NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-10-16-01JAB4N79JTJ29ZCR7X5Q3BNAW
Run Details
Model:
Ministral 8B
Test:
Language Writing
Scenario:
Character dialogue (Spanish) in a story
Duration:
3.3s
Cost:
$0.000064
Evaluation summary
Score
Evaluator
Details Link
81.82%
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
**Voice Sheet** *Maria, looking through her camera, adjusts the lens slightly, her eyes scanning the scene of the bustling cafe. She speaks softly in Spanish, "A ver, a ver. ¿Dónde está mi café? Necesito una buena foto." *Hunter approaches the table, his boots clunking on the wooden floor. He looks around, then addresses her in English, "Excuse me, miss. I don't mean to interrupt, but I need to ask you something." *Maria looks up, startled, her eyes meeting Hunter's. She smiles, but it's a nervous one. "¿Hablas español?" she asks, her voice trembling slightly. *Hunter looks confused, shakes his head, "No, I don't. Do you speak English?" *Maria nods, but her smile fades. "Sí, but... not much." *Hunter pauses, then continues, "I'm Detective Hunter. I'm investigating some disappearances in town. Have you seen or heard anything unusual?" *Maria looks troubled. She speaks slowly, "Sí, algo... algo extraño. Anoche, vi... vi algo." *Hunter raises an eyebrow, "What did you see?" *Maria looks down, her voice barely above a whisper, "Un hombre... en el bosque. Él... él no era un hombre normal." *Hunter's expression hardens, "What do you mean, 'not a normal man'?" *Before Maria can answer, Hunter's radio crackles to life. He steps away, listening intently. After a moment, he turns back to Maria, "I gotta go. Can you meet me at the station later? We need to talk more." *Maria nods, her eyes wide with fear. Hunter turns and walks away, leaving Maria alone at the table, her camera forgotten.
total_cost
0.00006430000000000002
Evaluation details
Result
Evaluator
Details
Meta Data
81.82%
Parse dialogue
n/a
dialogue
0
name
"Maria"
dialogue
"A ver, a ver. ¿Dónde está mi café? Necesito una buena foto."
detectedLang
"es"
heavyLang
"es"
scores
es
0.789805570152391
pt
0.7173144876325088
ca
0.6688741721854304
it
0.6035678889990089
ro
0.5897435897435898
nl
0.5067817509247842
sk
0.47643979057591623
cs
0.47368421052631576
tl
0.4020926756352765
sl
0.3930197268588771
hr
0.38366718027734975
pl
0.38080495356037153
hu
0.37597503900156004
en
0.35275080906148865
yo
0.34102141680395387
fr
0.3127147766323024
eu
0.3079584775086505
no
0.2753623188405797
tr
0.27140255009107467
da
0.26199261992619927
lv
0.24953095684803
de
0.24528301886792453
et
0.23371647509578544
lt
0.17012448132780084
is
0.15789473684210525
sq
0.15254237288135594
az
0.14893617021276595
vi
0.14893617021276595
fi
0.13606911447084233
ms
0.13606911447084233
sv
0.13606911447084233
reliable
true
passes
true
1
name
"Hunter"
dialogue
"Excuse me, miss. I don't mean to interrupt, but I need to ask you something."
detectedLang
"en"
heavyLang
"en"
scores
en
0.7852622061482821
tl
0.5539906103286385
no
0.47222222222222227
cs
0.45150115473441105
et
0.4358669833729216
sq
0.433849821215733
pl
0.4193154034229829
hr
0.41574415744157445
da
0.4077306733167082
it
0.37989556135770236
sl
0.3782722513089006
sk
0.370026525198939
es
0.3683510638297872
lv
0.3632707774798928
fr
0.36155913978494625
pt
0.35636856368563685
lt
0.33936022253129344
ca
0.3271954674220963
ms
0.3252840909090909
yo
0.32045779685264664
sv
0.31259044862518093
ro
0.2835595776772248
nl
0.25897035881435254
tr
0.23014586709886548
hu
0.2238562091503268
az
0.21487603305785125
vi
0.2096505823627288
de
0.15630550621669628
eu
0.14721723518850988
fi
0.13636363636363635
be
0.12844036697247707
is
0.1171003717472119
uk
0.1171003717472119
reliable
true
passes
true
2
name
"Maria"
dialogue
"¿Hablas español?"
detectedLang
"es"
heavyLang
"es"
scores
es
0.7947454844006568
eu
0.4877049180327869
ca
0.48559670781893005
pt
0.4541484716157206
fr
0.423963133640553
reliable
true
passes
true
3
name
"Hunter"
dialogue
"No, I don't. Do you speak English?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.816311535635562
hr
0.6334310850439883
pl
0.5791245791245792
tl
0.5711835334476844
no
0.5644599303135889
cs
0.558303886925795
sk
0.5412844036697247
pt
0.5404411764705882
ca
0.5219885277246654
sq
0.500998003992016
da
0.4577006507592191
sv
0.45652173913043476
it
0.43820224719101125
lv
0.4369369369369369
vi
0.410377358490566
yo
0.39759036144578314
ro
0.39320388349514557
tr
0.3872549019607844
es
0.3540051679586563
sl
0.32432432432432434
de
0.22360248447204967
ms
0.22360248447204967
be
0.21875
hu
0.21135646687697163
az
0.20127795527156547
et
0.20127795527156547
is
0.20127795527156547
lt
0.20127795527156547
uk
0.20127795527156547
reliable
true
passes
true
4
name
"Maria"
dialogue
"Sí, but... not much."
