NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-08-09-01J4W19K291MN5F7QRKGM8DRVJ
Run Details
Model:
Mistral Large
Test:
Language Writing
Scenario:
Character dialogue (Spanish) in a story
Duration:
8.0s
Cost:
$0.002778
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
Messages
Meta
AI
Maria: (Looking up from her camera, she speaks rapidly in Spanish) "Lo siento, no entiendo inglés. ¿Hablas español? He visto algo terrible anoche, pero no sé cómo explicárselo a alguien que no entiende mi idioma." (I'm sorry, I don't understand English. Do you speak Spanish? I saw something terrible last night, but I don't know how to explain it to someone who doesn't understand my language.) Hunter: (Furrowing his brows, he tries to communicate) "I'm sorry, miss. I don't understand Spanish. But you look troubled. Can you show me what's wrong?" Maria: (She looks around nervously, then points to her camera) "Mi cámara... las fotos..." (My camera... the photos...) Hunter: (He looks at her camera, then back at her) "The photos? Are they important? Can you show me?" Maria: (She nods, scrolling through her camera to find the right photos) "Sí, son importantes. Muy importantes." (Yes, they are important. Very important.) Hunter: (His phone rings, he looks at it and then back at Maria) "I'm sorry, miss. I have to go. But this isn't over. I'll find someone who can help us communicate." Maria: (She looks worried but nods) "Está bien. Pero por favor, tenga cuidado." (Okay. But please, be careful.)
total_cost
0.002778
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Parse dialogue
n/a
dialogue
0
name
"Maria"
dialogue
"Lo siento, no entiendo inglés. ¿Hablas español? He visto algo terrible anoche, pero no sé cómo explicárselo a alguien que no entiende mi idioma."
detectedLang
"es"
heavyLang
"es"
scores
es
0.7866987530080946
pt
0.6387550944794368
ca
0.5989304812834225
it
0.5672436750998668
fr
0.5161290322580645
en
0.4284876905041032
tl
0.39740420271940663
sk
0.3821292775665399
yo
0.35301924353019243
hu
0.34738955823293177
et
0.3317340644276902
no
0.3065433854907539
nl
0.2945007235890014
de
0.28780131482834187
fi
0.2867593269934162
lt
0.28044280442804426
da
0.25742574257425743
pl
0.24535603715170282
ro
0.24418604651162787
cs
0.24006235385814498
hr
0.22985781990521328
sv
0.2292490118577075
eu
0.22062350119904073
lv
0.21875
is
0.21686746987951808
sl
0.21686746987951808
tr
0.19554455445544552
sq
0.18341708542713567
vi
0.14172535211267606
az
0.12003610108303249
ms
0.06069364161849711
reliable
true
passes
true
1
name
"Hunter"
dialogue
"I'm sorry, miss. I don't understand Spanish. But you look troubled. Can you show me what's wrong?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.7959516813581456
tl
0.5268735806207419
no
0.4951534733441034
da
0.44982394366197187
nl
0.4429590017825312
sv
0.40702087286527516
sq
0.36676798378926034
it
0.3206521739130435
fr
0.3169398907103825
de
0.3086283185840708
cs
0.29932735426008966
pt
0.29775280898876405
ro
0.2807825086306099
vi
0.2577197149643705
ca
0.25595238095238093
pl
0.2460796139927624
ms
0.21482412060301506
sk
0.20483460559796438
et
0.20178799489144317
tr
0.19041450777202074
az
0.1830065359477124
hr
0.1819371727748691
hu
0.18086500655307994
is
0.17979002624671916
es
0.14030261348005504
sl
0.12342215988779803
yo
0.12219101123595505
fi
0.10714285714285714
be
0.10071942446043164
lt
0.09156976744186046
lv
0.09156976744186046
uk
0.09156976744186046
reliable
true
passes
true
2
name
"Maria"
dialogue
"Mi cámara... las fotos..."
