Run: 2026-02-08-01KGYZ4Q3SG5QENQCAK6F6J3BT

Run Details

Model:
MoonshotAI: Kimi K2.5
Test:
Language Writing
Scenario:
Character dialogue (French) in a story
Duration:
53.4s
Cost:
$0.007564
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="Marie"> Marie is a 30-year old college student on a study abroad program. Born in France, she is fluent in French 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 French, 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: Marie 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 French, and Hunter looks confused. They talk for a while, until Hunter gets a call and has to leave. Return the dialogue between Marie and Hunter as a voice sheet: Marie: "..." Hunter: "..."

Model response

AI
Hunter: "Excuse me, miss. I'm Detective Hunter. I need to ask you some questions about the incident near the apple orchard last night." Marie: "Détective? Oh mon Dieu... vous devez m'aider. J'étais près du verger hier soir pour photographier le coucher de soleil, et j'ai vu quelque chose d'effroyable!" Hunter: "I'm sorry, I don't speak French. Do you understand English at all? Any English?" Marie: "Non, je ne comprends rien! Pourquoi ne me comprenez-vous pas? C'est urgent! Il y avait un homme dans les pommiers, et quelqu'un l'a attaqué. Je l'ai vu disparaître!" Hunter: "You seem distressed. Is this about the missing person? Did you witness the disappearance?" Marie: "Oui! La disparition! J'ai tout photographié avec mon appareil. Regardez ces images... l'homme en noir qui l'entraînait vers les arbres. C'est la preuve!" Hunter: "Your camera? Did you capture something on camera? Show me the photographs." Marie: "Oui, les photos! Attendez, je vais vous montrer... celle-ci, et celle-là. Vous voyez? L'ombre derrière lui. C'est l'assassin, n'est-ce pas?" Hunter: "I can't understand a word you're saying, but you obviously saw something. Can you just—" Hunter: "Hunter. ... Yeah. ... What do you mean, another one? ... Same location? ... I'm on my way." Marie: "Non, ne raccrochez pas! Vous devez voir ces images maintenant! C'est connecté à tout ça, je le sais!" Hunter: "Look, I have to go. There's been another incident. Stay here—I'll send someone who speaks French to take your statement." Marie: "Attendez! Vous ne pouvez pas partir! Ces photos sont importantes... quelqu'un veut les détruire, je le sens! Revenez!" Hunter: "Just... don't leave. I'll be back with a translator."
created_at"2026-02-08T15:51:13.233739+00:00" 2/8/2026, 3:51:13 PM
model"moonshotai/kimi-k2.5-0127"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency959
moderation_latency(null)
generation_time52905
tokens_prompt257
tokens_completion2223
native_tokens_prompt277
native_tokens_completion2466
native_tokens_completion_images(null)
native_tokens_reasoning2139
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"
usage0.0075642
router(null)
provider_responses
0
id"chatcmpl-6988b0bb8bd4efc09c145dfc"
status200
is_byokfalse
latency959
endpoint_id"49762299-66fd-4514-b0ee-c9e11e231e3b"
provider_name"Moonshot AI"
model_permaslug"moonshotai/kimi-k2.5-0127"
api_type"completions"
id"gen-1770565819-WNWieCSWMHoWQEMSoC0z"
upstream_id"chatcmpl-6988b0bb8bd4efc09c145dfc"
total_cost0.0075642
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 you some questions about the incident near the apple orchard last night."
detectedLang"en"
heavyLang"en"
scores
en0.7982885085574573
tl0.6246587807097361
fr0.6141253507951357
it0.5183887915936953
no0.5141342756183745
nl0.472168905950096
ca0.4708146247594612
da0.45291777188328913
es0.439918533604888
sq0.43298969072164945
pt0.43064182194616984
ro0.43064182194616984
de0.41901408450704225
cs0.38294689603590126
et0.37876506024096385
sv0.3726235741444867
sl0.3599689681923972
yo0.32926829268292684
hr0.3159203980099502
sk0.28756476683937826
pl0.28633217993079585
lt0.21503330161750714
ms0.2112810707456979
az0.20135527589545013
lv0.1831683168316832
tr0.13522012578616352
hu0.13249211356466878
fi0.08333333333333334
be0.0782122905027933
is0.07094594594594594
uk0.07094594594594594
vi0.07094594594594594
reliabletrue
passestrue
1
name"Marie"
dialogue"Détective? Oh mon Dieu... vous devez m'aider. J'étais près du verger hier soir pour photographier le coucher de soleil, et j'ai vu quelque chose d'effroyable!"
