Run: 2026-02-17-01KHNF4YQS7WDSVP6EXXATZWTX

Run Details

Model:
Arcee AI: Trinity Large (Preview)
Test:
Language Writing
Scenario:
Character dialogue (French) in a story
Duration:
16.6s
Cost:
$0.000000
Provider:
Arcee AI

Evaluation summary

Score Evaluator
Details Link
54.55% 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
Marie: (looking at her camera, troubled and shaken) "Je ne comprends pas ce qui s'est passé. Tout était normal, et puis tout à coup, il a disparu. C'est comme s'il n'avait jamais existé." Hunter: (looking confused) "Excuse me, ma'am, but I don't speak French. Can you tell me what happened in English?" Marie: (shaking her head, trying to compose herself) "I'm sorry, I don't speak English. I just don't understand what happened. He was there one moment, and then he was gone. Like he never existed." Hunter: (nodding, trying to understand) "I see. Can you tell me more about what you saw? Did you notice anything unusual before he disappeared?" Marie: (taking a deep breath) "I was taking pictures of the landscape when I saw him. He was walking down the street, and then he just vanished. It was like he was never there." Hunter: (listening intently) "Did you see anyone else around? Any suspicious activity?" Marie: (shaking her head) "No, there was no one else around. It was just him and me." Hunter: (nodding, taking notes) "I see. Thank you for your help, ma'am. If you remember anything else, please let me know." Marie: (nodding) "Of course. I hope you can find out what happened." Hunter: (getting up to leave) "I will do my best. Thank you again." Marie: (watching him leave) "Good luck, Detective."
created_at"2026-02-17T09:33:39.08421+00:00" 2/17/2026, 9:33:39 AM
model"arcee-ai/trinity-large-preview:free"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency273
moderation_latency(null)
generation_time16590
tokens_prompt316
tokens_completion348
native_tokens_prompt268
native_tokens_completion326
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"chatcmpl-85cc8982f3153b5b"
status200
is_byokfalse
latency127
endpoint_id"b9d81865-ce9a-432a-9cd5-0d9be55e7cb5"
provider_name"Arcee AI"
model_permaslug"arcee-ai/trinity-large-preview"
api_type"completions"
id"gen-1771320802-UX49iPkpRyXi84VsmsBS"
upstream_id"chatcmpl-85cc8982f3153b5b"
total_cost0
cache_discount(null)
upstream_inference_cost0
provider_name"Arcee AI"

