hr0.34077079107505076
sk0.3340163934426229
cs0.30703624733475476
yo0.22062350119904073
tr0.21307506053268765
hu0.20924574209245742
da0.20537897310513448
de0.20537897310513448
vi0.20537897310513448
nl0.20147420147420148
pl0.1875
sl0.1709183673469388
sv0.1709183673469388
reliabletrue
passestrue
14
name"Hunter"
dialogue"I promise I'll be back with an interpreter. Just don't delete those photos."
detectedLang"en"
heavyLang"en"
scores
en0.7899159663865546
ca0.5606694560669456
fr0.5580808080808082
ro0.5512820512820513
de0.5257452574525745
sq0.5222929936305732
es0.49856733524355296
et0.4902912621359223
no0.4770916334661355
sv0.4770916334661355
tl0.4723618090452261
pt0.4691607684529828
tr0.4473684210526315
hu0.44678609062170704
it0.44208289054197664
da0.41471571906354515
nl0.4101123595505618
ms0.40340909090909094
cs0.38739789964994165
lt0.38739789964994165
hr0.36746987951807225
yo0.3566176470588235
sl0.3526510480887793
pl0.34045226130653267
vi0.30921052631578944
lv0.2953020134228188
sk0.2895805142083897
eu0.26160337552742613
az0.1984732824427481
hi0.12790697674418602
be0.11764705882352942
is0.10714285714285714
uk0.10714285714285714
reliabletrue
passestrue
15
name"Maria"
dialogue"¡No la borraré! ¡Pero vuelva pronto... por favor!"
detectedLang"es"
heavyLang"es"
scores
es0.8066627007733491
ca0.6778989098116948
pt0.6475054229934923
it0.6055825242718447
fr0.5535714285714286
sq0.5206489675516224
tl0.500768049155146
no0.4992295839753467
ro0.41546762589928055
hr0.365234375
en0.3512974051896207
sk0.3394308943089431
cs0.3143459915611814
lv0.2872807017543859
eu0.2777777777777778
yo0.22062350119904073
tr0.21307506053268765
vi0.20537897310513448
de0.18952618453865336
pl0.1875
et0.1792929292929293
da0.16666666666666666
nl0.16666666666666666
sl0.16666666666666666
sv0.16666666666666666
reliabletrue
passestrue