Run: 2026-02-17-01KHNFZSS3ZVQG20ZRDEQ8JZRG

Run Details

Model:
Arcee AI: Trinity Large (Preview)
Test:
Language Writing
Scenario:
Character dialogue (Spanish) in a story
Duration:
13.6s
Cost:
$0.000000
Provider:
Arcee AI

Evaluation summary

Score Evaluator
Details Link
59.09% 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: (looking down at her camera, troubled) "No puedo creer que esto haya pasado. Es tan... tan horrible." (I can't believe this happened. It's so... so horrible.) Hunter: (approaching the table) "Excuse me, miss. I'm Detective Hunter. I was wondering if you could tell me anything about the recent event in town?" Maria: (looking up, startled) "¿Qué? ¿Qué evento?" (What? What event?) Hunter: (confused) "The... the disappearance? The one that happened last night?" Maria: (shaking her head) "No lo sé. No hablo inglés." (I don't know. I don't speak English.) Hunter: (sighing) "Right. Of course. Um... ¿Habla español?" (Do you speak Spanish?) Maria: (nodding) "Sí, hablo español. ¿Por qué?" (Yes, I speak Spanish. Why?) Hunter: (sitting down at the table) "Bueno, hay un problema en la ciudad. Algunas personas han desaparecido." (Well, there's a problem in the town. Some people have disappeared.) Maria: (looking concerned) "¿Desaparecido? ¿Cuántos?" (Disappeared? How many?) Hunter: (shrugging) "No estoy seguro. Pero necesito tu ayuda para resolver este caso." (I'm not sure. But I need your help to solve this case.) Maria: (nodding) "De acuerdo. ¿Qué puedo hacer?" (Okay. What can I do?) Hunter: (explaining the situation) "Necesito que me digas todo lo que sepas sobre lo que pasó anoche. ¿Viste algo sospechoso?" (I need you to tell me everything you know about what happened last night. Did you see anything suspicious?) Maria: (thinking) "No, no vi nada. Pero escuché un ruido extraño. Como un grito." (No, I didn't see anything. But I heard a strange noise. Like a scream.) Hunter: (taking notes) "Un grito. ¿A qué hora?" (A scream. What time?) Maria: (thinking) "Creo que fue alrededor de las 11 de la noche." (I think it was around 11 at night.) Hunter: (nodding) "Gracias por tu ayuda. Te llamaré si necesito más información." (Thank you for your help. I'll call you if I need more information.) Maria: (standing up) "De nada. Espero que encuentres a las personas desaparecidas." (You're welcome. I hope you find the missing people.) Hunter: (standing up as well) "Yo también. Gracias de nuevo." (Me too. Thanks again.) Hunter's phone rings and he answers it. Hunter: (on the phone) "¿Sí? ... ¿En serio? ... De acuerdo, voy para allá ahora mismo." (Yes? ... Really? ... Okay, I'm on my way there now.) Hunter hangs up and looks at Maria. Hunter: (apologetically) "Lo siento, pero tengo que irme. Te llamaré si necesito más información." (I'm sorry, but I have to go. I'll call you if I need more information.) Maria: (nodding) "Está bien. Buena suerte con el caso." (Okay. Good luck with the case.) Hunter: (smiling) "Gracias. Adiós." (Thanks. Goodbye.) Hunter leaves the cafe, and Maria sits back down, looking troubled and shaken.
created_at"2026-02-17T09:48:15.508359+00:00" 2/17/2026, 9:48:15 AM
model"arcee-ai/trinity-large-preview:free"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency304
moderation_latency(null)
generation_time13501
tokens_prompt317
tokens_completion757
native_tokens_prompt268
native_tokens_completion752
native_tokens_completion_images(null)
native_tokens_reasoning0
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
router(null)
provider_responses
0
id"9cf45ddee26405fd-IAD"
status200
is_byokfalse
latency192
endpoint_id"239c00d5-c404-4d17-b243-6a645212dc95"
provider_name"Arcee AI"
model_permaslug"arcee-ai/trinity-large-preview"
api_type"completions"
id"gen-1771321681-9O75QyxpjJ59EWd0jb5Q"
upstream_id"9cf45ddee26405fd-IAD"
total_cost0
cache_discount(null)
upstream_inference_cost0
provider_name"Arcee AI"

Evaluation details

Result Evaluator Details Meta Data
59.09% Parse dialogue n/a
dialogue
0
name"Maria"
dialogue"No puedo creer que esto haya pasado. Es tan... tan horrible."