detectedLang"fr"
heavyLang"fr"
scores
fr0.7951600609756098
en0.5402053036783576
de0.44300518134715033
da0.42390139335476956
nl0.4001116071428571
no0.38111686816350027
ca0.37024018746338605
ro0.35318892900120336
it0.3488794669897032
tl0.33559950556242274
sv0.33229813664596275
es0.2606602475928473
pt0.24295774647887322
sl0.19895678092399405
tr0.1905120481927711
lt0.168600154679041
yo0.1673121611154144
eu0.1647241647241647
az0.16212003117692905
hu0.15354330708661418
et0.12743506493506493
sq0.12672623883021933
hi0.12601626016260162
hr0.12244897959183673
lv0.08666100254885302
vi0.08432708688245316
ms0.05536028119507908
reliabletrue
passestrue
2
name"Hunter"
dialogue"I'm sorry, I don't speak French. Do you understand English at all? Any English?"
detectedLang"en"
heavyLang"en"
scores
en0.8076183147364372
tl0.6078431372549019
no0.6031746031746031
da0.5787700084245998
sv0.49647532729103727
cs0.4444444444444444
it0.4212962962962963
pt0.4110718492343934
pl0.40968122786304606
de0.4026284348864994
hr0.3983152827918171
sq0.3924665856622114
sk0.36948297604035313
ca0.3514915693904021
ro0.3206521739130435
nl0.2625368731563422
vi0.258160237388724
yo0.24812030075187969
et0.23195084485407066
is0.21507064364207218
sl0.1935483870967742
es0.1638795986622074
ms0.12587412587412586
be0.12280701754385964
tr0.12280701754385964
hu0.11816578483245149
az0.11190053285968028
lt0.11190053285968028
lv0.11190053285968028
uk0.11190053285968028
reliabletrue
passestrue
3
name"Marie"
dialogue"Non, je ne comprends rien! Pourquoi ne me comprenez-vous pas? C'est urgent! Il y avait un homme dans les pommiers, et quelqu'un l'a attaqué. Je l'ai vu disparaître!"
detectedLang"fr"
heavyLang"fr"
scores
fr0.8127021964924229
it0.5293110825845101
ca0.5190205509400961
es0.47619047619047616
en0.4591937069813176
ro0.4447248864209995
nl0.3353474320241692
et0.32432432432432434
no0.3068683049779458
sl0.2962252079334613
sq0.29260450160771706
da0.2815153494448073
pt0.26568758344459276
de0.2557510148849797
lv0.23822714681440443
cs0.21316165951359084
lt0.207492795389049
hr0.20520231213872833
pl0.20232052211747645
yo0.19649379108838566
fi0.17971662938105892
tl0.1791044776119403
eu0.1716867469879518
sk0.1628614916286149
tr0.13928012519561817
ms0.13249211356466878
az0.09465020576131687
vi0.08180300500834724
hu0.06937394247038917
sv0.06542056074766354
reliabletrue
passestrue
4
name"Hunter"
dialogue"You seem distressed. Is this about the missing person? Did you witness the disappearance?"
detectedLang"en"
heavyLang"en"
scores
en0.8073394495412844
tl0.58984375
nl0.5562130177514794
sv0.4942196531791907
da0.4892996108949417
fr0.4827586206896552
no0.4791666666666667
it0.42434210526315785
is0.4186046511627907
ms0.4160177975528365
de0.4040862656072645
sq0.40136830102622584
pt0.39999999999999997
yo0.3526510480887793
cs0.34701492537313433
ca0.3155149934810952
es0.31282722513089006
hu0.29245283018867924
hr0.2605633802816902
ro0.24242424242424243
lv0.2222222222222222
az0.19106317411402157
et0.19106317411402157
sk0.18351477449455675
fi0.12935323383084577
lt0.12060301507537688
tr0.11317567567567569
sl0.10714285714285714
pl0.10102739726027396
reliabletrue
passestrue
5
name"Marie"
dialogue"Oui! La disparition! J'ai tout photographié avec mon appareil. Regardez ces images... l'homme en noir qui l'entraînait vers les arbres. C'est la preuve!"