detectedLang
"es"
heavyLang
"es"
scores
es
0.7981157469717362
ca
0.6487119437939111
pt
0.6163682864450128
tr
0.5934959349593496
tl
0.5238095238095238
sl
0.5145631067961165
it
0.511400651465798
cs
0.4983277591973244
sk
0.4983277591973244
fr
0.4915254237288135
hr
0.4915254237288135
ro
0.4897959183673469
lt
0.48805460750853247
pl
0.47735191637630664
de
0.471830985915493
lv
0.471830985915493
nl
0.471830985915493
yo
0.3697478991596639
hu
0.3617021276595745
en
0.3212669683257918
et
0.29577464788732394
sq
0.29577464788732394
az
0.2822966507177033
da
0.2822966507177033
no
0.2822966507177033
sv
0.2822966507177033
reliable
true
passes
true
3
name
"Hunter"
dialogue
"The photos? Are they important? Can you show me?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.8266897746967071
fr
0.6845425867507886
tl
0.6651785714285715
ca
0.5978552278820375
pt
0.5956873315363882
ro
0.5850622406639004
nl
0.5633187772925764
es
0.5581737849779087
no
0.5192307692307693
sq
0.49409780775716694
it
0.47826086956521735
da
0.4186046511627907
ms
0.35064935064935066
tr
0.3435448577680525
lt
0.3348115299334811
sv
0.3258426966292135
yo
0.2628992628992629
et
0.24050632911392408
sl
0.22680412371134018
cs
0.20634920634920634
az
0.20424403183023873
hi
0.20424403183023873
fi
0.2
de
0.19137466307277629
lv
0.19137466307277629
reliable
true
passes
true
4
name
"Maria"
dialogue
"Sí, son importantes. Muy importantes."
detectedLang
"es"
heavyLang
"es"
scores
es
0.8190279214064116
fr
0.7422680412371134
ca
0.717741935483871
pt
0.7033898305084746
it
0.5977011494252874
ro
0.5977011494252874
tl
0.5668316831683169
da
0.5547073791348601
en
0.5205479452054795
tr
0.5179063360881543
yo
0.4582043343653251
no
0.44267515923566875
sv
0.4299674267100977
az
0.38596491228070173
fi
0.308300395256917
sq
0.2768595041322314
de
0.27083333333333337
nl
0.27083333333333337
reliable
true
passes
true
5
name
"Hunter"
dialogue
"I'm sorry, miss. I have to go. But this isn't over. I'll find someone who can help us communicate."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8085171568627451
tl
0.6212121212121212
da
0.5232646834477499
it
0.44933920704845814
no
0.421831637372803
fr
0.3902439024390244
nl
0.37311935807422264
pl
0.37122736418511065
ca
0.36612576064908725
pt
0.34141201264488935
yo
0.32505399568034554
ro
0.31394072447859495
sk
0.3040089086859688
hr
0.28977272727272724
cs
0.27409988385598144
es
0.2638398115429918
az
0.25059952038369304
sv
0.2487980769230769
lv
0.22839506172839508
de
0.21185372005044137
lt
0.21085858585858586
tr
0.19041450777202074
sq
0.17654808959156787
et
0.17437252311756934
sl
0.16219839142091153
be
0.10071942446043164
hu
0.09682080924855492
is
0.09156976744186046
uk
0.09156976744186046
vi
0.09156976744186046
reliable
true
passes
true
6
name
"Maria"
dialogue
"Está bien. Pero por favor, tenga cuidado."
detectedLang
"es"
heavyLang
"es"
scores
es
0.8197903014416775
pt
0.7400756143667296
ca
0.4907407407407407
fr
0.4444444444444444
sq
0.4148936170212766
tl
0.3707093821510297
it
0.36194895591647336
no
0.34210526315789475
is
0.2857142857142857
ms
0.27055702917771884
cs
0.2403314917127072
hu
0.21875
sk
0.21875
en
0.207492795389049
ro
0.207492795389049
da
0.19117647058823528
nl
0.19117647058823528
sl
0.19117647058823528
sv
0.19117647058823528
reliable
true
passes
true