detectedLang"es"
heavyLang"es"
scores
es0.8011664899257688
ca0.6380308880308881
tl0.5753114382785957
pt0.5259165613147914
en0.5241116751269036
lv0.48489010989010994
eu0.4230769230769231
fr0.40476190476190477
lt0.36115843270868825
ms0.33510638297872336
pl0.28023032629558536
de0.27606177606177607
hu0.21383647798742136
hr0.21218487394957983
no0.20550847457627117
sk0.19527896995708155
tr0.19006479481641467
yo0.18655097613882862
it0.1758241758241758
ro0.1591928251121076
sq0.1591928251121076
reliabletrue
passestrue
1
name"Hunter"
dialogue"Excuse me, miss. I'm Detective Hunter. I was wondering if you could tell me anything about the recent event in town?"
detectedLang"en"
heavyLang"en"
scores
en0.8144712430426716
tl0.5934959349593496
nl0.592044875063743
sv0.532437171244886
fr0.5021779713752333
ro0.49012109623964306
da0.4865211810012837
no0.4855305466237942
it0.477124183006536
sq0.43342776203966005
ca0.42569992821249103
de0.4240460763138949
pt0.3874425727411945
ms0.36808846761453395
sl0.35012185215272135
es0.3442622950819672
cs0.3333333333333333
yo0.31565440547476475
pl0.25857275254865614
hr0.2516370439663237
sk0.2172211350293542
et0.1649269311064718
az0.15522703273495247
tr0.13885898815931108
lt0.13606911447084233
fi0.08571428571428572
be0.08045977011494253
hu0.07727797001153403
is0.07300115874855156
lv0.07300115874855156
uk0.07300115874855156
vi0.07300115874855156
reliabletrue
passestrue
2
name"Maria"
dialogue"¿Qué? ¿Qué evento?"
detectedLang"es"
heavyLang"es"
scores
es0.8243559718969555
pt0.7564935064935066
it0.7457627118644068
tl0.7093023255813954
sk0.5786516853932584
lt0.5664739884393063
en0.5614035087719298
cs0.5562130177514794
nl0.5370370370370371
ro0.5370370370370371
da0.4791666666666667
de0.4791666666666667
no0.4791666666666667
sv0.4791666666666667
reliabletrue
passestrue
3
name"Hunter"
dialogue"The... the disappearance? The one that happened last night?"
detectedLang"en"
heavyLang"en"
scores
en0.8206401766004415
tl0.6973929236499069
fr0.5022970903522206
nl0.5
yo0.4247787610619469
no0.4122965641952984
da0.3981481481481482
ms0.3512974051896207
hr0.30997876857749473
it0.30997876857749473
de0.29653679653679654
sq0.29653679653679654
pl0.2111650485436893
sv0.1935483870967742
et0.19154228855721395
cs0.1709183673469388
es0.16237113402061853
sl0.16237113402061853
pt0.15364583333333331
sk0.15364583333333331
reliabletrue
passestrue
4
name"Maria"
dialogue"No lo sé. No hablo inglés."
detectedLang"es"
heavyLang"es"
scores
es0.8046875
ca0.6846846846846848
it0.6716697936210132
pt0.630801687763713
yo0.5603015075376884
tr0.4868035190615836
lv0.4281045751633987
is0.41275167785234906
en0.37275985663082434
hu0.37050359712230213
hr0.36594202898550726
no0.3566176470588235
sk0.34210526315789475
vi0.34210526315789475
fr0.3346007604562738
tl0.3137254901960784
et0.3055555555555556
pl0.3
reliabletrue
passestrue
5
name"Hunter"
dialogue"Right. Of course. Um... ¿Habla español?"
