NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-20-01KHXPSH205BXZ8QHRKMW2EC1J
Run Details
Model:
Mistral Large 3
Test:
Language Writing
Scenario:
Character dialogue (German) in a story
Duration:
11.8s
Cost:
$0.001026
Provider:
Mistral
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="Melanie"> Melanie is a 30-year old college student on a study abroad program. Born in Germany, she is fluent in German 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 German, 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: Melanie 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 German, and Hunter looks confused. They talk for a while, until Hunter gets a call and has to leave. Return the dialogue between Melanie and Hunter as a voice sheet: Melanie: "..." Hunter: "..."
Model response
Messages
Meta
AI
**Voice Sheet: Café Conversation** *(Melanie sits at a small outdoor table, her camera resting in her lap. She flips through the photos on the display, her expression troubled. Hunter approaches, his detective badge clipped to his belt, his posture rigid but not unkind.)* **Hunter:** *(clears throat, speaks slowly)* Excuse me. Mind if I sit for a minute? **Melanie:** *(startled, looks up, then nods hesitantly)* Ja… natürlich. *(Yes… of course.)* **Hunter:** *(pulls out the chair across from her, sits)* I’m Detective Hunter. I’m looking into some… unusual activity around town. You’ve been taking photos near the old orchard, right? **Melanie:** *(frowns, shakes her head slightly, then gestures toward her camera)* Ich verstehe nicht. *(I don’t understand.)* *(points to the orchard in the distance)* Die Bäume… sie sind anders. *(The trees… they’re different.)* **Hunter:** *(leans forward, trying to parse her words)* Different how? **Melanie:** *(flips through her camera, then turns the screen toward him, pointing at a photo of the orchard at dusk)* Sehen Sie? Keine Äpfel. Nur… Schatten. *(See? No apples. Only… shadows.)* *(shudders)* Und die Geräusche. *(And the sounds.)* **Hunter:** *(stares at the photo, then at her, frustration creeping in)* Ma’am, I don’t— **Melanie:** *(cuts him off, voice rising slightly)* Die Leute verschwinden. *(The people are disappearing.)* Ich habe es gehört. *(I’ve heard it.)* *(taps her camera)* Ich habe es gesehen. *(I’ve seen it.)* **Hunter:** *(rubs his temple, sighs)* Look, I’m trying to help, but I don’t speak German. Can you— **Melanie:** *(shakes her head, exasperated, then points to the orchard again)* Dort. *(There.)* Die Antwort ist dort. *(The answer is there.)* **Hunter:** *(phone rings—he pulls it out, glances at the screen, then stands abruptly)* I’ve gotta take this. *(points to her, then to the orchard)* Stay away from there, okay? It’s not safe. **Melanie:** *(stands as well, gripping her camera)* Aber— *(But—)* **Hunter:** *(already walking away, answering the call)* Hunter here. *(Melanie watches him go, then looks back at her camera, her fingers tightening around it. She mutters under her breath.)* **Melanie:** *(softly, to herself)* Ich muss es beweisen. *(I have to prove it.)*
created_at
"2026-02-20T14:20:51.66Z"
2/20/2026, 2:20:51 PM
model
"mistralai/mistral-large-2512"
1/1/2512, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
394
moderation_latency
(null)
generation_time
11681
tokens_prompt
319
tokens_completion
618
native_tokens_prompt
273
native_tokens_completion
593
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
0.001026
router
(null)
provider_responses
0
endpoint_id
"fa718841-07ea-4b7e-b8a3-6069545c7e6a"
id
"9c1624597b6f41b685192fab5cacb14e"
is_byok
false
latency
394
model_permaslug
"mistralai/mistral-large-2512"
1/1/2512, 12:00:00 AM
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771597251-OrkpAR2TRr2NzPDhu5mH"
upstream_id
"9c1624597b6f41b685192fab5cacb14e"
total_cost
0.001026
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Parse dialogue
n/a
dialogue
0
name
"Hunter"
dialogue
"Excuse me. Mind if I sit for a minute?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.753584229390681
no
0.6964679911699779
da
0.6733966745843231
it
0.626358695652174
et
0.6206896551724138
sq
0.6026011560693642
hr
0.5877061469265367
ro
0.5852187028657617
pt
0.5782208588957055
sv
0.5743034055727554
ca
0.5571658615136876
sl
0.5409015025041736
cs
0.5315161839863715
hu
0.5307167235494881
tl
0.5274914089347079
es
0.5225694444444445
pl
0.5166959578207382
sk
0.5018115942028986
fr
0.4963369963369963
nl
0.4410569105691057
fi
0.43298969072164945
de
0.43064182194616984
lt
0.43064182194616984
ms
0.42827442827442824
yo
0.42827442827442824
tr
0.3483412322274882
is
0.3341404358353511
az
0.32598039215686275
lv
0.32598039215686275
vi
0.32598039215686275
be
0.20289855072463767
eu
0.20289855072463767
uk
0.1863905325443787
reliable
true
passes
true
1
name
"Melanie"
dialogue
"Ja… natürlich."