Evaluation details

Result Evaluator Details Meta Data
54.55% Parse dialogue n/a
dialogue
0
name"Marie"
dialogue"Je ne comprends pas ce qui s'est passé. Tout était normal, et puis tout à coup, il a disparu. C'est comme s'il n'avait jamais existé."
detectedLang"fr"
heavyLang"fr"
scores
fr0.8241559485530546
ca0.5982552800734618
it0.5642430278884463
pt0.512263099219621
ro0.5119910764082544
en0.49942791762013733
es0.45685909373060213
cs0.43402328589909445
nl0.40918298446995266
de0.39945092656142756
sk0.3902439024390244
lt0.37766714082503555
tl0.35185185185185186
da0.35137138621200886
hr0.34210526315789475
sl0.33962264150943394
sq0.3356112376613516
ms0.33510638297872336
no0.3340943683409437
et0.32484567901234573
yo0.3148003132341425
tr0.31156569630212433
hu0.27864798021434456
lv0.27566225165562913
az0.26655490360435874
pl0.22566371681415928
fi0.19651056014692378
sv0.18604651162790697
is0.13793103448275862
eu0.13537549407114624
vi0.07407407407407407
reliabletrue
passestrue
1
name"Hunter"
dialogue"Excuse me, ma'am, but I don't speak French. Can you tell me what happened in English?"
detectedLang"en"
heavyLang"en"
scores
en0.794054441260745
tl0.5204336947456214
it0.42152917505030174
no0.3561030235162374
sv0.35538116591928254
ro0.3458475540386803
sq0.3290548424737456
sl0.2962056303549572
nl0.29447852760736193
ms0.2866004962779156
az0.28035043804755944
de0.2758186397984887
ca0.2721518987341772
da0.2684478371501272
hr0.2684478371501272
pl0.267515923566879
es0.2580645161290322
cs0.2414248021108179
pt0.23941798941798942
fr0.2374005305039788
yo0.23333333333333334
et0.21555252387448842
tr0.203601108033241
fi0.11538461538461538
sk0.11128284389489954
be0.10852713178294573
hu0.1043613707165109
is0.0987460815047022
lt0.0987460815047022
lv0.0987460815047022
uk0.0987460815047022
vi0.0987460815047022
reliabletrue
passestrue
2
name"Marie"
dialogue"I'm sorry, I don't speak English. I just don't understand what happened. He was there one moment, and then he was gone. Like he never existed."
detectedLang"en"
heavyLang"en"
scores
en0.8183619550858654
no0.5164126611957796
tl0.5152761457109283
de0.48372966207759704
da0.4808055380742605
sv0.44963308872581725
ca0.4186046511627907
nl0.4051910598413843
ro0.38016528925619836
sk0.3614551083591331
yo0.34679334916864607
pl0.3426294820717132
cs0.3248772504091653
hr0.30438448566610454
fr0.30143945808636746
pt0.298469387755102
sq0.298469387755102
es0.2918454935622317
it0.26666666666666666
hu0.21428571428571427
et0.16666666666666666
lt0.14330218068535827
lv0.14330218068535827
is0.1424116424116424
az0.13249211356466878
fi0.09934497816593887
sl0.08333333333333334
ms0.0802675585284281
be0.0782122905027933
tr0.0782122905027933
uk0.07094594594594594
vi0.07094594594594594
reliabletrue
passesfalse
3
name"Hunter"
dialogue"I see. Can you tell me more about what you saw? Did you notice anything unusual before he disappeared?"
detectedLang"en"
heavyLang"en"
scores
en0.8128419234091563
ms0.40202391904323825
et0.39981532779316714
tl0.38446969696969696
sq0.3701550387596899
it0.36336924583741426
es0.3512974051896207
fr0.3340163934426229
no0.33127572016460904
ca0.3200836820083682
hr0.31650893796004204
cs0.2911668484187568
pt0.2688413948256468
da0.2571428571428571
sv0.2476851851851852
nl0.22526817640047678
ro0.22526817640047678
yo0.22526817640047678
lv0.21875
sl0.21307506053268765
fi0.2034313725490196
tr0.18444165621079048
sk0.18341708542713567
hu0.18032786885245902
az0.17721518987341772
eu0.1761723700887199
pl0.16237113402061853
be0.09722222222222222
is0.08835904628330996
lt0.08835904628330996
uk0.08835904628330996
vi0.08835904628330996
reliabletrue
passestrue
4
name"Marie"
dialogue"I was taking pictures of the landscape when I saw him. He was walking down the street, and then he just vanished. It was like he was never there."
detectedLang"en"
heavyLang"en"
scores
en0.8207082025997311
tl0.5941146626078133
no0.5240928019036288
nl0.513677811550152
sv0.47229551451187335
de0.46524064171123
yo0.45615227736233854
da0.44865609924190214
fr0.4087213599408721
sq0.3874425727411945
ca0.3730407523510972
pl0.34156378600823045
is0.3311036789297659
et0.3294216261525566
lv0.313893653516295
sk0.2857142857142857
ro0.27338782924613986
ms0.2366412213740458
sl0.21414538310412573
hr0.19839679358717435