detectedLang"en"
heavyLang"es"
scores
en0.697136563876652
es0.6798603026775321
tl0.6794871794871795
fr0.5703125
de0.5124113475177305
pt0.48405253283302063
is0.47115384615384615
yo0.40476190476190477
no0.3792325056433409
nl0.314214463840399
eu0.30203045685279184
ca0.3002544529262086
sq0.260752688172043
ro0.23822714681440443
da0.21203438395415475
reliabletrue
passestrue
6
name"Maria"
dialogue"Sí, hablo español. ¿Por qué?"
detectedLang"es"
heavyLang"es"
scores
es0.8275862068965517
ca0.5959595959595959
pt0.5555555555555556
yo0.42528735632183906
sq0.3939393939393939
eu0.3730407523510972
fr0.3150684931506849
tr0.2805755395683453
reliabletrue
passestrue
7
name"Hunter"
dialogue"Bueno, hay un problema en la ciudad. Algunas personas han desaparecido."
detectedLang"es"
heavyLang"es"
scores
es0.820635462931329
ca0.7062115277000559
pt0.6593121349772875
ro0.6043707611152976
it0.5721271393643031
fr0.5635910224438903
sv0.5524296675191815
no0.5489690721649484
lv0.5196706312900274
da0.5165745856353591
tl0.5138888888888888
lt0.4980879541108987
et0.4739478957915832
tr0.4198895027624309
nl0.41077441077441074
en0.4061085972850679
sq0.40340909090909094
sk0.34863523573200994
hr0.34127979924717694
de0.33879093198992444
eu0.33290978398983484
is0.32778489116517284
ms0.3137254901960784
vi0.3
az0.28765264586160105
sl0.2768595041322314
cs0.27586206896551724
pl0.2738589211618257
yo0.2738589211618257
hu0.1935483870967742
fi0.13793103448275862
reliabletrue
passesfalse
8
name"Maria"
dialogue"¿Desaparecido? ¿Cuántos?"
detectedLang"es"
heavyLang"es"
scores
es0.789410348977136
pt0.7407407407407407
ca0.4912790697674419
hu0.36363636363636365
eu0.3445692883895131
tl0.3445692883895131
lt0.32950191570881227
sk0.32950191570881227
en0.3055555555555556
ms0.3055555555555556
tr0.3055555555555556
reliabletrue
passestrue
9
name"Hunter"
dialogue"No estoy seguro. Pero necesito tu ayuda para resolver este caso."
detectedLang"es"
heavyLang"es"
scores
es0.815422477440525
pt0.740484429065744
it0.5722433460076045
ca0.5618305744888024
tl0.5490981963927856
ro0.5176848874598071
en0.45188794153471373
sk0.3723849372384937
pl0.337260677466863
lv0.3212669683257918
hr0.29245283018867924
sq0.27884615384615385
no0.27652733118971057
tr0.27652733118971057
ms0.2706645056726094
eu0.1773308957952468
hu0.16044776119402984
cs0.15887850467289721
et0.14611005692599618
fr0.13793103448275862
lt0.13793103448275862
sl0.13793103448275862
sv0.13793103448275862
reliabletrue
passesfalse
10
name"Maria"
dialogue"De acuerdo. ¿Qué puedo hacer?"
detectedLang"es"
heavyLang"es"
scores
es0.84779299847793
fr0.5555555555555556
nl0.43342776203966005
ca0.4318181818181818
pt0.4269340974212034
ro0.4269340974212034
da0.3730407523510972
sv0.3630573248407643
no0.35275080906148865
tr0.3288590604026846
hu0.3265993265993266
yo0.3197278911564626
tl0.2727272727272727
eu0.25925925925925924
de0.250936329588015
it0.250936329588015
az0.23954372623574144
en0.23954372623574144
ms0.23954372623574144
sq0.23954372623574144
reliabletrue
passestrue
11
name"Hunter"
dialogue"Necesito que me digas todo lo que sepas sobre lo que pasó anoche. ¿Viste algo sospechoso?"
