NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-08-09-01J4W2AQ3EJFQN2VVY8KDW2M4J
Run Details
Model:
Mistral Large
Test:
Language Writing
Scenario:
Character dialogue (French) in a story
Duration:
11.1s
Cost:
$0.003594
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
Messages
Meta
AI
Marie: (Looking up from her camera, Marie speaks in French) "Je suis désolée, mais je ne parle pas anglais. Vous m'avez l'air perdu." (I'm sorry, but I don't speak English. You seem lost.) Hunter: (Raising an eyebrow, Hunter responds) "I'm not lost, ma'am. I'm Detective Hunter. I'm investigating some recent events in town. Did you notice anything unusual?" Marie: (Looking troubled, Marie responds in French) "Oui, j'ai vu quelque chose d'étrange. Il y a deux nuits, j'ai vu une lumière étrange dans les bois. J'étais effrayée." (Yes, I saw something strange. Two nights ago, I saw a strange light in the woods. I was scared.) Hunter: (Looking confused, Hunter tries to understand) "I'm sorry, I don't understand. Can you show me in your photos?" Marie: (Shaking her head, Marie responds in French) "Non, je n'ai pas pu prendre de photo. C'était trop loin et c'est parti trop vite." (No, I couldn't take a photo. It was too far away and it disappeared too quickly.) Hunter: (Nodding, Hunter takes out his card) "Alright, if you remember anything else, please call me." Marie: (Taking the card, Marie responds in French) "Je ne suis pas sûre de pouvoir vous aider, mais je vous appellerai si je me souviens de quelque chose." (I'm not sure I can help you, but I will call you if I remember anything.) Hunter: (Getting a call, Hunter stands up) "I have to go. Thank you for your time." Marie: (Nodding, Marie responds in French) "De rien, détective. J'espère que vous trouverez ce que vous cherchez." (You're welcome, detective. I hope you find what you're looking for.)
total_cost
0.003594
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Parse dialogue
n/a
dialogue
0
name
"Marie"
dialogue
"Je suis désolée, mais je ne parle pas anglais. Vous m'avez l'air perdu."
detectedLang
"fr"
heavyLang
"fr"
scores
fr
0.794283239497618
sl
0.5230923694779117
ca
0.5158002038735984
lt
0.5153061224489796
sq
0.489247311827957
cs
0.4391971664698937
hr
0.4221411192214112
it
0.41066997518610426
pt
0.4069912609238452
sk
0.37582128777923784
nl
0.3708609271523179
lv
0.35020519835841313
ms
0.34392265193370164
ro
0.3384401114206128
es
0.3338008415147265
yo
0.2554858934169279
pl
0.24960505529225907
tr
0.24363057324840762
hu
0.23878205128205127
de
0.2313915857605178
en
0.22003284072249588
fi
0.15630550621669628
az
0.12844036697247707
et
0.1171003717472119
da
0.11048689138576778
no
0.11048689138576778
sv
0.11048689138576778
reliable
true
passes
true
1
name
"Hunter"
dialogue
"I'm not lost, ma'am. I'm Detective Hunter. I'm investigating some recent events in town. Did you notice anything unusual?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.7944078947368421
tl
0.633610161211529
ro
0.5917256396298313
fr
0.5490078171978352
pt
0.5364647713226205
it
0.5285983658076682
nl
0.51171875
sv
0.47662247034194
ca
0.4673295454545454
es
0.4577006507592191
de
0.44196428571428575
cs
0.4042891183478951
sl
0.38474159146841674
da
0.37395659432387307
ms
0.3713327745180218
no
0.36386768447837153
hr
0.3578767123287671
sq
0.33035714285714285
sk
0.32553956834532377
lv
0.27606177606177607
et
0.2378048780487805
az
0.21218487394957983
lt
0.20127795527156547
pl
0.16943521594684383
is
0.15540540540540537
tr
0.1544532130777903
yo
0.10501193317422433
fi
0.07292954264524104
reliable
true
passes
true
2
name
"Marie"
dialogue
"Oui, j'ai vu quelque chose d'étrange. Il y a deux nuits, j'ai vu une lumière étrange dans les bois. J'étais effrayée."
detectedLang
"fr"
heavyLang
"fr"
scores
fr
0.7991707696294377
en
0.41816816816816815
ca
0.4079449961802903
es
0.39829192546583847
it
0.3509212730318258
ro
0.2896425297891842
pt
0.2857142857142857
da
0.2777260018639329
no
0.26609848484848486
nl
0.2504835589941973
de
0.2357001972386588
tl
0.23038728897715988
pl
0.2131979695431472
lt
0.2083758937691522
az
0.19270833333333331
lv
0.18162618796198524
vi
0.17815482502651114
tr
0.17200854700854698
sq
0.16934619506966772
hu
0.16756176154672395
sv
0.15300546448087432
fi
0.1520787746170678
cs
0.14553472987872104
sk
0.143646408839779
yo
0.1331096196868009
hr
0.1262683201803833
sl
0.10404624277456648
is
0.08823529411764706
eu
0.08284023668639054
et
0.07517899761336516
ms
0.07517899761336516
reliable
true
passes
true
3
name
"Hunter"
dialogue
"I'm sorry, I don't understand. Can you show me in your photos?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.800656660412758
tl
0.6129326047358833
nl
0.5711402623612513
no
0.5563674321503131
sv
0.5175936435868331
it
0.5098039215686274
da
0.5086705202312138
de
0.49162679425837325
pt
0.448051948051948
ro
0.4186046511627907
pl
0.4039270687237027
ca
0.4022503516174402
sq
0.3988684582743989
fr
0.3911174785100286
cs
0.38583815028901736
sl
0.36281859070464767
ms
0.3580060422960725
az
0.34514637904468415
es
0.29983525535420097
yo
0.2916666666666667
sk
0.2747440273037543
et
0.27101200686106347
tr
0.256993006993007
lt
0.2517605633802817
hr
0.24645390070921988
is
0.24377224199288253
lv
0.23971377459749554
hi
0.1533864541832669
fi
0.15
be
0.1414141414141414
hu
0.1361788617886179
uk
0.1290983606557377
vi
0.1290983606557377
reliable
true
passes
true
4
name
"Marie"
dialogue
"Non, je n'ai pas pu prendre de photo. C'était trop loin et c'est parti trop vite."