lt0.19759277833500502
it0.18200408997955012
fi0.17610710607621008
cs0.17012448132780084
hu0.1683991683991684
tr0.16317991631799164
pt0.15164369034994699
es0.09502262443438914
eu0.09502262443438914
be0.08045977011494253
az0.07300115874855156
uk0.07300115874855156
vi0.07300115874855156
reliabletrue
passesfalse
5
name"Hunter"
dialogue"Did you see anyone else around? Any suspicious activity?"
detectedLang"en"
heavyLang"en"
scores
en0.8099341104916371
tl0.6069182389937107
ca0.49528936742934054
ro0.4094488188976378
fr0.38825448613376834
et0.37913907284768217
cs0.3644067796610169
pt0.3119266055045872
es0.3093922651933701
nl0.29245283018867924
ms0.2774566473988439
sk0.267578125
hu0.19006479481641467
fi0.1515837104072398
da0.14383561643835618
it0.14383561643835618
lv0.14383561643835618
sq0.14383561643835618
de0.1359447004608295
no0.1359447004608295
sv0.1359447004608295
tr0.1359447004608295
reliabletrue
passestrue
6
name"Marie"
dialogue"No, there was no one else around. It was just him and me."
detectedLang"en"
heavyLang"en"
scores
en0.84169508037019
tl0.595771144278607
sq0.4897959183673469
de0.477491961414791
yo0.4463373083475298
es0.4237588652482269
pt0.41016333938294003
nl0.4014732965009208
lv0.4003690036900369
ca0.39478584729981375
et0.37739463601532564
hr0.36647173489278756
no0.36647173489278756
pl0.33264887063655035
it0.3298969072164949
sv0.2388758782201405
fr0.21875
sk0.21875
sl0.21307506053268765
tr0.21307506053268765
ms0.20537897310513448
fi0.1875
reliabletrue
passesfalse
7
name"Hunter"
dialogue"I see. Thank you for your help, ma'am. If you remember anything else, please let me know."
detectedLang"en"
heavyLang"en"
scores
en0.808970099667774
tl0.5351657235246565
no0.4960560911481157
da0.481981981981982
ms0.4180161943319838
et0.4138634046890927
sv0.40290758047767394
sq0.3991640543364681
sl0.35825892857142855
cs0.339080459770115
yo0.32432432432432434
nl0.31952662721893493
hu0.29792429792429787
is0.27398989898989895
vi0.2656449553001277
sk0.2580645161290322
it0.2532467532467532
fr0.2493472584856397
ro0.2483660130718954
pt0.23230974632843793
de0.213406292749658
hr0.19467787114845939
ca0.1935483870967742
pl0.1797432239657632
es0.15066469719350073
fi0.11538461538461538
be0.10852713178294573
tr0.10852713178294573
az0.0987460815047022
lt0.0987460815047022
lv0.0987460815047022
uk0.0987460815047022
reliabletrue
passestrue
8
name"Marie"
dialogue"Of course. I hope you can find out what happened."
detectedLang"en"
heavyLang"en"
scores
en0.8329048843187661
tl0.6614583333333334
da0.4237588652482269
no0.4237588652482269
sq0.41546762589928055
ca0.3981481481481482
yo0.38095238095238093
fr0.37977099236641226
cs0.3602362204724409
ro0.3512974051896207
is0.3186582809224318
tr0.3114406779661017
az0.3010752688172043
hr0.2995689655172413
sv0.29805615550755943
nl0.2793791574279379
pl0.2793791574279379
it0.26136363636363635
de0.2034313725490196
sk0.181360201511335
be0.17721518987341772
hu0.1709183673469388
et0.16237113402061853
lt0.16237113402061853
lv0.16237113402061853
uk0.16237113402061853
vi0.16237113402061853
reliabletrue
passesfalse
9
name"Hunter"
dialogue"I will do my best. Thank you again."
detectedLang"en"
heavyLang"en"
scores
en0.8228206945428774
cs0.6165644171779141
tl0.6111975116640747
pl0.5908346972176759
vi0.5606326889279437
sk0.5370370370370371
nl0.5335820895522388
hr0.5088408644400786
sq0.500998003992016
no0.4692144373673036
yo0.39759036144578314
pt0.3842364532019704
is0.3734335839598998
da0.3573264781491003
ca0.3556701030927836
sv0.3556701030927836
sl0.32432432432432434
it0.3150684931506849
de0.29775280898876405
ro0.2647058823529412
be0.21875
tr0.21875
hu0.21135646687697163
az0.20127795527156547
et0.20127795527156547
lt0.20127795527156547
lv0.20127795527156547
uk0.20127795527156547
reliabletrue
passestrue
10
name"Marie"
dialogue"Good luck, Detective."
detectedLang"en"
heavyLang"en"
scores
en0.7775800711743772
tl0.7240618101545254
ro0.6684350132625994
fr0.6069182389937107
ca0.5901639344262295
es0.5874587458745875
it0.5805369127516778
pt0.576271186440678
sq0.42660550458715596
da0.40191387559808617
de0.40191387559808617
nl0.3961352657004831
no0.3902439024390244
cs0.3654822335025381
hr0.34895833333333337
sl0.34895833333333337
sv0.34895833333333337
reliabletrue
passesfalse