detectedLang"es"
heavyLang"es"
scores
es0.7695390781563126
pt0.6921841541755889
it0.603448275862069
ca0.5933521923620934
fr0.4611059044048735
ms0.4502868068833652
ro0.36743674367436746
no0.3162901307966707
et0.3146603098927294
en0.30639324487334135
tl0.30133657351154314
sl0.2857142857142857
sq0.28393524283935245
de0.21124828532235942
nl0.20798898071625344
da0.1991643454038997
hr0.1935483870967742
yo0.19241573033707865
lv0.18785310734463279
vi0.13663663663663664
lt0.1314199395770393
sk0.13010590015128592
fi0.11538461538461538
cs0.11128284389489954
is0.11128284389489954
pl0.10990712074303406
tr0.09591194968553458
reliabletrue
passesfalse
12
name"Maria"
dialogue"No, no vi nada. Pero escuché un ruido extraño. Como un grito."
detectedLang"es"
heavyLang"es"
scores
es0.7822536744692433
pt0.6509598603839442
it0.6086105675146771
ca0.5249406175771971
tl0.5031055900621118
fr0.4550408719346049
lv0.4269340974212034
sk0.40119760479041916
cs0.38176197836166925
ro0.3630573248407643
no0.3579454253611557
sv0.355877616747182
en0.3174061433447099
da0.26199261992619927
yo0.20948616600790515
hr0.20159680638722555
vi0.2
tr0.18032786885245902
nl0.17012448132780084
de0.16142557651991615
lt0.15966386554621848
pl0.15789473684210525
reliabletrue
passestrue
13
name"Hunter"
dialogue"Un grito. ¿A qué hora?"
detectedLang"es"
heavyLang"es"
scores
es0.8257839721254355
it0.7159090909090909
ca0.715370018975332
pt0.6842105263157895
ro0.6551724137931034
fr0.6411483253588517
lv0.6124031007751938
yo0.6
lt0.512987012987013
tl0.512987012987013
hu0.5098039215686274
en0.471830985915493
cs0.46808510638297873
sk0.46428571428571425
hr0.42748091603053434
pl0.4117647058823529
sl0.375
tr0.33920704845814975
is0.3333333333333333
da0.32432432432432434
sq0.32432432432432434
az0.3181818181818182
eu0.3181818181818182
nl0.3181818181818182
no0.3181818181818182
vi0.3181818181818182
de0.3087557603686636
et0.29577464788732394
fi0.29577464788732394
ms0.29577464788732394
sv0.29577464788732394
reliabletrue
passesfalse
14
name"Maria"
dialogue"Creo que fue alrededor de las 11 de la noche."
detectedLang"es"
heavyLang"es"
scores
es0.8409485251590515
ca0.7052518756698821
fr0.6698679471788717
pt0.597953216374269
ro0.5283018867924528
it0.5233968804159446
de0.48015122873345933
tl0.462890625
no0.4123931623931624
yo0.40347071583514105
en0.39956331877729256
nl0.3574766355140187
sq0.33894230769230765
da0.30203045685279184
sv0.2930591259640103
tr0.26273458445040215
hu0.260752688172043
vi0.233983286908078
eu0.20289855072463767
az0.1863905325443787
ms0.1863905325443787
reliabletrue
passestrue
15
name"Hunter"
dialogue"Gracias por tu ayuda. Te llamaré si necesito más información."
detectedLang"es"
heavyLang"es"
scores
es0.8122529644268774
ca0.6138211382113822
ro0.5747538048343778
pt0.573608617594255
sq0.5501893939393939
it0.5192307692307693
sk0.48759439050701187
pl0.47802197802197804
cs0.47339246119733924
sl0.46083995459704885
fr0.45652173913043476
hr0.42073170731707316
lv0.39180537772087065
lt0.37989556135770236
nl0.36412315930388217
tl0.3546195652173913
en0.3338008415147265
no0.30453879941434847
yo0.3014705882352941
et0.2952522255192878
hu0.2835595776772248
de0.23014586709886548
da0.2238562091503268
eu0.22003284072249588
sv0.22003284072249588
az0.2096505823627288
ms0.1171003717472119
reliabletrue
passesfalse
16
name"Maria"
dialogue"De nada. Espero que encuentres a las personas desaparecidas."