detectedLang
"fr"
heavyLang
"fr"
scores
fr
0.820574162679426
ca
0.5358090185676392
no
0.5308310991957105
da
0.5084269662921348
it
0.48173741362290223
nl
0.45987654320987653
en
0.44267515923566875
sq
0.44208289054197664
sv
0.39999999999999997
es
0.39095127610208813
sl
0.38668224299065423
hr
0.37722419928825623
pt
0.37648456057007124
yo
0.37574316290130794
ro
0.373508353221957
tr
0.36746987951807225
ms
0.3667068757539204
cs
0.362089914945322
et
0.36053593179049936
sk
0.35424354243542433
eu
0.3110236220472441
lt
0.30921052631578944
tl
0.3064729194187582
de
0.3018617021276596
pl
0.23469387755102045
hu
0.2335766423357664
az
0.21407185628742514
hi
0.12790697674418602
lv
0.12060301507537688
reliable
true
passes
true
5
name
"Hunter"
dialogue
"Alright, if you remember anything else, please call me."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8113682092555332
tl
0.5777027027027027
no
0.473314606741573
ms
0.471830985915493
nl
0.4186046511627907
fr
0.4140625
yo
0.41222570532915365
sv
0.39999999999999997
sq
0.3980738362760835
da
0.3842364532019704
de
0.38016528925619836
sl
0.3654822335025381
hu
0.3206521739130435
et
0.31569343065693434
is
0.29111531190926276
sk
0.25447316103379725
es
0.21383647798742136
ro
0.21052631578947367
pt
0.19006479481641467
it
0.1758241758241758
cs
0.17218543046357618
fi
0.16666666666666666
reliable
true
passes
true
6
name
"Marie"
dialogue
"Je ne suis pas sûre de pouvoir vous aider, mais je vous appellerai si je me souviens de quelque chose."
detectedLang
"fr"
heavyLang
"fr"
scores
fr
0.8163924794359577
it
0.5377218934911242
nl
0.521805661820964
en
0.5063191153238547
sq
0.4791666666666667
no
0.4541484716157206
sl
0.4444444444444444
ca
0.43946188340807174
de
0.4281793229643184
cs
0.423963133640553
ro
0.422365988909427
es
0.41259398496240596
da
0.4064577397910731
pt
0.39496611810261373
yo
0.37810945273631835
lt
0.3699596774193548
tl
0.3648373983739837
tr
0.3596311475409836
sv
0.35367114788004134
ms
0.33011789924973206
lv
0.3272335844994618
hr
0.3124312431243124
sk
0.30011198208286677
fi
0.2816091954022989
hu
0.22263681592039805
az
0.17437252311756934
et
0.13194444444444445
pl
0.1270949720670391
eu
0.10071942446043164
reliable
true
passes
true
7
name
"Hunter"
dialogue
"I have to go. Thank you for your time."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8356344510190664
da
0.7139588100686498
tl
0.7002398081534772
no
0.66078697421981
pl
0.5961227786752827
hr
0.5755517826825127
cs
0.5567375886524822
yo
0.5462794918330308
vi
0.4541484716157206
sk
0.44933920704845814
lv
0.42528735632183906
pt
0.40476190476190477
lt
0.4004796163069544
ca
0.3556701030927836
sv
0.3556701030927836
sq
0.34895833333333337
sl
0.32614555256064687
it
0.3150684931506849
ro
0.2647058823529412
ms
0.2378048780487805
be
0.21875
tr
0.21875
hu
0.21135646687697163
az
0.20127795527156547
et
0.20127795527156547
is
0.20127795527156547
uk
0.20127795527156547
reliable
true
passes
true
8
name
"Marie"
dialogue
"De rien, détective. J'espère que vous trouverez ce que vous cherchez."
detectedLang
"fr"
heavyLang
"fr"
scores
fr
0.8069059518400727
ro
0.5175936435868331
ca
0.5098039215686274
es
0.5052386495925495
en
0.44516971279373363
nl
0.4378306878306878
pt
0.43029490616621985
de
0.371301775147929
it
0.35703479576399394
da
0.32324840764331214
no
0.3078175895765472
sv
0.29867986798679863
tl
0.2722602739726028
sq
0.2685025817555938
is
0.1904761904761905
tr
0.18738049713193117
hu
0.18582375478927202
yo
0.18111753371868977
eu
0.1414141414141414
hr
0.1361788617886179
sl
0.1361788617886179
az
0.1290983606557377
ms
0.1290983606557377
reliable
true
passes
true