detectedLang
"de"
heavyLang
"de"
scores
de
0.8281786941580757
et
0.6062992125984252
fi
0.6047430830039525
sq
0.6047430830039525
lv
0.5348837209302325
ca
0.5215311004784688
tr
0.5
sk
0.45652173913043476
da
0.4444444444444444
pl
0.4444444444444444
sl
0.4444444444444444
cs
0.43820224719101125
sv
0.42857142857142855
yo
0.42857142857142855
reliable
true
passes
true
2
name
"Hunter"
dialogue
"I’m Detective Hunter. I’m looking into some… unusual activity around town. You’ve been taking photos near the old orchard, right?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.804872280037843
tl
0.6375219683655536
fr
0.5247695852534562
nl
0.43376801647220314
no
0.3986880466472303
pt
0.39692982456140347
de
0.39159292035398224
ro
0.3692660550458715
ca
0.3644067796610169
es
0.3431528662420382
da
0.3159203980099502
sq
0.30613961312026916
sv
0.2948717948717949
it
0.26601423487544484
ms
0.25742574257425743
et
0.22169811320754715
cs
0.20212765957446807
sk
0.20135527589545013
tr
0.19825072886297376
sl
0.19275929549902154
yo
0.17992047713717693
fi
0.15123456790123457
lv
0.1397288842544317
pl
0.11385606874328678
lt
0.08839779005524862
hi
0.08536585365853659
is
0.07924107142857142
hr
0.07511210762331838
reliable
true
passes
true
3
name
"Melanie"
dialogue
"Ich verstehe nicht. Die Bäume… sie sind anders."
detectedLang
"de"
heavyLang
"de"
scores
de
0.8358585858585857
nl
0.6564482029598308
sv
0.4337979094076655
no
0.4196428571428571
pl
0.411231884057971
da
0.3959107806691449
en
0.3298969072164949
fr
0.2919389978213508
ca
0.2857142857142857
sk
0.27616926503340755
cs
0.23529411764705882
et
0.23529411764705882
yo
0.21307506053268765
lt
0.19154228855721395
hu
0.181360201511335
it
0.181360201511335
tl
0.1792929292929293
is
0.1709183673469388
es
0.16237113402061853
pt
0.16237113402061853
az
0.15364583333333331
ro
0.15364583333333331
sq
0.15364583333333331
reliable
true
passes
true
4
name
"Hunter"
dialogue
"Different how?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.823321554770318
fr
0.6805111821086262
it
0.6515679442508711
ca
0.6062992125984252
no
0.45652173913043476
ro
0.45652173913043476
nl
0.42857142857142855
hr
0.4117647058823529
tl
0.4117647058823529
cs
0.38650306748466257
de
0.38650306748466257
es
0.38650306748466257
lt
0.38650306748466257
lv
0.38650306748466257
pl
0.38650306748466257
sk
0.38650306748466257
sl
0.38650306748466257
sq
0.38650306748466257
reliable
true
passes
true
5
name
"Melanie"
dialogue
"Sehen Sie? Keine Äpfel. Nur… Schatten. Und die Geräusche."
detectedLang
"de"
heavyLang
"de"
scores
de
0.8324958123953099
nl
0.631336405529954
fi
0.40476190476190477
no
0.4038748137108793
sv
0.3265993265993266
da
0.3185689948892675
tr
0.3174061433447099
ms
0.3079584775086505
it
0.28825622775800713
eu
0.22330097087378642
pl
0.21875
is
0.21568627450980393
et
0.18699186991869918
fr
0.18699186991869918
yo
0.18032786885245902
en
0.17012448132780084
az
0.16142557651991615
reliable
true
passes
true
6
name
"Hunter"
dialogue
"Ma’am, I don’t—"
detectedLang
"en"
heavyLang
"en"
scores
en
0.7459349593495935
tl
0.6438746438746439
no
0.5370370370370371
da
0.5265151515151516
hr
0.5265151515151516
ca
0.5247148288973384
sv
0.5247148288973384
sq
0.5173745173745175
pl
0.50199203187251
it
0.4791666666666667
cs
0.45652173913043476
ro
0.4186046511627907
yo
0.410377358490566
sk
0.3654822335025381
be
0.358974358974359
tr
0.358974358974359
hu
0.34895833333333337
az
0.33510638297872336
et
0.33510638297872336
is
0.33510638297872336
lt
0.33510638297872336
lv
0.33510638297872336
uk
0.33510638297872336
vi
0.33510638297872336
reliable
true
passes
true
7
name
"Melanie"
dialogue
"Die Leute verschwinden. Ich habe es gehört. Ich habe es gesehen."