detectedLang"es"
heavyLang"es"
scores
es0.8138414367060884
pt0.7789911596463859
ca0.7233072916666666
fr0.5952380952380952
it0.5841487279843445
en0.5758483033932136
tl0.5526315789473685
ro0.5081018518518519
lt0.4897959183673469
sv0.48609431680773885
no0.47724477244772445
ms0.4627054361567636
eu0.44152431011826543
da0.4348404255319149
tr0.42876344086021506
hu0.4264507422402159
lv0.4162087912087912
nl0.4121715076071923
et0.4097222222222222
sq0.3988684582743989
sk0.3928571428571429
de0.38672438672438675
yo0.3338557993730407
is0.3167202572347267
az0.3111831442463533
cs0.31006493506493504
hr0.2869127516778523
pl0.2784380305602716
sl0.17475728155339806
vi0.1414141414141414
fi0.1290983606557377
reliabletrue
passestrue
17
name"Hunter"
dialogue"Yo también. Gracias de nuevo."
detectedLang"es"
heavyLang"es"
scores
es0.8464163822525598
pt0.6489859594383774
ca0.5562130177514794
tl0.5292887029288702
yo0.45520581113801456
ms0.4230769230769231
nl0.40476190476190477
fr0.39999999999999997
ro0.39839572192513373
da0.34593023255813954
sv0.336283185840708
no0.3263473053892215
pl0.30769230769230765
tr0.303405572755418
hu0.30124223602484473
eu0.23728813559322032
de0.22945205479452058
it0.22945205479452058
az0.21875
en0.21875
sq0.21875
reliabletrue
passesfalse
18
name"Hunter"
dialogue"¿Sí? ... ¿En serio? ... De acuerdo, voy para allá ahora mismo."
detectedLang"es"
heavyLang"es"
scores
es0.8267097966728282
ca0.6334310850439883
pt0.5941558441558442
tl0.5481927710843374
fr0.5358910891089109
nl0.4959677419354839
tr0.4834710743801653
da0.46808510638297873
sv0.4673295454545454
no0.4588744588744588
it0.4573082489146165
lt0.39222042139384117
yo0.39222042139384117
sq0.3892508143322475
ms0.37810945273631835
is0.3718592964824121
ro0.3686868686868687
sl0.36655405405405406
eu0.27884615384615385
hr0.27466150870406186
en0.2618110236220473
de0.25742574257425743
az0.2454728370221328
hu0.20550847457627117
fi0.1830065359477124
pl0.14383561643835618
cs0.1359447004608295
sk0.1359447004608295
reliabletrue
passesfalse
19
name"Hunter"
dialogue"Lo siento, pero tengo que irme. Te llamaré si necesito más información."
detectedLang"es"
heavyLang"es"
scores
es0.809368191721133
ca0.6462264150943396
it0.6004566210045662
pt0.5885579937304075
ro0.5205479452054795
tl0.5018975332068311
fr0.4755244755244755
sk0.4696969696969697
cs0.45369406867845996
lt0.4496855345911949
sq0.42371020856201974
yo0.3944636678200692
sl0.38882421420256114
nl0.34127979924717694
hu0.3354430379746835
hr0.3312101910828026
pl0.3251928020565552
eu0.3181818181818182
en0.3119266055045872
lv0.29906542056074764
no0.2837653478854025
et0.27486187845303867
ms0.2391304347826087
de0.2128935532233883
da0.20694864048338368
sv0.2033383915022762
az0.1935483870967742
is0.1732283464566929
vi0.14772727272727273
reliabletrue
passesfalse
20
name"Maria"
dialogue"Está bien. Buena suerte con el caso."
detectedLang"es"
heavyLang"es"
scores
es0.8314227916385704
pt0.635036496350365
ca0.5954692556634305
it0.571917808219178
tl0.5309568480300189
fr0.4769874476987448
hu0.4577006507592191
ro0.4279176201372997
vi0.3438320209973753
no0.3169398907103825
de0.30362116991643456
eu0.30167597765363136
cs0.258160237388724
sk0.23547400611620795
da0.22118380062305293
reliabletrue
passestrue
21
name"Hunter"
dialogue"Gracias. Adiós."
detectedLang"es"
heavyLang"es"
scores
es0.7214484679665738
pt0.5850622406639004
hu0.5708154506437768
ca0.5
pl0.5
reliabletrue
passesfalse