NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHXQ2VKVEFXCZE4FRMM6JN9Z
Run Details
Model:
Mistral Large 3
Test:
Language Writing
Scenario:
Character dialogue (Spanish) in a story
Duration:
16.5s
Cost:
$0.001404
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
85.71%
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: Café Conversation in Alborn, MN** *(The café is quiet, the hum of conversation and clinking of coffee cups filling the air. Maria sits at a small corner table, her camera resting in front of her as she scrolls through the photos she’s taken. The door chimes as Hunter enters, scanning the room before his gaze lands on her. He approaches, his expression serious but not unkind.)* **Hunter:** *(clears throat, standing beside her table)* Excuse me, miss. Mind if I sit for a moment? **Maria:** *(looks up, startled, then offers a small, polite smile)* Ah—sí, claro. *(gestures to the empty chair across from her, then hesitates, realizing he might not understand)* Um… por favor? **Hunter:** *(nods, taking the seat)* Thanks. I’m Detective Hunter Cole. I’m looking into some… unusual activity around town. *(leans forward slightly, keeping his voice low)* I noticed you’ve been taking a lot of photos. You’ve been around the orchards and the old mill, right? **Maria:** *(frowns, her fingers tightening around her camera)* ¿El molino? *(shakes her head, her voice trembling slightly)* No entiendo… ¿qué pasa? *(glances around nervously, then back at him)* ¿Por qué me pregunta? **Hunter:** *(blinks, clearly not understanding)* Uh… I’m sorry, I don’t speak Spanish. *(rubs the back of his neck, frustrated with himself)* Look, I’m just trying to figure out if you’ve seen anything strange. People going missing, things out of place… *(trails off at her expression)* **Maria:** *(her breath hitches, her eyes widening)* ¡Dios mío! *(presses a hand to her chest, her words spilling out rapidly)* Yo vi algo… anoche. En el bosque cerca del molino. Había luces, como… como faros, pero no eran coches. Y luego—*(cuts herself off, shaking her head)* No sé. No sé qué era. **Hunter:** *(leans in, trying to piece together her words)* Lights? Near the mill? *(mimics holding a camera, then points to her)* You took pictures? **Maria:** *(nods eagerly, flipping through her camera and turning the screen toward him)* ¡Sí, sí! Aquí. *(points to a blurry image of distant, flickering lights between the trees)* Pero no sé qué es. Pensé que era… no sé, un reflejo o algo. **Hunter:** *(studies the photo, his jaw tightening)* That’s not a reflection. *(glances up at her, his tone softening)* You shouldn’t go back there alone, okay? It’s not safe. **Maria:** *(swallows hard, her voice barely above a whisper)* ¿Por qué? ¿Qué está pasando? **Hunter:** *(hesitates, then shakes his head)* I can’t say yet. But I need you to be careful. *(pulls out a business card and sets it on the table, pointing to it)* If you see anything else—anything at all—call me. *(mimes a phone to his ear)* ¿Entiende? **Maria:** *(nods, taking the card with shaky fingers)* Sí. Entiendo. *(looks up at him, her dark eyes filled with worry)* Pero… ¿está en peligro la gente? **Hunter:** *(phone buzzes in his pocket; he pulls it out, glancing at the screen, then stands abruptly)* I’ve gotta go. *(meets her gaze, his voice firm but not unkind)* Stay out of the woods, okay? And call me if you see anything. **Maria:** *(watches him leave, her fingers tracing the edge of the business card)* *(softly, to herself)* Dios mío, ¿en qué me he metido? *(Hunter exits the café, already speaking into his phone as the door swings shut behind him.)*
created_at
"2026-02-20T14:25:57.382Z"
2/20/2026, 2:25:57 PM
model
"mistralai/mistral-large-2512"
1/1/2512, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
745
moderation_latency
(null)
generation_time
16443
tokens_prompt
317
tokens_completion
905
native_tokens_prompt
269
native_tokens_completion
846
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0014035
router
(null)
provider_responses
0
endpoint_id
"fa718841-07ea-4b7e-b8a3-6069545c7e6a"
id
"b2abba67737b4d2796e78692cd183de9"
is_byok
false
latency
745
model_permaslug
"mistralai/mistral-large-2512"
1/1/2512, 12:00:00 AM
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771597557-zCZ6izQVLdOAS0i58R1T"
upstream_id
"b2abba67737b4d2796e78692cd183de9"
total_cost
0.0014035
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
85.71%
Parse dialogue
n/a
dialogue
0
name
"Hunter"
dialogue
"** Excuse me, miss. Mind if I sit for a moment?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.7647058823529411
no
0.6777658431793769
da
0.6539792387543253
sq
0.6216897856242118
ca
0.6163682864450128
tl
0.5896032831737346
fr
0.5786516853932584
it
0.574468085106383
pt
0.5708154506437768
ro
0.5708154506437768
hu
0.5548961424332344
pl
0.5522388059701493
cs
0.5488721804511278
sv
0.5481927710843374
sk
0.5290423861852434
es
0.5176848874598071
nl
0.512987012987013
hr
0.511400651465798
et
0.5073891625615764
yo
0.4727592267135325
de
0.40828402366863903
az
0.3951612903225807
sl
0.3723849372384937
ms
0.3288590604026846
tr
0.3288590604026846
lt
0.3258426966292135
fi
0.3150684931506849
is
0.3150684931506849
lv
0.3071593533487298
vi
0.3071593533487298
be
0.1891891891891892
eu
0.1891891891891892
uk
0.17355371900826447
reliable
true
passes
true
1
name
"Maria"
dialogue
"** Um… por favor?"