detectedLang
"en"
heavyLang
"en"
scores
en
0.803921568627451
tl
0.609375
yo
0.5967741935483871
ca
0.49748743718592964
es
0.49748743718592964
fr
0.46808510638297873
tr
0.43820224719101125
reliable
true
passes
false
5
name
"Hunter"
dialogue
"I'm Detective Hunter. I'm investigating some disappearances in town. Have you seen or heard anything unusual?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.8033098209441129
tl
0.6176160337552743
fr
0.5460237946149029
pt
0.5150501672240804
ro
0.5124411566913248
it
0.48654390934844194
nl
0.46808510638297873
ms
0.4273301737756714
ca
0.42551505546751184
de
0.42000000000000004
es
0.40476190476190477
sv
0.3808710503842869
da
0.377147766323024
sl
0.358974358974359
sq
0.3378995433789954
no
0.3317972350230415
cs
0.27860696517412936
hr
0.2720883534136546
et
0.24400417101147026
az
0.21790722761596548
lv
0.1657077100115075
is
0.15990730011587484
sk
0.15990730011587484
lt
0.14806110458284372
yo
0.1082410824108241
pl
0.103831891223733
fi
0.07525510204081631
tr
0.07525510204081631
reliable
true
passes
true
6
name
"Maria"
dialogue
"Sí, algo... algo extraño. Anoche, vi... vi algo."
detectedLang
"es"
heavyLang
"es"
scores
es
0.7601918465227818
sv
0.5249406175771971
pt
0.48586118251928023
ca
0.46808510638297873
fr
0.4594594594594595
it
0.45799457994579945
de
0.45054945054945056
yo
0.42528735632183906
da
0.4152046783625731
no
0.38650306748466257
vi
0.3333333333333333
en
0.2907801418439716
nl
0.2907801418439716
ro
0.2907801418439716
sk
0.2779783393501805
cs
0.25650557620817843
reliable
true
passes
true
7
name
"Hunter"
dialogue
"What did you see?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.8475609756097561
et
0.6296296296296297
cs
0.43820224719101125
tl
0.43820224719101125
reliable
true
passes
true
8
name
"Maria"
dialogue
"Un hombre... en el bosque. Él... él no era un hombre normal."
detectedLang
"es"
heavyLang
"es"
scores
es
0.8059508408796896
ca
0.7615262321144673
fr
0.6710526315789473
it
0.6309963099630996
ro
0.6254681647940075
pt
0.5522388059701493
lv
0.5488721804511278
tr
0.5305164319248826
en
0.5137763371150729
tl
0.5008319467554077
no
0.4991652754590985
eu
0.43396226415094336
nl
0.4140625
da
0.4129158512720157
sv
0.40828402366863903
ms
0.40119760479041916
hr
0.34782608695652173
sk
0.3333333333333333
fi
0.3288590604026846
is
0.3087557603686636
pl
0.3087557603686636
sl
0.3087557603686636
az
0.3071593533487298
de
0.3071593533487298
hu
0.29411764705882354
yo
0.26108374384236455
lt
0.17355371900826447
sq
0.17355371900826447
cs
0.16434540389972147
et
0.16434540389972147
reliable
true
passes
true
9
name
"Hunter"
dialogue
"What do you mean, 'not a normal man'?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.7926267281105991
pt
0.6559633027522936
cs
0.6411483253588517
tl
0.6256239600665559
sk
0.5879120879120879
de
0.5841035120147875
pl
0.5770676691729324
hr
0.563953488372093
ro
0.5508982035928144
ca
0.5445344129554657
sl
0.5445344129554657
es
0.5408163265306122
da
0.5398773006134969
sq
0.5283018867924528
sv
0.5253164556962026
lv
0.5212765957446809
lt
0.5150862068965517
nl
0.5044052863436124
no
0.5022123893805309
tr
0.49209932279909707
az
0.4742990654205608
yo
0.4668246445497631
ms
0.460431654676259
it
0.45520581113801456
vi
0.44581280788177335
fr
0.4444444444444444
hu
0.4094488188976378
eu
0.3784530386740331
fi
0.358974358974359
et
0.3515850144092219
is
0.25
reliable
true
passes
true
10
name
"Maria"
dialogue
"I gotta go. Can you meet me at the station later? We need to talk more."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8144531249999999
tl
0.6671338472319551
no
0.639331814730448
da
0.6203037569944045
nl
0.579273693534101
pl
0.5626151012891344
yo
0.5428296438883542
sv
0.5410628019323671
it
0.5108135942327497
fr
0.48759439050701187
sq
0.47339246119733924
hr
0.4546498277841562
cs
0.4424882629107981
sl
0.43113772455089816
et
0.42839951865222625
de
0.42073170731707316
fi
0.36155913978494625
sk
0.35636856368563685
lv
0.343015214384509
lt
0.33751743375174337
ms
0.31752873563218387
ca
0.3115942028985507
tr
0.302496328928047
az
0.2994100294985251
hu
0.2692307692307693
ro
0.2601246105919003
pt
0.250788643533123
es
0.17677642980935876
zh
0.1394927536231884
hi
0.13793103448275862
be
0.12844036697247707
is
0.1171003717472119
uk
0.1171003717472119
vi
0.1171003717472119
reliable
true
passes
false