detectedLang
"de"
heavyLang
"de"
scores
de
0.8364485981308412
nl
0.5111731843575419
ca
0.4664634146341463
es
0.453125
hu
0.44267515923566875
sv
0.4299674267100977
tr
0.3738819320214669
lt
0.32432432432432434
no
0.3055555555555556
sq
0.2842535787321063
sk
0.26160337552742613
da
0.26004228329809725
lv
0.25531914893617025
eu
0.24731182795698922
pl
0.24731182795698922
fi
0.2009132420091324
yo
0.2009132420091324
it
0.17061611374407584
is
0.1606714628297362
en
0.15254237288135594
fr
0.15254237288135594
pt
0.15254237288135594
az
0.14425427872860636
ro
0.14425427872860636
reliable
true
passes
true
8
name
"Hunter"
dialogue
"Look, I’m trying to help, but I don’t speak German. Can you—"
detectedLang
"en"
heavyLang
"en"
scores
en
0.8282828282828283
tl
0.7064917127071823
cs
0.42489851150202973
ca
0.4129834254143646
pl
0.380466472303207
hr
0.375
no
0.37407952871870404
ro
0.371301775147929
da
0.36377245508982037
yo
0.34514637904468415
tr
0.33800623052959505
az
0.33070866141732286
sv
0.3285939968404423
sk
0.32432432432432434
sq
0.32432432432432434
it
0.3189102564102564
lv
0.30327868852459017
lt
0.28209459459459457
sl
0.2216117216117216
fr
0.17153996101364524
nl
0.1550695825049702
de
0.15
be
0.1414141414141414
es
0.1414141414141414
ms
0.1414141414141414
hu
0.1361788617886179
et
0.1290983606557377
is
0.1290983606557377
uk
0.1290983606557377
vi
0.1290983606557377
reliable
true
passes
true
9
name
"Melanie"
dialogue
"Dort. Die Antwort ist dort."
detectedLang
"de"
heavyLang
"de"
scores
de
0.8479318734793188
nl
0.6890547263681591
hi
0.4588744588744588
tr
0.4292237442922375
yo
0.4131455399061033
reliable
true
passes
true
10
name
"Hunter"
dialogue
"I’ve gotta take this. Stay away from there, okay? It’s not safe."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8110533774208786
tl
0.6842936069455406
it
0.3311036789297659
de
0.3079584775086505
fi
0.21875
hu
0.2125984251968504
nl
0.19839679358717435
sl
0.16317991631799164
sq
0.16317991631799164
tr
0.16317991631799164
sv
0.16142557651991615
reliable
true
passes
true
11
name
"Melanie"
dialogue
"Aber—"
detectedLang
"de"
heavyLang
"de"
scores
de
0.868421052631579
reliable
false
passes
true
12
name
"Hunter"
dialogue
"Hunter here."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8036649214659686
sq
0.6794871794871795
de
0.5398773006134969
da
0.5222929936305732
no
0.5098039215686274
fr
0.4897959183673469
sv
0.4827586206896552
tl
0.471830985915493
it
0.45652173913043476
nl
0.45652173913043476
pt
0.45652173913043476
ca
0.44029850746268656
ms
0.44029850746268656
ro
0.44029850746268656
sl
0.44029850746268656
tr
0.44029850746268656
reliable
true
passes
true
13
name
"Melanie"
dialogue
"Ich muss es beweisen."
detectedLang
"de"
heavyLang
"de"
scores
de
0.8318385650224215
fi
0.6332518337408314
ca
0.494949494949495
es
0.494949494949495
sk
0.45255474452554745
lv
0.4444444444444444
nl
0.4444444444444444
pl
0.43396226415094336
da
0.42528735632183906
sv
0.4140625
hu
0.40476190476190477
no
0.39271255060728744
lt
0.3775933609958506
reliable
true
passes
true