detectedLang
"pt"
heavyLang
"pt"
scores
pt
0.8181818181818182
es
0.7584541062801933
sq
0.6610169491525424
is
0.609375
ca
0.6
de
0.5689655172413793
it
0.43820224719101125
en
0.4186046511627907
fr
0.4186046511627907
ro
0.4186046511627907
da
0.3939393939393939
nl
0.3939393939393939
no
0.3939393939393939
sl
0.3939393939393939
sv
0.3939393939393939
reliable
true
passes
false
2
name
"Hunter"
dialogue
"** I noticed you’ve been taking a lot of photos. You’ve been around the orchards and the old mill, right?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.8070987654320988
tl
0.6664887940234792
fr
0.5236280487804877
no
0.5055379746835442
yo
0.48937908496732024
nl
0.4202226345083488
de
0.4186046511627907
da
0.4120413922859831
pt
0.3686868686868687
sq
0.36224489795918363
sv
0.358974358974359
sk
0.35699588477366256
ca
0.3556701030927836
pl
0.3503118503118503
it
0.3448637316561845
lv
0.3407172995780591
es
0.32505399568034554
is
0.3228602383531961
hr
0.2865296803652968
cs
0.27494199535962877
tr
0.2715617715617716
ro
0.2681498829039813
lt
0.2647058823529412
hu
0.26297169811320753
et
0.23965936739659366
sl
0.20483460559796438
fi
0.18619791666666666
ms
0.18407310704960833
az
0.17546174142480211
vi
0.17546174142480211
hi
0.10968660968660969
be
0.10071942446043164
eu
0.10071942446043164
uk
0.09156976744186046
reliable
true
passes
true
3
name
"Maria"
dialogue
"** ¿Por qué me pregunta?"
detectedLang
"es"
heavyLang
"es"
scores
es
0.8164014687882496
pt
0.7252747252747253
sq
0.6495327102803737
ca
0.6445497630331753
it
0.6124031007751938
sl
0.5412844036697247
fi
0.5356037151702787
ro
0.5283018867924528
no
0.5238095238095238
et
0.3877551020408163
tl
0.38524590163934425
fr
0.3775933609958506
en
0.3697478991596639
ms
0.358974358974359
nl
0.358974358974359
hr
0.3562231759656652
reliable
true
passes
true
4
name
"Hunter"
dialogue
"**"
detectedLang
""
heavyLang
""
scores
reliable
false
passes
true
5
name
"Maria"
dialogue
"** No sé. No sé qué era."
detectedLang
"es"
heavyLang
"es"
scores
es
0.8191681735985533
ca
0.7590361445783133
it
0.7252747252747253
pt
0.7032640949554896
en
0.6376811594202898
lv
0.5670995670995671
is
0.5515695067264574
ro
0.504950495049505
hr
0.5024875621890548
no
0.49238578680203043
sk
0.47643979057591623
eu
0.46808510638297873
tr
0.46808510638297873
yo
0.46236559139784944
tl
0.4444444444444444
pl
0.42857142857142855
ms
0.4186046511627907
reliable
true
passes
true
6
name
"Hunter"
dialogue
"** You took pictures?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.810318664643399
tl
0.647887323943662
fr
0.6056782334384858
ca
0.576271186440678
ro
0.5487364620938628
et
0.43946188340807174
lv
0.39903846153846156
cs
0.3842364532019704
da
0.3654822335025381
de
0.3654822335025381
nl
0.3654822335025381
no
0.3654822335025381
sv
0.3654822335025381
reliable
true
passes
true
7
name
"Maria"
dialogue
"** Pero no sé qué es. Pensé que era… no sé, un reflejo o algo."