detectedLang"fr"
heavyLang"fr"
scores
fr0.8073588903872086
ca0.6001599360255897
en0.5208433157642549
es0.4686503719447397
da0.37694704049844235
it0.3757802746566792
tl0.33377748167888077
ro0.33065595716198126
no0.3270524899057874
nl0.324780553679946
de0.29725931131412503
sv0.2475545522949586
pt0.20948616600790515
yo0.15611814345991562
fi0.1423670668953688
hi0.1341991341991342
sl0.13119026933101652
sq0.1281604184829991
sk0.12663755458515283
is0.11816578483245149
tr0.0990990990990991
hr0.08424908424908424
vi0.07749077490774908
et0.07149489322191271
zh0.07149489322191271
eu0.06976744186046512
cs0.06454630495790459
reliabletrue
passestrue
6
name"Hunter"
dialogue"Your camera? Did you capture something on camera? Show me the photographs."
detectedLang"en"
heavyLang"en"
scores
en0.7997329773030708
fr0.6522411128284389
tl0.63084495488105
ms0.46428571428571425
es0.4409937888198758
it0.4186046511627907
nl0.4163424124513619
pt0.41482444733420026
sq0.39759036144578314
ca0.38101788170563966
yo0.35988620199146515
et0.3562231759656652
fi0.3333333333333333
no0.29245283018867924
hr0.27884615384615385
sl0.27184466019417475
hi0.26350245499181674
sv0.26229508196721313
ro0.2598684210526316
cs0.2537313432835821
de0.24114671163575044
pl0.15730337078651685
da0.14772727272727273
sk0.14285714285714285
reliabletrue
passestrue
7
name"Marie"
dialogue"Oui, les photos! Attendez, je vais vous montrer... celle-ci, et celle-là. Vous voyez? L'ombre derrière lui. C'est l'assassin, n'est-ce pas?"
detectedLang"fr"
heavyLang"fr"
scores
fr0.8125851885506589
ca0.5464540956569544
it0.5375560538116592
es0.4302486187845304
nl0.406901509705248
no0.3911439114391144
en0.375
tl0.3648960739030023
ro0.33681672025723475
de0.3330638641875505
da0.32098765432098764
et0.29366438356164387
yo0.27312775330396477
pt0.2724867724867725
sk0.25271739130434784
fi0.2438130155820348
hr0.21800947867298578
pl0.18397626112759644
sq0.18154761904761904
sl0.17334669338677355
lt0.1716867469879518
vi0.159877800407332
cs0.15123456790123457
lv0.15123456790123457
sv0.13066385669125397
tr0.13066385669125397
az0.1185897435897436
ms0.0924092409240924
hi0.08536585365853659
reliabletrue
passestrue
8
name"Hunter"
dialogue"I can't understand a word you're saying, but you obviously saw something. Can you just—"
detectedLang"en"
heavyLang"en"
scores
en0.8165869218500799
tl0.4964973730297723
sv0.47199265381083566
da0.47102115915363385
no0.47102115915363385
cs0.4534220532319392
ca0.4267198404785643
sk0.39727463312368977
tr0.3604004449388209
pl0.3495475113122172
ro0.3451025056947608
de0.31137724550898205
hr0.30387409200968524
nl0.30133657351154314
ms0.2953431372549019
it0.29447852760736193
et0.28393524283935245
hu0.27944862155388467
pt0.27490542244640603
is0.26937738246505716
az0.267515923566879
es0.267515923566879
sq0.26376440460947503
yo0.26376440460947503
fr0.26282051282051283
lt0.20138888888888887
lv0.18785310734463279
vi0.18785310734463279
sl0.13533834586466165
be0.10852713178294573
eu0.10852713178294573
fi0.0987460815047022
uk0.0987460815047022
reliabletrue
passestrue
9
name"Hunter"
dialogue"Hunter. ... Yeah. ... What do you mean, another one? ... Same location? ... I'm on my way."
detectedLang"en"
heavyLang"en"
scores
en0.8203592814371257
tl0.6370967741935484
fr0.5562130177514794
pl0.4742990654205608
da0.4545454545454546
hr0.4532199270959903
cs0.45255474452554745
yo0.4186046511627907
pt0.4178525226390685
de0.4094488188976378
nl0.39597315436241615
sk0.3943472409152086
sv0.3818681318681319
ca0.3617021276595745
no0.3562231759656652
sq0.35344827586206895
fi0.3401759530791789
es0.30124223602484473
sl0.28457869634340227
ro0.2706645056726094
et0.2549668874172185
it0.2549668874172185
tr0.2227979274611399
vi0.19786096256684493
hi0.15730337078651685
zh0.14611005692599618
ms0.11591355599214145
reliabletrue
passestrue
10
name"Marie"
dialogue"Non, ne raccrochez pas! Vous devez voir ces images maintenant! C'est connecté à tout ça, je le sais!"