detectedLang
"es"
heavyLang
"es"
scores
es
0.8178032274856845
ca
0.7491039426523297
pt
0.7000856898029134
it
0.6288441145281017
lv
0.5828367103694875
ro
0.5569620253164557
fr
0.5172413793103449
tl
0.49275362318840576
yo
0.48224852071005914
lt
0.4308943089430894
en
0.4186046511627907
hr
0.3761140819964349
sk
0.37163375224416517
pl
0.35424354243542433
tr
0.3346007604562738
az
0.3217054263565891
no
0.3110236220472441
de
0.29006085192697767
ms
0.2753623188405797
is
0.26004228329809725
cs
0.2456896551724138
sl
0.2290748898678414
hu
0.22566371681415928
eu
0.2009132420091324
sq
0.1784037558685446
et
0.16864608076009502
da
0.1484184914841849
nl
0.1484184914841849
sv
0.1484184914841849
reliable
true
passes
true
8
name
"Hunter"
dialogue
"** You shouldn’t go back there alone, okay? It’s not safe."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8170173833485819
tl
0.6652719665271967
pl
0.3162393162393162
de
0.3079584775086505
tr
0.3079584775086505
nl
0.19839679358717435
it
0.17864476386036962
cs
0.16317991631799164
sq
0.16317991631799164
fr
0.16142557651991615
yo
0.16142557651991615
reliable
true
passes
true
9
name
"Maria"
dialogue
"** ¿Por qué? ¿Qué está pasando?"
detectedLang
"es"
heavyLang
"es"
scores
es
0.8407643312101911
pt
0.7832369942196532
sq
0.5726495726495726
tl
0.5356037151702787
it
0.46619217081850534
lt
0.44649446494464945
ca
0.43396226415094336
lv
0.40476190476190477
ms
0.39271255060728744
eu
0.38524590163934425
cs
0.3670886075949367
sk
0.33920704845814975
pl
0.3212669683257918
ro
0.3212669683257918
reliable
true
passes
true
10
name
"Hunter"
dialogue
"** ¿Entiende?"
detectedLang
"es"
heavyLang
"es"
scores
es
0.7875354107648725
nl
0.7262773722627737
et
0.704724409448819
pt
0.6951219512195121
fr
0.6822033898305085
da
0.6359223300970874
no
0.6134020618556701
de
0.5856353591160222
it
0.5535714285714286
sv
0.5535714285714286
en
0.5481927710843374
fi
0.5481927710843374
eu
0.5370370370370371
ca
0.5283018867924528
sq
0.506578947368421
reliable
true
passes
false
11
name
"Maria"
dialogue
"** Pero… ¿está en peligro la gente?"
detectedLang
"es"
heavyLang
"es"
scores
es
0.8366013071895425
pt
0.6813031161473088
tl
0.660633484162896
ca
0.6590909090909091
fr
0.6445497630331753
it
0.6262458471760797
no
0.5802238805970149
da
0.5738636363636364
ro
0.53125
nl
0.5212765957446809
fi
0.44717444717444715
sq
0.4201030927835051
eu
0.40476190476190477
sk
0.39839572192513373
sv
0.3967828418230563
is
0.3732590529247911
tr
0.3283582089552239
yo
0.2902208201892744
cs
0.27884615384615385
vi
0.27184466019417475
de
0.25742574257425743
ms
0.2549668874172185
sl
0.25
reliable
true
passes
true
12
name
"Hunter"
dialogue
"** Stay out of the woods, okay? And call me if you see anything."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8315789473684211
tl
0.6694214876033058
sq
0.4490358126721763
yo
0.44367176634214184
nl
0.42363112391930835
no
0.4117647058823529
et
0.39849624060150374
ms
0.375
sv
0.3079584775086505
fr
0.29701230228471004
es
0.20318725099601595
is
0.18200408997955012
pt
0.18032786885245902
sl
0.18032786885245902
de
0.17184265010351968
it
0.16666666666666666
cs
0.16317991631799164
da
0.16317991631799164
fi
0.15789473684210525
reliable
true
passes
true
13
name
"Maria"
dialogue
"** Dios mío, ¿en qué me he metido?"
detectedLang
"es"
heavyLang
"es"
scores
es
0.7799779977997799
fi
0.5555555555555556
ca
0.5444191343963554
fr
0.5423340961098398
nl
0.5423340961098398
no
0.5348837209302325
en
0.5271867612293144
tr
0.5121951219512195
pt
0.49238578680203043
sl
0.4490358126721763
tl
0.43342776203966005
da
0.42528735632183906
sq
0.42528735632183906
sv
0.42528735632183906
is
0.40119760479041916
yo
0.33774834437086093
lt
0.3333333333333333
et
0.3220338983050847
ms
0.29577464788732394
it
0.2857142857142857
eu
0.2727272727272727
reliable
true
passes
true