detectedLang"fr"
heavyLang"fr"
scores
fr0.8137931034482759
en0.5496997998665777
ca0.5236414961185604
it0.4689221085759244
ro0.4453574363188167
sl0.4260204081632653
yo0.375
hr0.3522072936660269
nl0.3515850144092219
pt0.32432432432432434
tl0.3098159509202454
es0.3084016393442623
de0.30626927029804724
lt0.299792531120332
sq0.2606790799561884
cs0.25331858407079644
lv0.22055427251732102
hu0.21052631578947367
fi0.20681551116333724
zh0.1847826086956522
sk0.17682926829268292
tr0.1222366710013004
pl0.11879895561357702
eu0.1141732283464567
ms0.11067193675889328
da0.10949868073878628
no0.09999999999999999
et0.09638554216867469
reliabletrue
passestrue
11
name"Hunter"
dialogue"Look, I have to go. There's been another incident. Stay here—I'll send someone who speaks French to take your statement."
detectedLang"en"
heavyLang"en"
scores
en0.814150217892848
tl0.5954241071428572
da0.5252128356254093
no0.4515885022692889
pl0.43972179289026275
sq0.43403590944574555
it0.4129554655870445
fr0.40427280197206245
cs0.40230832646331405
es0.4013212221304706
ro0.3943191311612364
ca0.3938127090301004
sk0.3855932203389831
hr0.3776824034334764
yo0.3706597222222222
sv0.36067019400352734
sl0.3503584229390681
et0.34977578475336324
pt0.3378995433789954
de0.33729433272394876
nl0.3249534450651769
az0.3153918791312559
lt0.2933723196881091
lv0.25488180883864336
hu0.20678336980306347
ms0.15893271461716937
tr0.15105386416861827
be0.0880503144654088
is0.0799492385786802
uk0.0799492385786802
vi0.0799492385786802
reliabletrue
passestrue
12
name"Marie"
dialogue"Attendez! Vous ne pouvez pas partir! Ces photos sont importantes... quelqu'un veut les détruire, je le sens! Revenez!"
detectedLang"fr"
heavyLang"fr"
scores
fr0.8143267848586488
es0.6159563924677899
ca0.6009268795056643
it0.5804006497022198
pt0.5268620268620269
ro0.5192307692307693
en0.5035233824471492
no0.40108191653786707
nl0.39594699922057675
sl0.38492063492063494
de0.37449556093623887
tl0.37399030694668817
sq0.3272569444444444
da0.3260869565217392
lt0.3153710247349823
hr0.3117229129662522
yo0.3074173369079536
lv0.2935278030993619
tr0.28307123034227566
cs0.2736644798500469
sv0.2597898758357211
hu0.23870333988212183
eu0.22188755020080322
sk0.2115971515768057
fi0.17640807651434642
pl0.17200854700854698
ms0.16576964477933262
et0.14835164835164832
az0.0935672514619883
hi0.0903755868544601
is0.08930669800235018
reliabletrue
passestrue
13
name"Hunter"
dialogue"Just... don't leave. I'll be back with a translator."
detectedLang"en"
heavyLang"en"
scores
en0.809830310122879
tl0.5390070921985816
ro0.48
ca0.4698205546492659
et0.4672131147540984
sv0.4672131147540984
pt0.46369636963696376
hu0.45652173913043476
lt0.44539249146757676
ms0.44539249146757676
pl0.4268077601410935
hr0.4206773618538324
yo0.4133574007220217
sq0.4025735294117647
sl0.3925233644859813
es0.39138576779026213
de0.3821292775665399
nl0.38095238095238093
fr0.37739463601532564
da0.37619961612284064
no0.3737957610789981
sk0.3725868725868726
cs0.3701550387596899
it0.36647173489278756
vi0.3271221532091097
tr0.3010752688172043
eu0.29653679653679654
lv0.29653679653679654
az0.28414096916299564
is0.1875
fi0.16237113402061853
reliabletrue
passestrue